{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling","name":"Language Modeling","slug":"language-modeling","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":14182,"papers_with_code":5620,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[{"url":"/task/dream-generation","name":"Dream Generation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":142,"rows_per_page":100,"shown":100,"of":14182,"of_with_code":5620,"tagged_in_all":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1511,"every_run_a_failure_of_syntologys_instrument":383,"listed_with_a_run_with_no_instrument_failure":1511,"listed_every_run_a_failure_of_syntologys_instrument":383,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/semi-supervised-sequence-learning","slug":"semi-supervised-sequence-learning","title":"Semi-supervised Sequence Learning","date":"2015-11-04","arxiv_id":"1511.01432","repositories_listed":161,"syntology":null},{"url":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_honours":3,"n_violates":2,"n_no_contract":32,"n_pointer_only":7,"phrase":"45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}},"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":37,"n_constructed":11,"n_ran_checked":36,"n_instrument":1,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":34,"n_pointer_only":24,"phrase":"37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}},"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/universal-language-model-fine-tuning-for-text","slug":"universal-language-model-fine-tuning-for-text","title":"Universal Language Model Fine-tuning for Text Classification","date":"2018-01-18","arxiv_id":"1801.06146","repositories_listed":66,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/universal-language-model-fine-tuning-for-text#ran","syntology_url":"https://syntology.ai/paper/1801.06146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.06146"}},"official":{"repos":["fastai/fastai"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/darts-differentiable-architecture-search","slug":"darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","arxiv_id":"1806.09055","repositories_listed":59,"syntology":{"n":156,"n_ran":74,"n_constructed":30,"n_ran_checked":59,"n_instrument":15,"n_unverified":82,"n_honours":10,"n_violates":1,"n_no_contract":48,"n_pointer_only":54,"phrase":"74 ran (of which 30 constructed an object rather than computing a result; 59 with no instrument failure: 10 honoured, 1 violated, 48 with no contract checked; 15 where Syntology's instrument failed) · 82 unverified","sample_list":"/paper/darts-differentiable-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1806.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.09055"}},"official":{"repos":["quark0/darts"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-contextualized-word-representations","slug":"deep-contextualized-word-representations","title":"Deep contextualized word representations","date":"2018-02-15","arxiv_id":"1802.05365","repositories_listed":46,"syntology":{"n":58,"n_ran":30,"n_constructed":12,"n_ran_checked":24,"n_instrument":6,"n_unverified":28,"n_honours":2,"n_violates":0,"n_no_contract":22,"n_pointer_only":25,"phrase":"30 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 28 unverified","sample_list":"/paper/deep-contextualized-word-representations#ran","syntology_url":"https://syntology.ai/paper/1802.05365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05365"}},"official":null}},{"url":"/paper/regularizing-and-optimizing-lstm-language","slug":"regularizing-and-optimizing-lstm-language","title":"Regularizing and Optimizing LSTM Language Models","date":"2017-08-07","arxiv_id":"1708.02182","repositories_listed":45,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/regularizing-and-optimizing-lstm-language#ran","syntology_url":"https://syntology.ai/paper/1708.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02182"}},"official":{"repos":["salesforce/awd-lstm-lm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/end-to-end-memory-networks","slug":"end-to-end-memory-networks","title":"End-To-End Memory Networks","date":"2015-03-31","arxiv_id":"1503.08895","repositories_listed":44,"syntology":{"n":15,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/end-to-end-memory-networks#ran","syntology_url":"https://syntology.ai/paper/1503.08895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.08895"}},"official":{"repos":["facebook/MemNN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/listen-attend-and-spell","slug":"listen-attend-and-spell","title":"Listen, Attend and Spell","date":"2015-08-05","arxiv_id":"1508.01211","repositories_listed":40,"syntology":{"n":51,"n_ran":30,"n_constructed":0,"n_ran_checked":20,"n_instrument":10,"n_unverified":21,"n_honours":1,"n_violates":1,"n_no_contract":18,"n_pointer_only":9,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 10 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/listen-attend-and-spell#ran","syntology_url":"https://syntology.ai/paper/1508.01211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.01211"}},"official":null}},{"url":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","repositories_listed":37,"syntology":{"n":27,"n_ran":21,"n_constructed":5,"n_ran_checked":12,"n_instrument":9,"n_unverified":6,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/distilbert-a-distilled-version-of-bert#ran","syntology_url":"https://syntology.ai/paper/1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}},"official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","repositories_listed":37,"syntology":{"n":143,"n_ran":67,"n_constructed":37,"n_ran_checked":49,"n_instrument":18,"n_unverified":76,"n_honours":4,"n_violates":1,"n_no_contract":44,"n_pointer_only":43,"phrase":"67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified","sample_list":"/paper/transformer-xl-attentive-language-models#ran","syntology_url":"https://syntology.ai/paper/1901.02860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02860"}},"official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/mamba-linear-time-sequence-modeling-with","slug":"mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","repositories_listed":35,"syntology":{"n":62,"n_ran":28,"n_constructed":7,"n_ran_checked":20,"n_instrument":8,"n_unverified":34,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":29,"phrase":"28 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 34 unverified","sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}},"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unsupervised-cross-lingual-representation-1","slug":"unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","arxiv_id":"1911.02116","repositories_listed":35,"syntology":{"n":59,"n_ran":40,"n_constructed":13,"n_ran_checked":35,"n_instrument":5,"n_unverified":19,"n_honours":4,"n_violates":1,"n_no_contract":30,"n_pointer_only":52,"phrase":"40 ran (of which 13 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/unsupervised-cross-lingual-representation-1#ran","syntology_url":"https://syntology.ai/paper/1911.02116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02116"}},"official":{"repos":["facebookresearch/cc_net","facebookresearch/XLM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/specaugment-a-simple-data-augmentation-method","slug":"specaugment-a-simple-data-augmentation-method","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","date":"2019-04-18","arxiv_id":"1904.08779","repositories_listed":30,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}},"official":null}},{"url":"/paper/direct-preference-optimization-your-language","slug":"direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","arxiv_id":"2305.18290","repositories_listed":29,"syntology":{"n":31,"n_ran":25,"n_constructed":1,"n_ran_checked":21,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":2,"phrase":"25 ran (of which 1 