{"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/masked-language-modeling","name":"Masked Language Modeling","slug":"masked-language-modeling","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":475,"papers_with_code":254,"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":7,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/difair","name":"DiFair","full_name":"","num_papers_in_archive":3},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/blbooks","name":"blbooks","full_name":"The British Library Books","num_papers_in_archive":1},{"url":"/dataset/geneutral","name":"GENEUTRAL","full_name":"","num_papers_in_archive":1},{"url":"/dataset/genter","name":"GENTER","full_name":"GEnder Name TEmplates with pRonouns","num_papers_in_archive":1},{"url":"/dataset/gentypes","name":"GENTYPES","full_name":"Gender Stereotypes","num_papers_in_archive":1},{"url":"/dataset/spanish-corpus-xix","name":"Spanish Corpus XIX","full_name":"19th Century Spanish Corpus","num_papers_in_archive":1}],"subtasks":[],"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":5,"rows_per_page":100,"shown":100,"of":475,"of_with_code":254,"tagged_in_all":475,"counts":{"archive_papers_tagged":475,"with_a_code_link":254,"where_syntology_ran_a_sample":67,"not_listed_spam_title":0,"listed":475,"listed_where_code_ran":67,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":48,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":48,"listed_every_run_a_failure_of_syntologys_instrument":19,"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/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/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/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/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/language-agnostic-bert-sentence-embedding","slug":"language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","date":"2020-07-03","arxiv_id":"2007.01852","repositories_listed":6,"syntology":null},{"url":"/paper/realm-retrieval-augmented-language-model-pre","slug":"realm-retrieval-augmented-language-model-pre","title":"REALM: Retrieval-Augmented Language Model Pre-Training","date":"2020-02-10","arxiv_id":"2002.08909","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/realm-retrieval-augmented-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2002.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08909"}},"official":{"repos":["google-research/language"],"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/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","repositories_listed":5,"syntology":null},{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/w2v-bert-combining-contrastive-learning-and","slug":"w2v-bert-combining-contrastive-learning-and","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","date":"2021-08-07","arxiv_id":"2108.06209","repositories_listed":4,"syntology":null},{"url":"/paper/talking-heads-attention","slug":"talking-heads-attention","title":"Talking-Heads Attention","date":"2020-03-05","arxiv_id":"2003.02436","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/talking-heads-attention#ran","syntology_url":"https://syntology.ai/paper/2003.02436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02436"}},"official":{"repos":["zygmuntz/hyperband"],"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/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","repositories_listed":3,"syntology":{"n":34,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":20,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}},"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]}}},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/self-supervised-log-parsing","slug":"self-supervised-log-parsing","title":"Self-Supervised Log Parsing","date":"2020-03-17","arxiv_id":"2003.07905","repositories_listed":3,"syntology":null},{"url":"/paper/simple-and-effective-masked-diffusion","slug":"simple-and-effective-masked-diffusion","title":"Simple and Effective Masked Diffusion Language Models","date":"2024-06-11","arxiv_id":"2406.07524","repositories_listed":2,"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":1,"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/simple-and-effective-masked-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.07524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07524"}},"official":{"repos":["kuleshov-group/mdlm"],"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/syllable-discovery-and-cross-lingual","slug":"syllable-discovery-and-cross-lingual","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","date":"2023-05-19","arxiv_id":"2305.11435","repositories_listed":2,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/syllable-discovery-and-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2305.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11435"}},"official":{"repos":["jasonppy/syllable-discovery"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-vision-language-pretraining","slug":"self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","arxiv_id":"2211.13594","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 4 unverified","sample_list":"/paper/self-supervised-vision-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2211.