{"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/sentence-completion","name":"Sentence Completion","slug":"sentence-completion","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":"archive_url"},"counts":{"papers_tagged":91,"papers_with_code":49,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/sentence-completion-on-hellaswag","slug":"sentence-completion-on-hellaswag","dataset":"HellaSwag","dataset_url":"/dataset/hellaswag","rows_in_archive":89,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CompassMTL 567M with Tailor","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","paper_url":"/paper/task-compass-scaling-multi-task-pre-training","paper_date":"2022-10-12","arxiv_id":"2210.06277","code_links":[{"title":"cooelf/compassmtl","url":"https://github.com/cooelf/compassmtl"}],"syntology":null}}],"datasets":[{"url":"/dataset/hellaswag","name":"HellaSwag","full_name":"","num_papers_in_archive":994},{"url":"/dataset/xp3","name":"xP3","full_name":"","num_papers_in_archive":34}],"subtasks":[{"url":"/task/hurtful-sentence-completion","name":"Hurtful Sentence Completion"}],"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":1,"rows_per_page":100,"shown":91,"of":91,"of_with_code":49,"tagged_in_all":91,"counts":{"archive_papers_tagged":91,"with_a_code_link":49,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":91,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/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/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_honours":3,"n_violates":0,"n_no_contract":22,"n_pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}},"official":{"repos":["facebookresearch/llama"],"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/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/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_honours":1,"n_violates":1,"n_no_contract":18,"n_pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}},"official":{"repos":["facebookresearch/llama"],"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/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 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; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}},"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]}}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"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, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"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/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/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/factuality-enhanced-language-models-for-open","slug":"factuality-enhanced-language-models-for-open","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","date":"2022-06-09","arxiv_id":"2206.04624","repositories_listed":5,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/factuality-enhanced-language-models-for-open#ran","syntology_url":"https://syntology.ai/paper/2206.04624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04624"}},"official":{"repos":["nayeon7lee/factualityprompt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}},"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-efficient-sparsity-crafting-from","slug":"parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/sheared-llama-accelerating-language-model-pre","slug":"sheared-llama-accelerating-language-model-pre","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","date":"2023-10-10","arxiv_id":"2310.06694","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}},"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-subtler-biases-in-llms-ageism","slug":"investigating-subtler-biases-in-llms-ageism","title":"Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models","date":"2023-09-16","arxiv_id":"2309.08902","repositories_listed":2,"syntology":null},{"url":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","repositories_listed":2,"syntology":null},{"url":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","repositories_listed":2,"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":3,"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/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}},"official":{"repos":["joeljang/elm"],"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":["official","unlocated"]}}},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/using-deepspeed-and-megatron-to-train","slug":"using-deepspeed-and-megatron-to-train","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","date":"2022-01-28","arxiv_id":"2201.11990","repositories_listed":2,"syntology":null},{"url":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","repositories_listed":2,"syntology":null},{"url":"/paper/hellaswag-can-a-machine-really-finish-your","slug":"hellaswag-can-a-machine-really-finish-your","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","date":"2019-05-19","arxiv_id":"1905.07830","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}},"official":null}},{"url":"/paper/aqua-an-adversarially-authored-question","slug":"aqua-an-adversarially-authored-question","title":"CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense","date":"2019-04-08","arxiv_id":"1904.04365","repositories_listed":2,"syntology":null},{"url":"/paper/recurrent-memory-networks-for-language","slug":"recurrent-memory-networks-for-language","title":"Recurrent