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/direct-preference-optimization-your-language#ran","syntology_url":"https://syntology.ai/paper/2305.18290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18290"}},"official":null}},{"url":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","repositories_listed":27,"syntology":{"n":24,"n_ran":15,"n_constructed":2,"n_ran_checked":10,"n_instrument":5,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}},"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/matching-networks-for-one-shot-learning","slug":"matching-networks-for-one-shot-learning","title":"Matching Networks for One Shot Learning","date":"2016-06-13","arxiv_id":"1606.04080","repositories_listed":26,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/matching-networks-for-one-shot-learning#ran","syntology_url":"https://syntology.ai/paper/1606.04080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04080"}},"official":null}},{"url":"/paper/conformer-convolution-augmented-transformer","slug":"conformer-convolution-augmented-transformer","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","date":"2020-05-16","arxiv_id":"2005.08100","repositories_listed":25,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conformer-convolution-augmented-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}},"official":null}},{"url":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","repositories_listed":22,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for#ran","syntology_url":"https://syntology.ai/paper/2101.00027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00027"}},"official":{"repos":["EleutherAI/The-Pile"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","repositories_listed":22,"syntology":{"n":35,"n_ran":22,"n_constructed":4,"n_ran_checked":14,"n_instrument":8,"n_unverified":13,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":5,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/longformer-the-long-document-transformer#ran","syntology_url":"https://syntology.ai/paper/2004.05150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05150"}},"official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/on-the-variance-of-the-adaptive-learning-rate","slug":"on-the-variance-of-the-adaptive-learning-rate","title":"On the Variance of the Adaptive Learning Rate and Beyond","date":"2019-08-08","arxiv_id":"1908.03265","repositories_listed":21,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-variance-of-the-adaptive-learning-rate#ran","syntology_url":"https://syntology.ai/paper/1908.03265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03265"}},"official":{"repos":["LiyuanLucasLiu/RAdam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/recurrent-neural-network-regularization","slug":"recurrent-neural-network-regularization","title":"Recurrent Neural Network Regularization","date":"2014-09-08","arxiv_id":"1409.2329","repositories_listed":21,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/recurrent-neural-network-regularization#ran","syntology_url":"https://syntology.ai/paper/1409.2329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1409.2329"}},"official":{"repos":["wojzaremba/lstm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_constructed":10,"n_ran_checked":12,"n_instrument":5,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}},"official":{"repos":["kzl/decision-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","repositories_listed":19,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-thought-prompting-elicits-reasoning#ran","syntology_url":"https://syntology.ai/paper/2201.11903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11903"}},"official":null}},{"url":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","repositories_listed":19,"syntology":{"n":40,"n_ran":31,"n_constructed":7,"n_ran_checked":18,"n_instrument":13,"n_unverified":9,"n_honours":2,"n_violates":2,"n_no_contract":14,"n_pointer_only":10,"phrase":"31 ran (of which 7 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 2 violated, 14 with no contract checked; 13 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/electra-pre-training-text-encoders-as-1#ran","syntology_url":"https://syntology.ai/paper/2003.10555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10555"}},"official":{"repos":["google-research/electra"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/variational-autoencoders-for-collaborative","slug":"variational-autoencoders-for-collaborative","title":"Variational Autoencoders for Collaborative Filtering","date":"2018-02-16","arxiv_id":"1802.05814","repositories_listed":18,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/variational-autoencoders-for-collaborative#ran","syntology_url":"https://syntology.ai/paper/1802.05814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05814"}},"official":{"repos":["dawenl/vae_cf"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-curious-case-of-neural-text-degeneration","slug":"the-curious-case-of-neural-text-degeneration","title":"The Curious Case of Neural Text Degeneration","date":"2019-04-22","arxiv_id":"1904.09751","repositories_listed":17,"syntology":{"n":17,"n_ran":10,"n_constructed":1,"n_ran_checked":5,"n_instrument":5,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/the-curious-case-of-neural-text-degeneration#ran","syntology_url":"https://syntology.ai/paper/1904.09751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09751"}},"official":{"repos":["ari-holtzman/degen"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","repositories_listed":17,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-lingual-language-model-pretraining#ran","syntology_url":"https://syntology.ai/paper/1901.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07291"}},"official":null}},{"url":"/paper/knowing-when-to-look-adaptive-attention-via-a","slug":"knowing-when-to-look-adaptive-attention-via-a","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","date":"2016-12-06","arxiv_id":"1612.01887","repositories_listed":17,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowing-when-to-look-adaptive-attention-via-a#ran","syntology_url":"https://syntology.ai/paper/1612.01887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01887"}},"official":{"repos":["jiasenlu/AdaptiveAttention"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/generating-sentences-from-a-continuous-space","slug":"generating-sentences-from-a-continuous-space","title":"Generating Sentences from a Continuous Space","date":"2015-11-19","arxiv_id":"1511.06349","repositories_listed":17,"syntology":{"n":31,"n_ran":14,"n_constructed":6,"n_ran_checked":12,"n_instrument":2,"n_unverified":17,"n_honours":2,"n_violates":1,"n_no_contract":9,"n_pointer_only":19,"phrase":"14 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/generating-sentences-from-a-continuous-space#ran","syntology_url":"https://syntology.ai/paper/1511.06349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06349"}},"official":null}},{"url":"/paper/how-to-fine-tune-bert-for-text-classification","slug":"how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","arxiv_id":"1905.05583","repositories_listed":15,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/how-to-fine-tune-bert-for-text-classification#ran","syntology_url":"https://syntology.ai/paper/1905.05583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05583"}},"official":{"repos":["xuyige/BERT4doc-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evaluation-of-sentence-embeddings-in","slug":"evaluation-of-sentence-embeddings-in","title":"Evaluation of sentence embeddings in downstream and linguistic probing tasks","date":"2018-06-16","arxiv_id":"1806.06259","repositories_listed":14,"syntology":null},{"url":"/paper/improved-training-of-end-to-end-attention","slug":"improved-training-of-end-to-end-attention","title":"Improved training of end-to-end attention models for speech recognition","date":"2018-05-08","arxiv_id":"1805.03294","repositories_listed":14,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improved-training-of-end-to-end-attention#ran","syntology_url":"https://syntology.ai/paper/1805.03294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.03294"}},"official":null}},{"url":"/paper/improving-neural-language-models-with-a","slug":"improving-neural-language-models-with-a","title":"Improving Neural Language Models with a Continuous