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13594"}},"official":{"repos":["pengfeiliheu/m2i2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","repositories_listed":2,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deep-bidirectional-language-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2210.09338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09338"}},"official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-attention-heads-selecting","slug":"mixture-of-attention-heads-selecting","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","date":"2022-10-11","arxiv_id":"2210.05144","repositories_listed":2,"syntology":{"n":17,"n_ran":13,"n_constructed":2,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mixture-of-attention-heads-selecting#ran","syntology_url":"https://syntology.ai/paper/2210.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05144"}},"official":{"repos":["yikangshen/moa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-pre-training-of-graph","slug":"unsupervised-pre-training-of-graph","title":"Unsupervised pre-training of graph transformers on patient population graphs","date":"2022-07-21","arxiv_id":"2207.10603","repositories_listed":2,"syntology":null},{"url":"/paper/smt-dta-improving-drug-target-affinity","slug":"smt-dta-improving-drug-target-affinity","title":"SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction","date":"2022-06-20","arxiv_id":"2206.09818","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/smt-dta-improving-drug-target-affinity#ran","syntology_url":"https://syntology.ai/paper/2206.09818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09818"}},"official":{"repos":["qizhipei/smt-dta","qizhipei/ssm-dta"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-self-supervised","slug":"an-empirical-study-of-self-supervised","title":"An Empirical Study Of Self-supervised Learning Approaches For Object Detection With Transformers","date":"2022-05-11","arxiv_id":"2205.05543","repositories_listed":2,"syntology":null},{"url":"/paper/vision-language-pre-training-for-boosting","slug":"vision-language-pre-training-for-boosting","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","date":"2022-04-29","arxiv_id":"2204.13867","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vision-language-pre-training-for-boosting#ran","syntology_url":"https://syntology.ai/paper/2204.13867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13867"}},"official":{"repos":["AlibabaResearch/AdvancedLiterateMachinery"],"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":["found_in_text"]}}},{"url":"/paper/transformer-quality-in-linear-time","slug":"transformer-quality-in-linear-time","title":"Transformer Quality in Linear Time","date":"2022-02-21","arxiv_id":"2202.10447","repositories_listed":2,"syntology":null},{"url":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","repositories_listed":2,"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":1,"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/dense-to-sparse-gate-for-mixture-of-experts-1#ran","syntology_url":"https://syntology.ai/paper/2112.14397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.14397"}},"official":{"repos":["codecaution/evomoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ibot-image-bert-pre-training-with-online","slug":"ibot-image-bert-pre-training-with-online","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","date":"2021-11-15","arxiv_id":"2111.07832","repositories_listed":2,"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/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}},"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/composable-sparse-fine-tuning-for-cross","slug":"composable-sparse-fine-tuning-for-cross","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","date":"2021-10-14","arxiv_id":"2110.07560","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/composable-sparse-fine-tuning-for-cross#ran","syntology_url":"https://syntology.ai/paper/2110.07560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07560"}},"official":{"repos":["cambridgeltl/composable-sft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledgeable-prompt-tuning-incorporating","slug":"knowledgeable-prompt-tuning-incorporating","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","date":"2021-08-04","arxiv_id":"2108.02035","repositories_listed":2,"syntology":null},{"url":"/paper/luna-linear-unified-nested-attention","slug":"luna-linear-unified-nested-attention","title":"Luna: Linear Unified Nested Attention","date":"2021-06-03","arxiv_id":"2106.01540","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/luna-linear-unified-nested-attention#ran","syntology_url":"https://syntology.ai/paper/2106.01540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01540"}},"official":{"repos":["XuezheMax/fairseq-apollo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/from-masked-language-modeling-to-translation","slug":"from-masked-language-modeling-to-translation","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","date":"2021-05-15","arxiv_id":"2105.07316","repositories_listed":2,"syntology":null},{"url":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","repositories_listed":2,"syntology":null},{"url":"/paper/structformer-joint-unsupervised-induction-of-1","slug":"structformer-joint-unsupervised-induction-of-1","title":"StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling","date":"2020-12-01","arxiv_id":"2012.00857","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-gram-pre-training-with-explicitly-n","slug":"ernie-gram-pre-training-with-explicitly-n","title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","date":"2020-10-23","arxiv_id":"2010.12148","repositories_listed":2,"syntology":null},{"url":"/paper/semi-supervised-speech-language-joint-pre-1","slug":"semi-supervised-speech-language-joint-pre-1","title":"SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding","date":"2020-10-05","arxiv_id":"2010.02295","repositories_listed":2,"syntology":null},{"url":"/paper/intermediate-training-of-bert-for-product","slug":"intermediate-training-of-bert-for-product","title":"Intermediate