{"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/hoc-1","name":"HOC","full_name":"Hallmarks of Cancer","description_markdown":"The **Hallmarks of Cancer** (**HOC*) corpus consists of 1852 PubMed publication abstracts manually annotated by experts according to the Hallmarks of Cancer taxonomy. The taxonomy consists of 37 classes in a hierarchy. Zero or more class labels are assigned to each sentence in the corpus. \r\n\r\nSource: [Hallmarks of Cancer Corpus](https://s-baker.net/resource/hoc/)\r\n\r\nImage source: [Hallmarks of Cancer Corpus](https://s-baker.net/resource/hoc/)","description_withheld":null,"homepage":"https://s-baker.net/resource/hoc/","introduced_date":"2015-10-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/automatic-semantic-classification-of","title":"Automatic semantic classification of scientific literature according to the hallmarks of cancer","first_author":"Simon Baker","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HOC"],"data_loaders":[],"num_papers_in_archive":37,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-classification-on-hoc","task":"Document Classification","dataset_variant":"HOC","rows":5,"metrics":["F1","Micro F1"],"first_row_in_archive_order":{"model":"BioLinkBERT (large)","paper":"/paper/linkbert-pretraining-language-models-with","metrics":{"F1":"88.1","Micro F1":"84.87"},"code_links":[{"title":"michiyasunaga/LinkBERT","url":"https://github.com/michiyasunaga/LinkBERT"}]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":5,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":5,"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/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}}}},{"paper":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/transfer-learning-in-biomedical-natural","slug":"transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","arxiv_id":"1906.05474","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ncbi-nlp/BLUE_Benchmark","ncbi-nlp/NCBI_BERT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transfer-learning-in-biomedical-natural#ran","syntology_url":"https://syntology.ai/paper/1906.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05474"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}}}},{"paper":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/transfer-learning-in-biomedical-natural","slug":"transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","arxiv_id":"1906.05474","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ncbi-nlp/BLUE_Benchmark","ncbi-nlp/NCBI_BERT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transfer-learning-in-biomedical-natural#ran","syntology_url":"https://syntology.ai/paper/1906.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05474"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/hoc-1/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/hoc-1/papers/ran/1","json":"/dataset/hoc-1/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":3,"samples_harvested":21,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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":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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"2bbbc484dabcf2e91b063810062ee7d6d0935fca8b37d308375dc8cb8443e171","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}