Cache","date":"2016-12-13","arxiv_id":"1612.04426","repositories_listed":14,"syntology":null},{"url":"/paper/character-aware-neural-language-models","slug":"character-aware-neural-language-models","title":"Character-Aware Neural Language Models","date":"2015-08-26","arxiv_id":"1508.06615","repositories_listed":14,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/character-aware-neural-language-models#ran","syntology_url":"https://syntology.ai/paper/1508.06615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.06615"}},"official":{"repos":["yoonkim/lstm-char-cnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deepwalk-online-learning-of-social","slug":"deepwalk-online-learning-of-social","title":"DeepWalk: Online Learning of Social Representations","date":"2014-03-26","arxiv_id":"1403.6652","repositories_listed":14,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepwalk-online-learning-of-social#ran","syntology_url":"https://syntology.ai/paper/1403.6652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1403.6652"}},"official":null}},{"url":"/paper/vmamba-visual-state-space-model","slug":"vmamba-visual-state-space-model","title":"VMamba: Visual State Space Model","date":"2024-01-18","arxiv_id":"2401.10166","repositories_listed":13,"syntology":{"n":46,"n_ran":32,"n_constructed":6,"n_ran_checked":22,"n_instrument":10,"n_unverified":14,"n_honours":6,"n_violates":1,"n_no_contract":15,"n_pointer_only":14,"phrase":"32 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 10 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/vmamba-visual-state-space-model#ran","syntology_url":"https://syntology.ai/paper/2401.10166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10166"}},"official":{"repos":["mzeromiko/vmamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","repositories_listed":13,"syntology":{"n":39,"n_ran":26,"n_constructed":0,"n_ran_checked":22,"n_instrument":4,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/evaluating-large-language-models-trained-on#ran","syntology_url":"https://syntology.ai/paper/2107.03374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03374"}},"official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/tokens-to-token-vit-training-vision","slug":"tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","arxiv_id":"2101.11986","repositories_listed":13,"syntology":{"n":26,"n_ran":21,"n_constructed":16,"n_ran_checked":21,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":20,"n_pointer_only":8,"phrase":"21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tokens-to-token-vit-training-vision#ran","syntology_url":"https://syntology.ai/paper/2101.11986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11986"}},"official":{"repos":["yitu-opensource/T2T-ViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","repositories_listed":13,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prefix-tuning-optimizing-continuous-prompts#ran","syntology_url":"https://syntology.ai/paper/2101.00190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00190"}},"official":{"repos":["XiangLi1999/PrefixTuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/rezero-is-all-you-need-fast-convergence-at","slug":"rezero-is-all-you-need-fast-convergence-at","title":"ReZero is All You Need: Fast Convergence at Large Depth","date":"2020-03-10","arxiv_id":"2003.04887","repositories_listed":13,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rezero-is-all-you-need-fast-convergence-at#ran","syntology_url":"https://syntology.ai/paper/2003.04887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04887"}},"official":{"repos":["majumderb/rezero"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bert-has-a-mouth-and-it-must-speak-bert-as-a","slug":"bert-has-a-mouth-and-it-must-speak-bert-as-a","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","date":"2019-02-11","arxiv_id":"1902.04094","repositories_listed":13,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bert-has-a-mouth-and-it-must-speak-bert-as-a#ran","syntology_url":"https://syntology.ai/paper/1902.04094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04094"}},"official":{"repos":["kyunghyuncho/bert-gen","nyu-dl/bert-gen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"repositories_listed":13,"syntology":null},{"url":"/paper/awq-activation-aware-weight-quantization-for","slug":"awq-activation-aware-weight-quantization-for","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","date":"2023-06-01","arxiv_id":"2306.00978","repositories_listed":12,"syntology":{"n":18,"n_ran":16,"n_constructed":1,"n_ran_checked":6,"n_instrument":10,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"16 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/awq-activation-aware-weight-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2306.00978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00978"}},"official":{"repos":["internlm/lmdeploy","mit-han-lab/llm-awq","nvidia/tensorrt-llm","vllm-project/vllm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/an-analysis-of-neural-language-modeling-at","slug":"an-analysis-of-neural-language-modeling-at","title":"An Analysis of Neural Language Modeling at Multiple Scales","date":"2018-03-22","arxiv_id":"1803.08240","repositories_listed":12,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":11,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/an-analysis-of-neural-language-modeling-at#ran","syntology_url":"https://syntology.ai/paper/1803.08240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08240"}},"official":{"repos":["salesforce/awd-lstm-lm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/where-to-put-the-image-in-an-image-caption","slug":"where-to-put-the-image-in-an-image-caption","title":"Where to put the Image in an Image Caption Generator","date":"2017-03-27","arxiv_id":"1703.09137","repositories_listed":12,"syntology":null},{"url":"/paper/neural-architecture-search-with-reinforcement","slug":"neural-architecture-search-with-reinforcement","title":"Neural Architecture Search with Reinforcement Learning","date":"2016-11-05","arxiv_id":"1611.01578","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-architecture-search-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1611.01578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01578"}},"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","repositories_listed":11,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gpt-neox-20b-an-open-source-autoregressive-1#ran","syntology_url":"https://syntology.ai/paper/2204.06745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06745"}},"official":{"repos":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-equilibrium-models","slug":"deep-equilibrium-models","title":"Deep Equilibrium Models","date":"2019-09-03","arxiv_id":"1909.01377","repositories_listed":11,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/1909.01377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01377"}},"official":{"repos":["locuslab/deq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/language-modeling-with-gated-convolutional","slug":"language-modeling-with-gated-convolutional","title":"Language Modeling with Gated Convolutional