Training of BERT for Product Matching","date":"2020-08-31","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/the-lottery-ticket-hypothesis-for-pre-trained","slug":"the-lottery-ticket-hypothesis-for-pre-trained","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","date":"2020-07-23","arxiv_id":"2007.12223","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-lottery-ticket-hypothesis-for-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2007.12223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12223"}},"official":{"repos":["TAMU-VITA/BERT-Tickets","VITA-Group/BERT-Tickets"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-training-via-paraphrasing","slug":"pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","arxiv_id":"2006.15020","repositories_listed":2,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":2,"n_no_contract":7,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pre-training-via-paraphrasing#ran","syntology_url":"https://syntology.ai/paper/2006.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15020"}},"official":null}},{"url":"/paper/massive-choice-ample-tasks-machamp-a-toolkit","slug":"massive-choice-ample-tasks-machamp-a-toolkit","title":"Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP","date":"2020-05-29","arxiv_id":"2005.14672","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/massive-choice-ample-tasks-machamp-a-toolkit#ran","syntology_url":"https://syntology.ai/paper/2005.14672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14672"}},"official":{"repos":["machamp-nlp/machamp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-the-knowledge-of-bert-for-text-1","slug":"distilling-the-knowledge-of-bert-for-text-1","title":"Distilling Knowledge Learned in BERT for Text Generation","date":"2019-11-10","arxiv_id":"1911.03829","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/distilling-the-knowledge-of-bert-for-text-1#ran","syntology_url":"https://syntology.ai/paper/1911.03829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03829"}},"official":{"repos":["ChenRocks/Distill-BERT-Textgen"],"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":["official"]}}},{"url":"/paper/190409324","slug":"190409324","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","date":"2019-04-19","arxiv_id":"1904.09324","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/190409324#ran","syntology_url":"https://syntology.ai/paper/1904.09324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09324"}},"official":{"repos":["facebookresearch/Mask-Predict"],"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/bmfm-rna-an-open-framework-for-building-and","slug":"bmfm-rna-an-open-framework-for-building-and","title":"BMFM-RNA: An Open Framework for Building and Evaluating Transcriptomic Foundation Models","date":"2025-06-17","arxiv_id":"2506.14861","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-sequence-models-for-enhanced","slug":"diffusion-sequence-models-for-enhanced","title":"Diffusion Sequence Models for Enhanced Protein Representation and Generation","date":"2025-06-09","arxiv_id":"2506.08293","repositories_listed":1,"syntology":null},{"url":"/paper/masked-language-models-are-good-heterogeneous","slug":"masked-language-models-are-good-heterogeneous","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","date":"2025-06-06","arxiv_id":"2506.06157","repositories_listed":1,"syntology":null},{"url":"/paper/gigaam-efficient-self-supervised-learner-for","slug":"gigaam-efficient-self-supervised-learner-for","title":"GigaAM: Efficient Self-Supervised Learner for Speech Recognition","date":"2025-06-01","arxiv_id":"2506.01192","repositories_listed":1,"syntology":null},{"url":"/paper/creopep-a-universal-deep-learning-framework","slug":"creopep-a-universal-deep-learning-framework","title":"CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and Optimization","date":"2025-05-05","arxiv_id":"2505.02887","repositories_listed":1,"syntology":null},{"url":"/paper/asma-tune-unlocking-llms-assembly-code","slug":"asma-tune-unlocking-llms-assembly-code","title":"ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction Tuning","date":"2025-03-14","arxiv_id":"2503.11617","repositories_listed":1,"syntology":null},{"url":"/paper/task-informed-anti-curriculum-by-masking","slug":"task-informed-anti-curriculum-by-masking","title":"Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text","date":"2025-02-18","arxiv_id":"2502.12953","repositories_listed":1,"syntology":null},{"url":"/paper/mask-enhanced-autoregressive-prediction-pay","slug":"mask-enhanced-autoregressive-prediction-pay","title":"Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More","date":"2025-02-11","arxiv_id":"2502.07490","repositories_listed":1,"syntology":null},{"url":"/paper/long-vita-scaling-large-multi-modal-models-to","slug":"long-vita-scaling-large-multi-modal-models-to","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray","date":"2025-02-07","arxiv_id":"2502.05177","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-or-bert-why-not-both","slug":"gpt-or-bert-why-not-both","title":"GPT