{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LJT4ECTKRKLQN5IVITDVRMSCLX","short_pith_number":"pith:LJT4ECTK","schema_version":"1.0","canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","source":{"kind":"arxiv","id":"1704.06360","version":1},"attestation_state":"computed","paper":{"title":"SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Ratner, Christopher R\\'e, Jason Fries, Sen Wu","submitted_at":"2017-04-20T23:02:14Z","abstract_excerpt":"We present SwellShark, a framework for building biomedical named entity recognition (NER) systems quickly and without hand-labeled data. Our approach views biomedical resources like lexicons as function primitives for autogenerating weak supervision. We then use a generative model to unify and denoise this supervision and construct large-scale, probabilistically labeled datasets for training high-accuracy NER taggers. In three biomedical NER tasks, SwellShark achieves competitive scores with state-of-the-art supervised benchmarks using no hand-labeled training data. In a drug name extraction t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1704.06360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-20T23:02:14Z","cross_cats_sorted":[],"title_canon_sha256":"c1af7f291f07c7ebc0a767910f60926e4dc027f676ac9f9257cb25e0efd90688","abstract_canon_sha256":"bc75f7e42770b8c2635af5d5e2e5e3c8e8526381160222ef8020b3165f58e53d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:59.908839Z","signature_b64":"sVgB+LvrsWic3bEXprI1aY+rUo40u5YZqe2SJsthvQF/X2NPyWYpQySwPw6sRC53Dt2QO1J6OnRfKY647wWNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","last_reissued_at":"2026-05-18T00:45:59.908423Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:59.908423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Ratner, Christopher R\\'e, Jason Fries, Sen Wu","submitted_at":"2017-04-20T23:02:14Z","abstract_excerpt":"We present SwellShark, a framework for building biomedical named entity recognition (NER) systems quickly and without hand-labeled data. Our approach views biomedical resources like lexicons as function primitives for autogenerating weak supervision. We then use a generative model to unify and denoise this supervision and construct large-scale, probabilistically labeled datasets for training high-accuracy NER taggers. In three biomedical NER tasks, SwellShark achieves competitive scores with state-of-the-art supervised benchmarks using no hand-labeled training data. In a drug name extraction t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06360","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1704.06360","created_at":"2026-05-18T00:45:59.908487+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06360v1","created_at":"2026-05-18T00:45:59.908487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06360","created_at":"2026-05-18T00:45:59.908487+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJT4ECTKRKLQ","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJT4ECTKRKLQN5IV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJT4ECTK","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00164","citing_title":"Named Entity Recognition Only from Word Embeddings","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX","json":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX.json","graph_json":"https://pith.science/api/pith-number/LJT4ECTKRKLQN5IVITDVRMSCLX/graph.json","events_json":"https://pith.science/api/pith-number/LJT4ECTKRKLQN5IVITDVRMSCLX/events.json","paper":"https://pith.science/paper/LJT4ECTK"},"agent_actions":{"view_html":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX","download_json":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX.json","view_paper":"https://pith.science/paper/LJT4ECTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06360&json=true","fetch_graph":"https://pith.science/api/pith-number/LJT4ECTKRKLQN5IVITDVRMSCLX/graph.json","fetch_events":"https://pith.science/api/pith-number/LJT4ECTKRKLQN5IVITDVRMSCLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/action/storage_attestation","attest_author":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/action/author_attestation","sign_citation":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/action/citation_signature","submit_replication":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/action/replication_record"}},"created_at":"2026-05-18T00:45:59.908487+00:00","updated_at":"2026-05-18T00:45:59.908487+00:00"}