Networks","date":"2016-12-23","arxiv_id":"1612.08083","repositories_listed":11,"syntology":null},{"url":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","repositories_listed":10,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-understands-too#ran","syntology_url":"https://syntology.ai/paper/2103.10385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10385"}},"official":{"repos":["THUDM/P-tuning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cpm-a-large-scale-generative-chinese-pre","slug":"cpm-a-large-scale-generative-chinese-pre","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","date":"2020-12-01","arxiv_id":"2012.00413","repositories_listed":10,"syntology":null},{"url":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","repositories_listed":10,"syntology":{"n":47,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":35,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/megatron-lm-training-multi-billion-parameter#ran","syntology_url":"https://syntology.ai/paper/1909.08053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08053"}},"official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","repositories_listed":10,"syntology":{"n":9,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}},"official":null}},{"url":"/paper/jasper-an-end-to-end-convolutional-neural","slug":"jasper-an-end-to-end-convolutional-neural","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","date":"2019-04-05","arxiv_id":"1904.03288","repositories_listed":10,"syntology":null},{"url":"/paper/espnetv2-a-light-weight-power-efficient-and","slug":"espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","date":"2018-11-28","arxiv_id":"1811.11431","repositories_listed":10,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/espnetv2-a-light-weight-power-efficient-and#ran","syntology_url":"https://syntology.ai/paper/1811.11431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11431"}},"official":{"repos":["sacmehta/EdgeNets"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pointer-sentinel-mixture-models","slug":"pointer-sentinel-mixture-models","title":"Pointer Sentinel Mixture Models","date":"2016-09-26","arxiv_id":"1609.07843","repositories_listed":10,"syntology":{"n":9,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/pointer-sentinel-mixture-models#ran","syntology_url":"https://syntology.ai/paper/1609.07843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07843"}},"official":null}},{"url":"/paper/exploring-the-limits-of-language-modeling","slug":"exploring-the-limits-of-language-modeling","title":"Exploring the Limits of Language Modeling","date":"2016-02-07","arxiv_id":"1602.02410","repositories_listed":10,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/exploring-the-limits-of-language-modeling#ran","syntology_url":"https://syntology.ai/paper/1602.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02410"}},"official":null}},{"url":"/paper/retentive-network-a-successor-to-transformer","slug":"retentive-network-a-successor-to-transformer","title":"Retentive Network: A Successor to Transformer for Large Language Models","date":"2023-07-17","arxiv_id":"2307.08621","repositories_listed":9,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retentive-network-a-successor-to-transformer#ran","syntology_url":"https://syntology.ai/paper/2307.08621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08621"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","repositories_listed":9,"syntology":{"n":21,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}},"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","repositories_listed":9,"syntology":null},{"url":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","repositories_listed":9,"syntology":{"n":10,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}},"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","repositories_listed":9,"syntology":{"n":15,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}},"official":{"repos":["airsplay/lxmert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/breaking-the-softmax-bottleneck-a-high-rank","slug":"breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","arxiv_id":"1711.03953","repositories_listed":9,"syntology":{"n":23,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/breaking-the-softmax-bottleneck-a-high-rank#ran","syntology_url":"https://syntology.ai/paper/1711.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03953"}},"official":{"repos":["zihangdai/mos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/order-matters-sequence-to-sequence-for-sets","slug":"order-matters-sequence-to-sequence-for-sets","title":"Order Matters: Sequence to sequence for sets","date":"2015-11-19","arxiv_id":"1511.06391","repositories_listed":9,"syntology":null},{"url":"/paper/llamafactory-unified-efficient-fine-tuning-of","slug":"llamafactory-unified-efficient-fine-tuning-of","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","date":"2024-03-20","arxiv_id":"2403.13372","repositories_listed":8,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/llamafactory-unified-efficient-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2403.13372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13372"}},"official":{"repos":["hiyouga/llama-factory"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/ring-attention-with-blockwise-transformers","slug":"ring-attention-with-blockwise-transformers","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","date":"2023-10-03","arxiv_id":"2310.01889","repositories_listed":8,"syntology":{"n":28,"n_ran":20,"n_constructed":0,"n_ran_checked":14,"n_instrument":6,"n_unverified":8,"n_honours":3,"n_violates":3,"n_no_contract":8,"n_pointer_only":9,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 3 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ring-attention-with-blockwise-transformers#ran","syntology_url":"https://syntology.ai/paper/2310.01889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01889"}},"official":{"repos":["forhaoliu/ringattention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/simple-and-controllable-music-generation","slug":"simple-and-controllable-music-generation","title":"Simple and Controllable Music Generation","date":"2023-06-08","arxiv_id":"2306.05284","repositories_listed":8,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/simple-and-controllable-music-generation#ran","syntology_url":"https://syntology.ai/paper/2306.05284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05284"}},"official":null}},{"url":"/paper/a-watermark-for-large-language-models","slug":"a-watermark-for-large-language-models","title":"A Watermark for Large Language Models","date":"2023-01-24","arxiv_id":"2301.10226","repositories_listed":8,"syntology":{"n":16,"n_ran":11,"n_constructed":7,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":5,"phrase":"11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-watermark-for-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2301.10226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10226"}},"official":{"repos":["jwkirchenbauer/lm-watermarking"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-conversational-paradigm-for-program","slug":"a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","arxiv_id":"2203.13474","repositories_listed":8,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-conversational-paradigm-for-program#ran","syntology_url":"https://syntology.ai/paper/2203.13474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13474"}},"official":{"repos":["salesforce/CodeGen","salesforce/jaxformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/efficiently-modeling-long-sequences-with-1","slug":"efficiently-modeling-long-sequences-with-1","title":"Efficiently Modeling Long Sequences with Structured State Spaces","date":"2021-10-31","arxiv_id":"2111.00396","repositories_listed":8,"syntology":{"n":55,"n_ran":37,"n_constructed":8,"n_ran_checked":21,"n_instrument":16,"n_unverified":18,"n_honours":2,"n_violates":1,"n_no_contract":18,"n_pointer_only":3,"phrase":"37 ran (of which 8 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 1 violated, 18 with no contract checked; 16 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/efficiently-modeling-long-sequences-with-1#ran","syntology_url":"https://syntology.ai/paper/2111.00396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00396"}},"official":{"repos":["state-spaces/s4"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["community","listed","official"]}}},{"url":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","repositories_listed":8,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trocr-transformer-based-optical-character#ran","syntology_url":"https://syntology.ai/paper/2109.10282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10282"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","repositories_listed":8,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}},"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/r-drop-regularized-dropout-for-neural","slug":"r-drop-regularized-dropout-for-neural","title":"R-Drop: Regularized Dropout for Neural