Memory Networks for Language Modeling","date":"2016-01-06","arxiv_id":"1601.01272","repositories_listed":2,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","slug":"katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}},"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-sentence-completion-with-a","slug":"language-model-sentence-completion-with-a","title":"Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method","date":"2024-02-09","arxiv_id":"2402.06125","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-model-sentence-completion-with-a#ran","syntology_url":"https://syntology.ai/paper/2402.06125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06125"}},"official":{"repos":["joshua-zingale/plug-and-play-rst-ctg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mahanlp-a-marathi-natural-language-processing","slug":"mahanlp-a-marathi-natural-language-processing","title":"mahaNLP: A Marathi Natural Language Processing Library","date":"2023-11-05","arxiv_id":"2311.02579","repositories_listed":1,"syntology":null},{"url":"/paper/btrec-bert-based-trajectory-recommendation","slug":"btrec-bert-based-trajectory-recommendation","title":"BTRec: BERT-Based Trajectory Recommendation for Personalized Tours","date":"2023-10-30","arxiv_id":"2310.19886","repositories_listed":1,"syntology":null},{"url":"/paper/scone-benchmarking-negation-reasoning-in","slug":"scone-benchmarking-negation-reasoning-in","title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","date":"2023-05-30","arxiv_id":"2305.19426","repositories_listed":1,"syntology":null},{"url":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","repositories_listed":1,"syntology":null},{"url":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","repositories_listed":1,"syntology":null},{"url":"/paper/crosslingual-generalization-through-multitask","slug":"crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crosslingual-generalization-through-multitask#ran","syntology_url":"https://syntology.ai/paper/2211.01786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01786"}},"official":{"repos":["bigscience-workshop/xmtf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}},"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/discosense-commonsense-reasoning-with","slug":"discosense-commonsense-reasoning-with","title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","date":"2022-10-22","arxiv_id":"2210.12478","repositories_listed":1,"syntology":null},{"url":"/paper/task-compass-scaling-multi-task-pre-training","slug":"task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","date":"2022-10-12","arxiv_id":"2210.06277","repositories_listed":1,"syntology":null},{"url":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","repositories_listed":1,"syntology":null},{"url":"/paper/sc-ques-a-sentence-completion-question","slug":"sc-ques-a-sentence-completion-question","title":"SC-Ques: A Sentence Completion Question Dataset for English as a Second Language Learners","date":"2022-06-24","arxiv_id":"2206.12036","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-harmful-sentence-completion-in","slug":"measuring-harmful-sentence-completion-in","title":"Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/solving-esl-sentence-completion-questions-via","slug":"solving-esl-sentence-completion-questions-via","title":"Solving ESL Sentence Completion Questions via Pre-trained Neural Language Models","date":"2021-07-15","arxiv_id":"2107.07122","repositories_listed":1,"syntology":null},{"url":"/paper/honest-measuring-hurtful-sentence-completion","slug":"honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unicorn-on-rainbow-a-universal-commonsense","slug":"unicorn-on-rainbow-a-universal-commonsense","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","date":"2021-03-24","arxiv_id":"2103.13009","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unicorn-on-rainbow-a-universal-commonsense#ran","syntology_url":"https://syntology.ai/paper/2103.