or BERT: why not both?","date":"2024-10-31","arxiv_id":"2410.24159","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/gpt-or-bert-why-not-both#ran","syntology_url":"https://syntology.ai/paper/2410.24159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24159"}},"official":{"repos":["ltgoslo/gpt-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/less-is-more-pre-training-cross-lingual-small","slug":"less-is-more-pre-training-cross-lingual-small","title":"Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies","date":"2024-10-30","arxiv_id":"2410.22886","repositories_listed":1,"syntology":null},{"url":"/paper/long-context-protein-language-model","slug":"long-context-protein-language-model","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","date":"2024-10-29","arxiv_id":"2411.08909","repositories_listed":1,"syntology":null},{"url":"/paper/distributionally-robust-self-supervised","slug":"distributionally-robust-self-supervised","title":"Distributionally robust self-supervised learning for tabular data","date":"2024-10-11","arxiv_id":"2410.08511","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","repositories_listed":1,"syntology":null},{"url":"/paper/sciprompt-knowledge-augmented-prompting-for","slug":"sciprompt-knowledge-augmented-prompting-for","title":"SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics","date":"2024-10-02","arxiv_id":"2410.01946","repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-free-text-medical","slug":"generating-synthetic-free-text-medical","title":"Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling","date":"2024-09-15","arxiv_id":"2409.09831","repositories_listed":1,"syntology":null},{"url":"/paper/domurls-bert-pre-trained-bert-based-model-for","slug":"domurls-bert-pre-trained-bert-based-model-for","title":"DomURLs_BERT: Pre-trained BERT-based Model for Malicious Domains and URLs Detection and Classification","date":"2024-09-13","arxiv_id":"2409.09143","repositories_listed":1,"syntology":null},{"url":"/paper/how-transformers-learn-structured-data","slug":"how-transformers-learn-structured-data","title":"How transformers learn structured data: insights from hierarchical filtering","date":"2024-08-27","arxiv_id":"2408.15138","repositories_listed":1,"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":1,"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/how-transformers-learn-structured-data#ran","syntology_url":"https://syntology.ai/paper/2408.15138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15138"}},"official":{"repos":["emanuele-moscato/tree-language-paper-submission"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mistral-splade-llms-for-for-better-learned","slug":"mistral-splade-llms-for-for-better-learned","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","date":"2024-08-20","arxiv_id":"2408.11119","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-efficiency-adaptive-masking-for","slug":"unlocking-efficiency-adaptive-masking-for","title":"Unlocking Efficiency: Adaptive Masking for Gene Transformer Models","date":"2024-08-13","arxiv_id":"2408.07180","repositories_listed":1,"syntology":null},{"url":"/paper/autoscale-automatic-prediction-of-compute","slug":"autoscale-automatic-prediction-of-compute","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","date":"2024-07-29","arxiv_id":"2407.20177","repositories_listed":1,"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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/autoscale-automatic-prediction-of-compute#ran","syntology_url":"https://syntology.ai/paper/2407.20177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20177"}},"official":{"repos":["feiyang-k/autoscale"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/xlip-cross-modal-attention-masked-modelling","slug":"xlip-cross-modal-attention-masked-modelling","title":"MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training","date":"2024-07-28","arxiv_id":"2407.19546","repositories_listed":1,"syntology":null},{"url":"/paper/promises-and-pitfalls-of-generative-masked","slug":"promises-and-pitfalls-of-generative-masked","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","date":"2024-07-22","arxiv_id":"2407.21046","repositories_listed":1,"syntology":null},{"url":"/paper/historical-ink-semantic-shift-detection-for","slug":"historical-ink-semantic-shift-detection-for","title":"Historical Ink: Semantic Shift Detection for 19th Century Spanish","date":"2024-07-08","arxiv_id":"2407.12852","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-multilingual-llms-to-low-resource","slug":"adapting-multilingual-llms-to-low-resource","title":"Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters","date":"2024-07-01","arxiv_id":"2407.01406","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-style-in-context-learning-for-few","slug":"retrieval-style-in-context-learning-for-few","title":"Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification","date":"2024-06-25","arxiv_id":"2406.17534","repositories_listed":1,"syntology":null},{"url":"/paper/queerbench-quantifying-discrimination-in","slug":"queerbench-quantifying-discrimination-in","title":"QueerBench: Quantifying Discrimination in Language Models Toward Queer Identities","date":"2024-06-18","arxiv_id":"2406.12399","repositories_listed":1,"syntology":null},{"url":"/paper/vcr-visual-caption-restoration","slug":"vcr-visual-caption-restoration","title":"VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text","date":"2024-06-10","arxiv_id":"2406.06462","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"10 