Networks","date":"2021-06-28","arxiv_id":"2106.14448","repositories_listed":8,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/r-drop-regularized-dropout-for-neural#ran","syntology_url":"https://syntology.ai/paper/2106.14448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14448"}},"official":{"repos":["dropreg/R-Drop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/all-nlp-tasks-are-generation-tasks-a-general#ran","syntology_url":"https://syntology.ai/paper/2103.10360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10360"}},"official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/adabelief-optimizer-adapting-stepsizes-by-the","slug":"adabelief-optimizer-adapting-stepsizes-by-the","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","date":"2020-10-15","arxiv_id":"2010.07468","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adabelief-optimizer-adapting-stepsizes-by-the#ran","syntology_url":"https://syntology.ai/paper/2010.07468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07468"}},"official":{"repos":["juntang-zhuang/Adabelief-Optimizer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/camembert-a-tasty-french-language-model","slug":"camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","date":"2019-11-10","arxiv_id":"1911.03894","repositories_listed":8,"syntology":null},{"url":"/paper/ctrl-a-conditional-transformer-language-model-1","slug":"ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","arxiv_id":"1909.05858","repositories_listed":8,"syntology":{"n":14,"n_ran":14,"n_constructed":3,"n_ran_checked":11,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ctrl-a-conditional-transformer-language-model-1#ran","syntology_url":"https://syntology.ai/paper/1909.05858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05858"}},"official":null}},{"url":"/paper/adaptive-attention-span-in-transformers","slug":"adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","date":"2019-05-19","arxiv_id":"1905.07799","repositories_listed":8,"syntology":null},{"url":"/paper/universal-transformers","slug":"universal-transformers","title":"Universal Transformers","date":"2018-07-10","arxiv_id":"1807.03819","repositories_listed":8,"syntology":{"n":25,"n_ran":17,"n_constructed":8,"n_ran_checked":17,"n_instrument":0,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":16,"n_pointer_only":24,"phrase":"17 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/universal-transformers#ran","syntology_url":"https://syntology.ai/paper/1807.03819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03819"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/2309-06180","slug":"2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","date":"2023-09-12","arxiv_id":"2309.06180","repositories_listed":7,"syntology":{"n":36,"n_ran":28,"n_constructed":0,"n_ran_checked":12,"n_instrument":16,"n_unverified":8,"n_honours":5,"n_violates":1,"n_no_contract":6,"n_pointer_only":11,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 1 violated, 6 with no contract checked; 16 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/2309-06180#ran","syntology_url":"https://syntology.ai/paper/2309.06180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06180"}},"official":{"repos":["vllm-project/vllm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/extending-context-window-of-large-language","slug":"extending-context-window-of-large-language","title":"Extending Context Window of Large Language Models via Positional Interpolation","date":"2023-06-27","arxiv_id":"2306.15595","repositories_listed":7,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/extending-context-window-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.15595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15595"}},"official":null}},{"url":"/paper/sophia-a-scalable-stochastic-second-order","slug":"sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","arxiv_id":"2305.14342","repositories_listed":7,"syntology":{"n":19,"n_ran":13,"n_constructed":4,"n_ran_checked":12,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/sophia-a-scalable-stochastic-second-order#ran","syntology_url":"https://syntology.ai/paper/2305.14342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14342"}},"official":null}},{"url":"/paper/hyena-hierarchy-towards-larger-convolutional","slug":"hyena-hierarchy-towards-larger-convolutional","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","date":"2023-02-21","arxiv_id":"2302.10866","repositories_listed":7,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hyena-hierarchy-towards-larger-convolutional#ran","syntology_url":"https://syntology.ai/paper/2302.10866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10866"}},"official":{"repos":["hazyresearch/safari"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/neural-codec-language-models-are-zero-shot","slug":"neural-codec-language-models-are-zero-shot","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","date":"2023-01-05","arxiv_id":"2301.02111","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-codec-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2301.02111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02111"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fast-inference-from-transformers-via","slug":"fast-inference-from-transformers-via","title":"Fast Inference from Transformers via Speculative Decoding","date":"2022-11-30","arxiv_id":"2211.17192","repositories_listed":7,"syntology":{"n":21,"n_ran":15,"n_constructed":1,"n_ran_checked":6,"n_instrument":9,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fast-inference-from-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2211.17192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.17192"}},"official":null}},{"url":"/paper/bloom-a-176b-parameter-open-access","slug":"bloom-a-176b-parameter-open-access","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","date":"2022-11-09","arxiv_id":"2211.05100","repositories_listed":7,"syntology":{"n":11,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/bloom-a-176b-parameter-open-access#ran","syntology_url":"https://syntology.ai/paper/2211.05100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05100"}},"official":null}},{"url":"/paper/interpretability-in-the-wild-a-circuit-for","slug":"interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","arxiv_id":"2211.00593","repositories_listed":7,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/interpretability-in-the-wild-a-circuit-for#ran","syntology_url":"https://syntology.ai/paper/2211.00593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00593"}},"official":{"repos":["redwoodresearch/easy-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mega-moving-average-equipped-gated-attention","slug":"mega-moving-average-equipped-gated-attention","title":"Mega: Moving Average Equipped Gated Attention","date":"2022-09-21","arxiv_id":"2209.10655","repositories_listed":7,"syntology":{"n":13,"n_ran":12,"n_constructed":6,"n_ran_checked":7,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mega-moving-average-equipped-gated-attention#ran","syntology_url":"https://syntology.ai/paper/2209.10655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.10655"}},"official":{"repos":["facebookresearch/mega"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}},{"url":"/paper/mpnet-masked-and-permuted-pre-training-for","slug":"mpnet-masked-and-permuted-pre-training-for","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","date":"2020-04-20","arxiv_id":"2004.09297","repositories_listed":7,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mpnet-masked-and-permuted-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2004.09297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09297"}},"official":{"repos":["microsoft/MPNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/flaubert-unsupervised-language-model-pre","slug":"flaubert-unsupervised-language-model-pre","title":"FlauBERT: Unsupervised Language Model Pre-training for