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13009"}},"official":{"repos":["allenai/rainbow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/geppetto-carves-italian-into-a-language-model","slug":"geppetto-carves-italian-into-a-language-model","title":"GePpeTto Carves Italian into a Language Model","date":"2020-04-29","arxiv_id":"2004.14253","repositories_listed":1,"syntology":null},{"url":"/paper/codah-an-adversarially-authored-question","slug":"codah-an-adversarially-authored-question","title":"CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantically-and-additively","slug":"learning-semantically-and-additively","title":"Learning Semantically and Additively Compositional Distributional Representations","date":"2016-06-08","arxiv_id":"1606.02461","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-architecture-for-semantic-matching","slug":"a-deep-architecture-for-semantic-matching","title":"A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations","date":"2015-11-26","arxiv_id":"1511.08277","repositories_listed":1,"syntology":null},{"url":"/paper/top-down-tree-long-short-term-memory-networks","slug":"top-down-tree-long-short-term-memory-networks","title":"Top-down Tree Long Short-Term Memory Networks","date":"2015-10-31","arxiv_id":"1511.00060","repositories_listed":1,"syntology":null},{"url":"/paper/dependency-recurrent-neural-language-models","slug":"dependency-recurrent-neural-language-models","title":"Dependency Recurrent Neural Language Models for Sentence Completion","date":"2015-07-05","arxiv_id":"1507.01193","repositories_listed":1,"syntology":null},{"url":null,"slug":"evaluating-gender-bias-in-large-language-1","title":"Evaluating Gender Bias in Large Language Models","date":"2024-11-14","arxiv_id":"2411.09826","repositories_listed":0,"syntology":null},{"url":null,"slug":"biasalert-a-plug-and-play-tool-for-social","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","date":"2024-07-14","arxiv_id":"2407.10241","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-llms-by-compression","title":"Ranking LLMs by compression","date":"2024-06-20","arxiv_id":"2406.14171","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-bangla-language-next-word","title":"Enhancing Bangla Language Next Word Prediction and Sentence Completion through Extended RNN with Bi-LSTM Model On N-gram Language","date":"2024-05-03","arxiv_id":"2405.01873","repositories_listed":0,"syntology":null},{"url":null,"slug":"illuminating-the-black-box-a-psychometric","title":"Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models","date":"2023-12-21","arxiv_id":"2312.14202","repositories_listed":0,"syntology":null},{"url":"/paper/llm-in-a-flash-efficient-large-language-model","slug":"llm-in-a-flash-efficient-large-language-model","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","date":"2023-12-12","arxiv_id":"2312.11514","repositories_listed":0,"syntology":null},{"url":"/paper/the-falcon-series-of-open-language-models","slug":"the-falcon-series-of-open-language-models","title":"The Falcon Series of Open Language Models","date":"2023-11-28","arxiv_id":"2311.16867","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-language-models-as-a-source-of","title":"Exploiting Language Models as a Source of Knowledge for Cognitive Agents","date":"2023-09-05","arxiv_id":"2310.06846","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-was-a-data-augmentation-method-with-gpt-2","title":"I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection","date":"2023-08-08","arxiv_id":"2308.04109","repositories_listed":0,"syntology":null},{"url":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","repositories_listed":0,"syntology":null},{"url":null,"slug":"numeracy-from-literacy-data-science-as-an","title":"Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models","date":"2023-01-31","arxiv_id":"2301.13382","repositories_listed":0,"syntology":null},{"url":null,"slug":"poibert-a-transformer-based-model-for-the","title":"POIBERT: A Transformer-based Model for the Tour Recommendation Problem","date":"2022-12-16","arxiv_id":"2212.13900","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-causality-in-gpt-2-a-case-study","title":"Implicit causality in GPT-2: a case study","date":"2022-12-08","arxiv_id":"2212.04348","repositories_listed":0,"syntology":null},{"url":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","repositories_listed":0,"syntology":null},{"url":null,"slug":"effidit-your-ai-writing-assistant","title":"Effidit: Your AI Writing Assistant","date":"2022-08-03","arxiv_id":"2208.01815","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-language-modeling-with-sparse-all","slug":"efficient-language-modeling-with-sparse-all","title":"Efficient Language Modeling with Sparse all-MLP","date":"2022-03-14","arxiv_id":"2203.06850","repositories_listed":0,"syntology":null},{"url":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-as-a-knowledge-source-for","title":"Language Models as a Knowledge Source for Cognitive Agents","date":"2021-09-17","arxiv_id":"2109.08270","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-n-gram-extraction","title":"Differentially Private n-gram Extraction","date":"2021-08-05","arxiv_id":"2108.02831","repositories_listed":0,"syntology":null},{"url":null,"slug":"clause-final-verb-prediction-in-hindi","title":"Clause Final Verb Prediction in Hindi: Evidence for Noisy Channel Model of Communication","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-better-sentence-representation-with","title":"Learning Better Sentence Representation with Syntax