{"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":"/dataset/scidocs","name":"SciDocs","full_name":"SciDocs","description_markdown":"SciDocs evaluation framework consists of a suite of evaluation tasks designed for document-level tasks.\r\n\r\nSource: [Allen Institute for AI](https://github.com/allenai/scidocs)","description_withheld":null,"homepage":"https://github.com/allenai/scidocs","introduced_date":"2020-04-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/document-level-representation-learning-using","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","first_author":"Arman Cohan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Representation Learning","url":"/task/representation-learning","datasets_with_task":"/datasets/task/representation-learning"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Re-Ranking","url":"/task/re-ranking","datasets_with_task":"/datasets/task/re-ranking"}],"languages":[],"variants":["SciDocs"],"data_loaders":[{"repo":"https://github.com/allenai/scidocs","url":"https://github.com/allenai/scidocs","frameworks":["pytorch"]}],"num_papers_in_archive":57,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/representation-learning-on-scidocs","task":"Representation Learning","dataset_variant":"SciDocs","rows":7,"metrics":["Avg."],"first_row_in_archive_order":{"model":"SciNCL","paper":"/paper/neighborhood-contrastive-learning-for-1","metrics":{"Avg.":"81.8"},"code_links":[{"title":"malteos/scincl","url":"https://github.com/malteos/scincl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-scidocs","task":"Text Retrieval","dataset_variant":"SciDocs","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"nDCG@10":"67.6"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":4,"of":4,"counts":{"papers_with_a_benchmark_row":4,"with_a_code_link":4,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/paper/neighborhood-contrastive-learning-for-1","slug":"neighborhood-contrastive-learning-for-1","title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","date":"2022-02-14","arxiv_id":"2202.06671","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["malteos/scincl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neighborhood-contrastive-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.06671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06671"}}}},{"paper":"/paper/document-level-representation-learning-using","slug":"document-level-representation-learning-using","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","date":"2020-04-15","arxiv_id":"2004.07180","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["allenai/scidocs","allenai/specter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/document-level-representation-learning-using#ran","syntology_url":"https://syntology.ai/paper/2004.07180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07180"}}}},{"paper":"/paper/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":4,"samples_unverified":10,"pointer_only_for_licence":3,"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/paper/neighborhood-contrastive-learning-for-1","slug":"neighborhood-contrastive-learning-for-1","title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","date":"2022-02-14","arxiv_id":"2202.06671","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["malteos/scincl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neighborhood-contrastive-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.06671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06671"}}}},{"paper":"/paper/document-level-representation-learning-using","slug":"document-level-representation-learning-using","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","date":"2020-04-15","arxiv_id":"2004.07180","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["allenai/scidocs","allenai/specter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/document-level-representation-learning-using#ran","syntology_url":"https://syntology.ai/paper/2004.07180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07180"}}}},{"paper":"/paper/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":4,"samples_unverified":10,"pointer_only_for_licence":3,"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/scidocs/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/scidocs/papers/ran/1","json":"/dataset/scidocs/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":49,"samples_ran":31,"samples_constructed":1,"samples_ran_checked":24,"samples_ran_instrument_failed":7,"samples_unverified":18,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":5,"papers_placed":1,"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/text-retrieval-on-scidocs","since_archive":"/sota/text-retrieval-on-scidocs#since-judged","papers_judged":5,"placed":1}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1af76e4e2c11d8583aee9ff5fc9a7c18c93d8b701ef32b0690815a7378b268b5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}