French","date":"2019-12-11","arxiv_id":"1912.05372","repositories_listed":7,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flaubert-unsupervised-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/1912.05372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.05372"}},"official":{"repos":["getalp/Flaubert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/on-the-cross-lingual-transferability-of","slug":"on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","date":"2019-10-25","arxiv_id":"1910.11856","repositories_listed":7,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-cross-lingual-transferability-of#ran","syntology_url":"https://syntology.ai/paper/1910.11856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11856"}},"official":{"repos":["deepmind/xquad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-memory-layers-with-product-keys","slug":"large-memory-layers-with-product-keys","title":"Large Memory Layers with Product Keys","date":"2019-07-10","arxiv_id":"1907.05242","repositories_listed":7,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-memory-layers-with-product-keys#ran","syntology_url":"https://syntology.ai/paper/1907.05242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05242"}},"official":{"repos":["facebookresearch/XLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mass-masked-sequence-to-sequence-pre-training","slug":"mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","repositories_listed":7,"syntology":null},{"url":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","repositories_listed":7,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-task-deep-neural-networks-for-natural#ran","syntology_url":"https://syntology.ai/paper/1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}},"official":{"repos":["namisan/mt-dnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"syntology_records":85,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":1894,"papers_where_code_ran_first_page":"/task/language-modeling/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":142,"url":"/task/language-modeling/papers/2","json":"/task/language-modeling/papers/2.json","rows":100},{"order":"archive","page":3,"of":142,"url":"/task/language-modeling/papers/3","json":"/task/language-modeling/papers/3.json","rows":100},{"order":"archive","page":4,"of":142,"url":"/task/language-modeling/papers/4","json":"/task/language-modeling/papers/4.json","rows":100},{"order":"archive","page":5,"of":142,"url":"/task/language-modeling/papers/5","json":"/task/language-modeling/papers/5.json","rows":100},{"order":"archive","page":6,"of":142,"url":"/task/language-modeling/papers/6","json":"/task/language-modeling/papers/6.json","rows":100},{"order":"archive","page":7,"of":142,"url":"/task/language-modeling/papers/7","json":"/task/language-modeling/papers/7.json","rows":100},{"order":"archive","page":8,"of":142,"url":"/task/language-modeling/papers/8","json":"/task/language-modeling/papers/8.json","rows":100},{"order":"archive","page":9,"of":142,"url":"/task/language-modeling/papers/9","json":"/task/language-modeling/papers/9.json","rows":100},{"order":"archive","page":10,"of":142,"url":"/task/language-modeling/papers/10","json":"/task/language-modeling/papers/10.json","rows":100},{"order":"archive","page":11,"of":142,"url":"/task/language-modeling/papers/11","json":"/task/language-modeling/papers/11.json","rows":100},{"order":"archive","page":12,"of":142,"url":"/task/language-modeling/papers/12","json":"/task/language-modeling/papers/12.json","rows":100},{"order":"archive","page":13,"of":142,"url":"/task/language-modeling/papers/13","json":"/task/language-modeling/papers/13.json","rows":100},{"order":"archive","page":14,"of":142,"url":"/task/language-modeling/papers/14","json":"/task/language-modeling/papers/14.json","rows":100},{"order":"archive","page":15,"of":142,"url":"/task/language-modeling/papers/15","json":"/task/language-modeling/papers/15.json","rows":100},{"order":"archive","page":16,"of":142,"url":"/task/language-modeling/papers/16","json":"/task/language-modeling/papers/16.json","rows":100},{"order":"archive","page":17,"of":142,"url":"/task/language-modeling/papers/17","json":"/task/language-modeling/papers/17.json","rows":100},{"order":"archive","page":18,"of":142,"url":"/task/language-modeling/papers/18","json":"/task/language-modeling/papers/18.json","rows":100},{"order":"archive","page":19,"of":142,"url":"/task/language-modeling/papers/19","json":"/task/language-modeling/papers/19.json","rows":100},{"order":"archive","page":20,"of":142,"url":"/task/language-modeling/papers/20","json":"/task/language-modeling/papers/20.json","rows":100},{"order":"archive","page":21,"of":142,"url":"/task/language-modeling/papers/21","json":"/task/language-modeling/papers/21.json","rows":100},{"order":"archive","page":22,"of":142,"url":"/task/language-modeling/papers/22","json":"/task/language-modeling/papers/22.json","rows":100},{"order":"archive","page":23,"of":142,"url":"/task/language-modeling/papers/23","json":"/task/language-modeling/papers/23.json","rows":100},{"order":"archive","page":24,"of":142,"url":"/task/language-modeling/papers/24","json":"/task/language-modeling/papers/24.json","rows":100},{"order":"archive","page":25,"of":142,"url":"/task/language-modeling/papers/25","json":"/task/language-modeling/papers/25.json","rows":100},{"order":"archive","page":26,"of":142,"url":"/task/language-modeling/papers/26","json":"/task/language-modeling/papers/26.json","rows":100},{"order":"archive","page":27,"of":142,"url":"/task/language-modeling/papers/27","json":"/task/language-modeling/papers/27.json","rows":100},{"order":"archive","page":28,"of":142,"url":"/task/language-modeling/papers/28","json":"/task/language-modeling/papers/28.json","rows":100},{"order":"archive","page":29,"of":142,"url":"/task/language-modeling/papers/29","json":"/task/language-modeling/papers/29.json","rows":100},{"order":"archive","page":30,"of":142,"url":"/task/language-modeling/papers/30","json":"/task/language-modeling/papers/30.json","rows":100},{"order":"archive","page":31,"of":142,"url":"/task/language-modeling/papers/31","json":"/task/language-modeling/papers/31.json","rows":100},{"order":"archive","page":32,"of":142,"url":"/task/language-modeling/papers/32","json":"/task/language-modeling/papers/32.json","rows":100},{"order":"archive","page":33,"of":142,"url":"/task/language-modeling/papers/33","json":"/task/language-modeling/papers/33.json","rows":100},{"order":"archive","page":34,"of":142,"url":"/task/language-modeling/papers/34","json":"/task/language-modeling/papers/34.json","rows":100},{"order":"archive","page":35,"of":142,"url":"/task/language-modeling/papers/35","json":"/task/language-modeling/papers/35.json","rows":100},{"order":"archive","page":36,"of":142,"url":"/task/language-modeling/papers/36","json":"/task/language-modeling/papers/36.json","rows":100},{"order":"archive","page":37,"of":142,"url":"/task/language-modeling/papers/37","json":"/task/language-modeling/papers/37.json","rows":100},{"order":"archive","page":38,"of":142,"url":"/task/language-modeling/papers/38","json":"/task/language-modeling/papers/38.json","rows":100},{"order":"archive","page":39,"of":142,"url":"/task/language-modeling/papers/39","json":"/task/language-modeling/papers/39.json","rows":100},{"order":"archive","page":40,"of":142,"url":"/task/language-modeling/papers/40","json":"/task/language-modeling/papers/40.json","rows":100},{"order":"archive","page":41,"of":142,"url":"/task/language-modeling/papers/41","json":"/task/language-modeling/papers/41.json","rows":100},{"order":"archive","page":42,"of":142,"url":"/task/language-modeling/papers/42","json":"/task/language-modeling/papers/42.json","rows":100},{"order":"archive","page":43,"of":142,"url":"/task/language-modeling/papers/43","json":"/task/language-modeling/papers/43.json","rows":100},{"order":"archive","page":44,"of":142,"url":"/task/language-modeling/papers/44","json":"/task/language-modeling/papers/44.json","rows":100},{"order":"archive","page":45,"of":142,"url":"/task/language-modeling/papers/45","json":"/task/language-modeling/papers/45.json","rows":100},{"order":"archive","page":46,"of":142,"url":"/task/language-modeling/papers/46","json":"/task/language-modeling/papers/46.json","rows":100},{"order":"archive","page":47,"of":142,"url":"/task