{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LJT4ECTKRKLQN5IVITDVRMSCLX","short_pith_number":"pith:LJT4ECTK","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"},"canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","source":{"kind":"arxiv","id":"1704.06360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06360","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06360v1","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06360","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"LJT4ECTKRKLQ","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LJT4ECTKRKLQN5IV","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LJT4ECTK","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LJT4ECTKRKLQN5IVITDVRMSCLX","target":"record","payload":{"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"},"canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","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"},"source_kind":"arxiv","source_id":"1704.06360","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VutGBMyVdl4diL+CWeQL1XOSYtJi+zgxCmYd+npHWKxjR4n+k/Me+yWR6DiClpeOEJljDLwYt2g5BNdufVfCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:34:20.080529Z"},"content_sha256":"9ba0e96a67703b12bc57d79821b543ed92af505602ac7557a783a178e16528af","schema_version":"1.0","event_id":"sha256:9ba0e96a67703b12bc57d79821b543ed92af505602ac7557a783a178e16528af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LJT4ECTKRKLQN5IVITDVRMSCLX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqm3nK5aOdetIYSuofXtOnA2+xpnezLh2cjtACzalyMFJGsVhi6wBgqeAT6iEtU42RiCVw7IVr73pOtb0TZPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:34:20.080998Z"},"content_sha256":"37a008b11ed579066509ae3a6baeecafb3d2bb1330561b1af9d6a3fa0d25119f","schema_version":"1.0","event_id":"sha256:37a008b11ed579066509ae3a6baeecafb3d2bb1330561b1af9d6a3fa0d25119f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/bundle.json","state_url":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T06:34:20Z","links":{"resolver":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX","bundle":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/bundle.json","state":"https://pith.science/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJT4ECTKRKLQN5IVITDVRMSCLX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LJT4ECTKRKLQN5IVITDVRMSCLX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bc75f7e42770b8c2635af5d5e2e5e3c8e8526381160222ef8020b3165f58e53d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-20T23:02:14Z","title_canon_sha256":"c1af7f291f07c7ebc0a767910f60926e4dc027f676ac9f9257cb25e0efd90688"},"schema_version":"1.0","source":{"id":"1704.06360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06360","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06360v1","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06360","created_at":"2026-05-18T00:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"LJT4ECTKRKLQ","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LJT4ECTKRKLQN5IV","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LJT4ECTK","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:37a008b11ed579066509ae3a6baeecafb3d2bb1330561b1af9d6a3fa0d25119f","target":"graph","created_at":"2026-05-18T00:45:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Alex Ratner, Christopher R\\'e, Jason Fries, Sen Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-20T23:02:14Z","title":"SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06360","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9ba0e96a67703b12bc57d79821b543ed92af505602ac7557a783a178e16528af","target":"record","created_at":"2026-05-18T00:45:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bc75f7e42770b8c2635af5d5e2e5e3c8e8526381160222ef8020b3165f58e53d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-20T23:02:14Z","title_canon_sha256":"c1af7f291f07c7ebc0a767910f60926e4dc027f676ac9f9257cb25e0efd90688"},"schema_version":"1.0","source":{"id":"1704.06360","kind":"arxiv","version":1}},"canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a67c20a6a8a9706f51544c758b2425dd83f43576e74038181d8e0c172ff41cd","first_computed_at":"2026-05-18T00:45:59.908423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:59.908423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sVgB+LvrsWic3bEXprI1aY+rUo40u5YZqe2SJsthvQF/X2NPyWYpQySwPw6sRC53Dt2QO1J6OnRfKY647wWNBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:59.908839Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ba0e96a67703b12bc57d79821b543ed92af505602ac7557a783a178e16528af","sha256:37a008b11ed579066509ae3a6baeecafb3d2bb1330561b1af9d6a3fa0d25119f"],"state_sha256":"2bd25e552b3f4a3942b0c033cd8453ff5c21f4411f2e35162ae7adeead5cd044"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rotKYpKvu3P8phXn40fm+wa31bnVRtXXWm+DT0SSPamh3NfID7H7SGs/Xmguv0L4B+mB14v4uwaRTLmJIBSiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:34:20.084851Z","bundle_sha256":"2fefb679e70462f76ecd47e5ac567b29631dcf46c0070ca32e2cd44ef85e3b76"}}