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vcr-visual-caption-restoration#ran","syntology_url":"https://syntology.ai/paper/2406.06462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06462"}},"official":{"repos":["tianyu-z/vcr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seventeenth-century-spanish-american-notary","slug":"seventeenth-century-spanish-american-notary","title":"Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models","date":"2024-06-09","arxiv_id":"2406.05812","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-neural-networks-for-emotion","slug":"transformer-based-neural-networks-for-emotion","title":"Transformer based neural networks for emotion recognition in conversations","date":"2024-05-18","arxiv_id":"2405.11222","repositories_listed":1,"syntology":null},{"url":"/paper/self-distillation-improves-dna-sequence","slug":"self-distillation-improves-dna-sequence","title":"Self-Distillation Improves DNA Sequence Inference","date":"2024-05-14","arxiv_id":"2405.08538","repositories_listed":1,"syntology":null},{"url":"/paper/promptcl-improving-event-representation-via","slug":"promptcl-improving-event-representation-via","title":"PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning","date":"2024-04-27","arxiv_id":"2404.17877","repositories_listed":1,"syntology":null},{"url":"/paper/fingerprinting-web-servers-through","slug":"fingerprinting-web-servers-through","title":"Fingerprinting web servers through Transformer-encoded HTTP response headers","date":"2024-03-26","arxiv_id":"2404.00056","repositories_listed":1,"syntology":null},{"url":"/paper/merging-text-transformer-models-from","slug":"merging-text-transformer-models-from","title":"Merging Text Transformer Models from Different Initializations","date":"2024-03-01","arxiv_id":"2403.00986","repositories_listed":1,"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/merging-text-transformer-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.00986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00986"}},"official":{"repos":["nverma1/merging-text-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/nextlevelbert-investigating-masked-language","slug":"nextlevelbert-investigating-masked-language","title":"NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents","date":"2024-02-27","arxiv_id":"2402.17682","repositories_listed":1,"syntology":null},{"url":"/paper/substrate-prediction-for-ripp-biosynthetic","slug":"substrate-prediction-for-ripp-biosynthetic","title":"Substrate Prediction for RiPP Biosynthetic Enzymes via Masked Language Modeling and Transfer Learning","date":"2024-02-23","arxiv_id":"2402.15181","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-social-biases-in-masked-language","slug":"measuring-social-biases-in-masked-language","title":"Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality","date":"2024-02-21","arxiv_id":"2402.13954","repositories_listed":1,"syntology":null},{"url":"/paper/codeart-better-code-models-by-attention","slug":"codeart-better-code-models-by-attention","title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","date":"2024-02-19","arxiv_id":"2402.11842","repositories_listed":1,"syntology":null},{"url":"/paper/punctuation-restoration-improves-structure","slug":"punctuation-restoration-improves-structure","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","date":"2024-02-13","arxiv_id":"2402.08382","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-synonym-bert-based-adversarial","slug":"arabic-synonym-bert-based-adversarial","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","date":"2024-02-05","arxiv_id":"2402.03477","repositories_listed":1,"syntology":null},{"url":"/paper/interpretation-of-intracardiac-electrograms","slug":"interpretation-of-intracardiac-electrograms","title":"Interpretation of Intracardiac Electrograms Through Textual Representations","date":"2024-02-02","arxiv_id":"2402.01115","repositories_listed":1,"syntology":null},{"url":"/paper/endowing-protein-language-models-with","slug":"endowing-protein-language-models-with","title":"Endowing Protein Language Models with Structural Knowledge","date":"2024-01-26","arxiv_id":"2401.14819","repositories_listed":1,"syntology":null},{"url":"/paper/a-character-based-steganography-using-masked","slug":"a-character-based-steganography-using-masked","title":"A character-based steganography using masked language modeling","date":"2024-01-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mosaicbert-a-bidirectional-encoder-optimized-1","slug":"mosaicbert-a-bidirectional-encoder-optimized-1","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","date":"2023-12-29","arxiv_id":"2312.17482","repositories_listed":1,"syntology":null},{"url":"/paper/ecamp-entity-centered-context-aware-medical","slug":"ecamp-entity-centered-context-aware-medical","title":"ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training","date":"2023-12-20","arxiv_id":"2312.13316","repositories_listed":1,"syntology":null},{"url":"/paper/labrador-exploring-the-limits-of-masked","slug":"labrador-exploring-the-limits-of-masked","title":"Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data","date":"2023-12-09","arxiv_id":"2312.11502","repositories_listed":1,"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/labrador-exploring-the-limits-of-masked#ran","syntology_url":"https://syntology.ai/paper/2312.11502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11502"}},"official":{"repos":["davidbellamy/labrador"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-prompt-based-self-training-with","slug":"boosting-prompt-based-self-training-with","title":"Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification","date":"2023-12-08","arxiv_id":"2312.04982","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactually-probing-language-identity-in","slug":"counterfactually-probing-language-identity-in","title":"Counterfactually