/language-modeling/papers/47","json":"/task/language-modeling/papers/47.json","rows":100},{"order":"archive","page":48,"of":142,"url":"/task/language-modeling/papers/48","json":"/task/language-modeling/papers/48.json","rows":100},{"order":"archive","page":49,"of":142,"url":"/task/language-modeling/papers/49","json":"/task/language-modeling/papers/49.json","rows":100},{"order":"archive","page":50,"of":142,"url":"/task/language-modeling/papers/50","json":"/task/language-modeling/papers/50.json","rows":100},{"order":"archive","page":51,"of":142,"url":"/task/language-modeling/papers/51","json":"/task/language-modeling/papers/51.json","rows":100},{"order":"archive","page":52,"of":142,"url":"/task/language-modeling/papers/52","json":"/task/language-modeling/papers/52.json","rows":100},{"order":"archive","page":53,"of":142,"url":"/task/language-modeling/papers/53","json":"/task/language-modeling/papers/53.json","rows":100},{"order":"archive","page":54,"of":142,"url":"/task/language-modeling/papers/54","json":"/task/language-modeling/papers/54.json","rows":100},{"order":"archive","page":55,"of":142,"url":"/task/language-modeling/papers/55","json":"/task/language-modeling/papers/55.json","rows":100},{"order":"archive","page":56,"of":142,"url":"/task/language-modeling/papers/56","json":"/task/language-modeling/papers/56.json","rows":100},{"order":"archive","page":57,"of":142,"url":"/task/language-modeling/papers/57","json":"/task/language-modeling/papers/57.json","rows":100},{"order":"archive","page":58,"of":142,"url":"/task/language-modeling/papers/58","json":"/task/language-modeling/papers/58.json","rows":100},{"order":"archive","page":59,"of":142,"url":"/task/language-modeling/papers/59","json":"/task/language-modeling/papers/59.json","rows":100},{"order":"archive","page":60,"of":142,"url":"/task/language-modeling/papers/60","json":"/task/language-modeling/papers/60.json","rows":100},{"order":"archive","page":61,"of":142,"url":"/task/language-modeling/papers/61","json":"/task/language-modeling/papers/61.json","rows":100},{"order":"archive","page":62,"of":142,"url":"/task/language-modeling/papers/62","json":"/task/language-modeling/papers/62.json","rows":100},{"order":"archive","page":63,"of":142,"url":"/task/language-modeling/papers/63","json":"/task/language-modeling/papers/63.json","rows":100},{"order":"archive","page":64,"of":142,"url":"/task/language-modeling/papers/64","json":"/task/language-modeling/papers/64.json","rows":100},{"order":"archive","page":65,"of":142,"url":"/task/language-modeling/papers/65","json":"/task/language-modeling/papers/65.json","rows":100},{"order":"archive","page":66,"of":142,"url":"/task/language-modeling/papers/66","json":"/task/language-modeling/papers/66.json","rows":100},{"order":"archive","page":67,"of":142,"url":"/task/language-modeling/papers/67","json":"/task/language-modeling/papers/67.json","rows":100},{"order":"archive","page":68,"of":142,"url":"/task/language-modeling/papers/68","json":"/task/language-modeling/papers/68.json","rows":100},{"order":"archive","page":69,"of":142,"url":"/task/language-modeling/papers/69","json":"/task/language-modeling/papers/69.json","rows":100},{"order":"archive","page":70,"of":142,"url":"/task/language-modeling/papers/70","json":"/task/language-modeling/papers/70.json","rows":100},{"order":"archive","page":71,"of":142,"url":"/task/language-modeling/papers/71","json":"/task/language-modeling/papers/71.json","rows":100},{"order":"archive","page":72,"of":142,"url":"/task/language-modeling/papers/72","json":"/task/language-modeling/papers/72.json","rows":100},{"order":"archive","page":73,"of":142,"url":"/task/language-modeling/papers/73","json":"/task/language-modeling/papers/73.json","rows":100},{"order":"archive","page":74,"of":142,"url":"/task/language-modeling/papers/74","json":"/task/language-modeling/papers/74.json","rows":100},{"order":"archive","page":75,"of":142,"url":"/task/language-modeling/papers/75","json":"/task/language-modeling/papers/75.json","rows":100},{"order":"archive","page":76,"of":142,"url":"/task/language-modeling/papers/76","json":"/task/language-modeling/papers/76.json","rows":100},{"order":"archive","page":77,"of":142,"url":"/task/language-modeling/papers/77","json":"/task/language-modeling/papers/77.json","rows":100},{"order":"archive","page":78,"of":142,"url":"/task/language-modeling/papers/78","json":"/task/language-modeling/papers/78.json","rows":100},{"order":"archive","page":79,"of":142,"url":"/task/language-modeling/papers/79","json":"/task/language-modeling/papers/79.json","rows":100},{"order":"archive","page":80,"of":142,"url":"/task/language-modeling/papers/80","json":"/task/language-modeling/papers/80.json","rows":100},{"order":"archive","page":81,"of":142,"url":"/task/language-modeling/papers/81","json":"/task/language-modeling/papers/81.json","rows":100},{"order":"archive","page":82,"of":142,"url":"/task/language-modeling/papers/82","json":"/task/language-modeling/papers/82.json","rows":100},{"order":"archive","page":83,"of":142,"url":"/task/language-modeling/papers/83","json":"/task/language-modeling/papers/83.json","rows":100},{"order":"archive","page":84,"of":142,"url":"/task/language-modeling/papers/84","json":"/task/language-modeling/papers/84.json","rows":100},{"order":"archive","page":85,"of":142,"url":"/task/language-modeling/papers/85","json":"/task/language-modeling/papers/85.json","rows":100},{"order":"archive","page":86,"of":142,"url":"/task/language-modeling/papers/86","json":"/task/language-modeling/papers/86.json","rows":100},{"order":"archive","page":87,"of":142,"url":"/task/language-modeling/papers/87","json":"/task/language-modeling/papers/87.json","rows":100},{"order":"archive","page":88,"of":142,"url":"/task/language-modeling/papers/88","json":"/task/language-modeling/papers/88.json","rows":100},{"order":"archive","page":89,"of":142,"url":"/task/language-modeling/papers/89","json":"/task/language-modeling/papers/89.json","rows":100},{"order":"archive","page":90,"of":142,"url":"/task/language-modeling/papers/90","json":"/task/language-modeling/papers/90.json","rows":100},{"order":"archive","page":91,"of":142,"url":"/task/language-modeling/papers/91","json":"/task/language-modeling/papers/91.json","rows":100},{"order":"archive","page":92,"of":142,"url":"/task/language-modeling/papers/92","json":"/task/language-modeling/papers/92.json","rows":100},{"order":"archive","page":93,"of":142,"url":"/task/language-modeling/papers/93","json":"/task/language-modeling/papers/93.json","rows":100},{"order":"archive","page":94,"of":142,"url":"/task/language-modeling/papers/94","json":"/task/language-modeling/papers/94.json","rows":100},{"order":"archive","page":95,"of":142,"url":"/task/language-modeling/papers/95","json":"/task/language-modeling/papers/95.json","rows":100},{"order":"archive","page":96,"of":142,"url":"/task/language-modeling/papers/96","json":"/task/language-modeling/papers/96.json","rows":100},{"order":"archive","page":97,"of":142,"url":"/task/language-modeling/papers/97","json":"/task/language-modeling/papers/97.json","rows":100},{"order":"archive","page":98,"of":142,"url":"/task/language-modeling/papers/98","json":"/task/language-modeling/papers/98.json","rows":100},{"order":"archive","page":99,"of":142,"url":"/task/language-modeling/papers/99","json":"/task/language-modeling/papers/99.json","rows":100},{"order":"archive","page":100,"of":142,"url":"/task/language-modeling/papers/100","json":"/task/language-modeling/papers/100.json","rows":100},{"order":"archive","page":101,"of":142,"url":"/task/language-modeling/papers/101","json":"/task/language-modeling/papers/101.json","rows":100},{"order":"archive","page":102,"of":142,"url":"/task/language-modeling/papers/102","json":"/task/language-modeling/papers/102.json","rows":100},{"order":"archive","page":103,"of":142,"url":"/task/language-modeling/papers/103","json":"/task/language-modeling/papers/103.json","rows":100},{"order":"archive","page":104,"of":142,"url":"/task/language-modeling/papers/104","json":"/task/language-modeling/papers/104.json","rows":100},{"order":"archive","page":105,"of":142,"url":"/task/language-modeling/papers/105","json":