Information","date":"2021-01-09","arxiv_id":"2101.03343","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-detection-of-sentence-completion","title":"On-Device detection of sentence completion for voice assistants with low-memory footprint","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mathematical-exploration-of-why-language-1","title":"A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks","date":"2020-10-07","arxiv_id":"2010.03648","repositories_listed":0,"syntology":null},{"url":null,"slug":"defining-and-evaluating-fair-natural-language-1","title":"Defining and Evaluating Fair Natural Language Generation","date":"2020-07-28","arxiv_id":"2008.01548","repositories_listed":0,"syntology":null},{"url":null,"slug":"icap-interative-image-captioning-with","title":"iCap: Interactive Image Captioning with Predictive Text","date":"2020-01-31","arxiv_id":"2001.11782","repositories_listed":0,"syntology":null},{"url":null,"slug":"filling-conversation-ellipsis-for-better","title":"Filling Conversation Ellipsis for Better Social Dialog Understanding","date":"2019-11-25","arxiv_id":"1911.10776","repositories_listed":0,"syntology":null},{"url":"/paper/towards-generalizable-neuro-symbolic-systems","slug":"towards-generalizable-neuro-symbolic-systems","title":"Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering","date":"2019-10-30","arxiv_id":"1910.14087","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-word-representations-a-sub-sampled","title":"Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling","date":"2019-10-21","arxiv_id":"1910.09362","repositories_listed":0,"syntology":null},{"url":null,"slug":"second-order-contexts-from-lexical","title":"Second-order contexts from lexical substitutes for few-shot learning of word representations","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-clustering-using-maximal-matrix","title":"Probabilistic Clustering Using Maximal Matrix Norm Couplings","date":"2018-10-10","arxiv_id":"1810.04738","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-model-for-word-prediction-using-naive","title":"Hybrid Model For Word Prediction Using Naive Bayes and Latent Information","date":"2018-03-02","arxiv_id":"1803.00985","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-word-representations-carrying","title":"Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts","date":"2017-10-29","arxiv_id":"1710.10574","repositories_listed":0,"syntology":null},{"url":null,"slug":"expect-the-unexpected-harnessing-sentence","title":"Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection","date":"2017-07-19","arxiv_id":"1707.06151","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-linguistic-features-for-sentence","title":"Exploiting Linguistic Features for Sentence Completion","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-lstm-clstm-models-for-large-scale","title":"Contextual LSTM (CLSTM) models for Large scale NLP tasks","date":"2016-02-19","arxiv_id":"1602.06291","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-fine-tuning-for-word-embedding","title":"Supervised Fine Tuning for Word Embedding with Integrated Knowledge","date":"2015-05-29","arxiv_id":"1505.07931","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-word-representations-with","title":"Learning Word Representations with Hierarchical Sparse Coding","date":"2014-06-08","arxiv_id":"1406.2035","repositories_listed":0,"syntology":null},{"url":null,"slug":"refinements-to-interactive-translation","title":"Refinements to Interactive Translation Prediction Based on Search Graphs","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-language-models-for-sentence","title":"Dependency Language Models for Sentence Completion","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularization-and-nonlinearities-for-neural","title":"Regularization and nonlinearities for neural language models: when are they needed?","date":"2013-01-23","arxiv_id":"1301.5650","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-approaches-to-sentence","title":"Computational Approaches to Sentence Completion","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sentence-completion-in-dialogues","title":"Improving Sentence Completion in Dialogues with Multi-Modal Features","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":21,"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":29,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/sentence-completion-on-hellaswag","since_archive":"/sota/sentence-completion-on-hellaswag#since-judged","papers_judged":29,"placed":0}]},"papers_where_code_ran":20,"papers_where_code_ran_first_page":"/task/sentence-completion/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":"ran","page":1,"of":1,"url":"/task/sentence-completion/papers/ran/1","json":"/task/sentence-completion/papers/ran/1.json","rows":20}],"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":"849ae93f8ba93d2c310329ad39116f6aa5a5fa9d403bc83c3f9446eace573373","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}