Probing Language Identity in Multilingual Models","date":"2023-10-29","arxiv_id":"2310.18862","repositories_listed":1,"syntology":null},{"url":"/paper/lil-bevo-explorations-of-strategies-for","slug":"lil-bevo-explorations-of-strategies-for","title":"Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways","date":"2023-10-26","arxiv_id":"2310.17591","repositories_listed":1,"syntology":null},{"url":"/paper/the-distributional-hypothesis-does-not-fully","slug":"the-distributional-hypothesis-does-not-fully","title":"The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining","date":"2023-10-25","arxiv_id":"2310.16261","repositories_listed":1,"syntology":null},{"url":"/paper/geolm-empowering-language-models-for","slug":"geolm-empowering-language-models-for","title":"GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding","date":"2023-10-23","arxiv_id":"2310.14478","repositories_listed":1,"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":11,"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/geolm-empowering-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2310.14478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14478"}},"official":{"repos":["knowledge-computing/geolm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/difair-a-benchmark-for-disentangled","slug":"difair-a-benchmark-for-disentangled","title":"DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias","date":"2023-10-22","arxiv_id":"2310.14329","repositories_listed":1,"syntology":null},{"url":"/paper/fata-trans-field-and-time-aware-transformer","slug":"fata-trans-field-and-time-aware-transformer","title":"FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data","date":"2023-10-20","arxiv_id":"2310.13818","repositories_listed":1,"syntology":null},{"url":"/paper/film-fill-in-language-models-for-any-order","slug":"film-fill-in-language-models-for-any-order","title":"FiLM: Fill-in Language Models for Any-Order Generation","date":"2023-10-15","arxiv_id":"2310.09930","repositories_listed":1,"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/film-fill-in-language-models-for-any-order#ran","syntology_url":"https://syntology.ai/paper/2310.09930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09930"}},"official":{"repos":["shentianxiao/film"],"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":["official"]}}},{"url":"/paper/pepmlm-target-sequence-conditioned-generation","slug":"pepmlm-target-sequence-conditioned-generation","title":"PepMLM: Target Sequence-Conditioned Generation of Therapeutic Peptide Binders via Span Masked Language Modeling","date":"2023-10-05","arxiv_id":"2310.03842","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/pepmlm-target-sequence-conditioned-generation#ran","syntology_url":"https://syntology.ai/paper/2310.03842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03842"}},"official":{"repos":["programmablebio/pepmlm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-task-semantic-decomposition-framework","slug":"a-multi-task-semantic-decomposition-framework","title":"A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER","date":"2023-08-28","arxiv_id":"2308.14533","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-language-models-can-perform-many","slug":"diffusion-language-models-can-perform-many","title":"Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning","date":"2023-08-23","arxiv_id":"2308.12219","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-language-models-can-perform-many#ran","syntology_url":"https://syntology.ai/paper/2308.12219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12219"}},"official":{"repos":["yegcjs/diffusionllm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-training-with-aspect-content-text-mutual","slug":"pre-training-with-aspect-content-text-mutual","title":"Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval","date":"2023-08-22","arxiv_id":"2308.11474","repositories_listed":1,"syntology":null}],"syntology_records":35,"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":67,"papers_where_code_ran_first_page":"/task/masked-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":5,"url":"/task/masked-language-modeling/papers/2","json":"/task/masked-language-modeling/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/masked-language-modeling/papers/3","json":"/task/masked-language-modeling/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/masked-language-modeling/papers/4","json":"/task/masked-language-modeling/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/masked-language-modeling/papers/5","json":"/task/masked-language-modeling/papers/5.json","rows":75},{"order":"ran","page":1,"of":1,"url":"/task/masked-language-modeling/papers/ran/1","json":"/task/masked-language-modeling/papers/ran/1.json","rows":67}],"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":"61f8bf5731b157636a207debe46343a068355a6cb9cae8e15dffa61948095193","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}