"/task/language-modeling/papers/105.json","rows":100},{"order":"archive","page":106,"of":142,"url":"/task/language-modeling/papers/106","json":"/task/language-modeling/papers/106.json","rows":100},{"order":"archive","page":107,"of":142,"url":"/task/language-modeling/papers/107","json":"/task/language-modeling/papers/107.json","rows":100},{"order":"archive","page":108,"of":142,"url":"/task/language-modeling/papers/108","json":"/task/language-modeling/papers/108.json","rows":100},{"order":"archive","page":109,"of":142,"url":"/task/language-modeling/papers/109","json":"/task/language-modeling/papers/109.json","rows":100},{"order":"archive","page":110,"of":142,"url":"/task/language-modeling/papers/110","json":"/task/language-modeling/papers/110.json","rows":100},{"order":"archive","page":111,"of":142,"url":"/task/language-modeling/papers/111","json":"/task/language-modeling/papers/111.json","rows":100},{"order":"archive","page":112,"of":142,"url":"/task/language-modeling/papers/112","json":"/task/language-modeling/papers/112.json","rows":100},{"order":"archive","page":113,"of":142,"url":"/task/language-modeling/papers/113","json":"/task/language-modeling/papers/113.json","rows":100},{"order":"archive","page":114,"of":142,"url":"/task/language-modeling/papers/114","json":"/task/language-modeling/papers/114.json","rows":100},{"order":"archive","page":115,"of":142,"url":"/task/language-modeling/papers/115","json":"/task/language-modeling/papers/115.json","rows":100},{"order":"archive","page":116,"of":142,"url":"/task/language-modeling/papers/116","json":"/task/language-modeling/papers/116.json","rows":100},{"order":"archive","page":117,"of":142,"url":"/task/language-modeling/papers/117","json":"/task/language-modeling/papers/117.json","rows":100},{"order":"archive","page":118,"of":142,"url":"/task/language-modeling/papers/118","json":"/task/language-modeling/papers/118.json","rows":100},{"order":"archive","page":119,"of":142,"url":"/task/language-modeling/papers/119","json":"/task/language-modeling/papers/119.json","rows":100},{"order":"archive","page":120,"of":142,"url":"/task/language-modeling/papers/120","json":"/task/language-modeling/papers/120.json","rows":100},{"order":"archive","page":121,"of":142,"url":"/task/language-modeling/papers/121","json":"/task/language-modeling/papers/121.json","rows":100},{"order":"archive","page":122,"of":142,"url":"/task/language-modeling/papers/122","json":"/task/language-modeling/papers/122.json","rows":100},{"order":"archive","page":123,"of":142,"url":"/task/language-modeling/papers/123","json":"/task/language-modeling/papers/123.json","rows":100},{"order":"archive","page":124,"of":142,"url":"/task/language-modeling/papers/124","json":"/task/language-modeling/papers/124.json","rows":100},{"order":"archive","page":125,"of":142,"url":"/task/language-modeling/papers/125","json":"/task/language-modeling/papers/125.json","rows":100},{"order":"archive","page":126,"of":142,"url":"/task/language-modeling/papers/126","json":"/task/language-modeling/papers/126.json","rows":100},{"order":"archive","page":127,"of":142,"url":"/task/language-modeling/papers/127","json":"/task/language-modeling/papers/127.json","rows":100},{"order":"archive","page":128,"of":142,"url":"/task/language-modeling/papers/128","json":"/task/language-modeling/papers/128.json","rows":100},{"order":"archive","page":129,"of":142,"url":"/task/language-modeling/papers/129","json":"/task/language-modeling/papers/129.json","rows":100},{"order":"archive","page":130,"of":142,"url":"/task/language-modeling/papers/130","json":"/task/language-modeling/papers/130.json","rows":100},{"order":"archive","page":131,"of":142,"url":"/task/language-modeling/papers/131","json":"/task/language-modeling/papers/131.json","rows":100},{"order":"archive","page":132,"of":142,"url":"/task/language-modeling/papers/132","json":"/task/language-modeling/papers/132.json","rows":100},{"order":"archive","page":133,"of":142,"url":"/task/language-modeling/papers/133","json":"/task/language-modeling/papers/133.json","rows":100},{"order":"archive","page":134,"of":142,"url":"/task/language-modeling/papers/134","json":"/task/language-modeling/papers/134.json","rows":100},{"order":"archive","page":135,"of":142,"url":"/task/language-modeling/papers/135","json":"/task/language-modeling/papers/135.json","rows":100},{"order":"archive","page":136,"of":142,"url":"/task/language-modeling/papers/136","json":"/task/language-modeling/papers/136.json","rows":100},{"order":"archive","page":137,"of":142,"url":"/task/language-modeling/papers/137","json":"/task/language-modeling/papers/137.json","rows":100},{"order":"archive","page":138,"of":142,"url":"/task/language-modeling/papers/138","json":"/task/language-modeling/papers/138.json","rows":100},{"order":"archive","page":139,"of":142,"url":"/task/language-modeling/papers/139","json":"/task/language-modeling/papers/139.json","rows":100},{"order":"archive","page":140,"of":142,"url":"/task/language-modeling/papers/140","json":"/task/language-modeling/papers/140.json","rows":100},{"order":"archive","page":141,"of":142,"url":"/task/language-modeling/papers/141","json":"/task/language-modeling/papers/141.json","rows":100},{"order":"archive","page":142,"of":142,"url":"/task/language-modeling/papers/142","json":"/task/language-modeling/papers/142.json","rows":82},{"order":"ran","page":1,"of":19,"url":"/task/language-modeling/papers/ran/1","json":"/task/language-modeling/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":19,"url":"/task/language-modeling/papers/ran/2","json":"/task/language-modeling/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":19,"url":"/task/language-modeling/papers/ran/3","json":"/task/language-modeling/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":19,"url":"/task/language-modeling/papers/ran/4","json":"/task/language-modeling/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":19,"url":"/task/language-modeling/papers/ran/5","json":"/task/language-modeling/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":19,"url":"/task/language-modeling/papers/ran/6","json":"/task/language-modeling/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":19,"url":"/task/language-modeling/papers/ran/7","json":"/task/language-modeling/papers/ran/7.json","rows":100},{"order":"ran","page":8,"of":19,"url":"/task/language-modeling/papers/ran/8","json":"/task/language-modeling/papers/ran/8.json","rows":100},{"order":"ran","page":9,"of":19,"url":"/task/language-modeling/papers/ran/9","json":"/task/language-modeling/papers/ran/9.json","rows":100},{"order":"ran","page":10,"of":19,"url":"/task/language-modeling/papers/ran/10","json":"/task/language-modeling/papers/ran/10.json","rows":100},{"order":"ran","page":11,"of":19,"url":"/task/language-modeling/papers/ran/11","json":"/task/language-modeling/papers/ran/11.json","rows":100},{"order":"ran","page":12,"of":19,"url":"/task/language-modeling/papers/ran/12","json":"/task/language-modeling/papers/ran/12.json","rows":100},{"order":"ran","page":13,"of":19,"url":"/task/language-modeling/papers/ran/13","json":"/task/language-modeling/papers/ran/13.json","rows":100},{"order":"ran","page":14,"of":19,"url":"/task/language-modeling/papers/ran/14","json":"/task/language-modeling/papers/ran/14.json","rows":100},{"order":"ran","page":15,"of":19,"url":"/task/language-modeling/papers/ran/15","json":"/task/language-modeling/papers/ran/15.json","rows":100},{"order":"ran","page":16,"of":19,"url":"/task/language-modeling/papers/ran/16","json":"/task/language-modeling/papers/ran/16.json","rows":100},{"order":"ran","page":17,"of":19,"url":"/task/language-modeling/papers/ran/17","json":"/task/language-modeling/papers/ran/17.json","rows":100},{"order":"ran","page":18,"of":19,"url":"/task/language-modeling/papers/ran/18","json":"/task/language-modeling/papers/ran/18.json","rows":100},{"order":"ran","page":19,"of":19,"url":"/task/language-modeling/papers/ran/19","json":"/task/language-modeling/papers/ran/19.json","rows":94}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e44187a71bb45a6f6d83cbf0d5019c4741f0067ae204a3d26d0827113d91dc5f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}