{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:FIAJULG5ERXG753OWBK4LMM5B6","short_pith_number":"pith:FIAJULG5","canonical_record":{"source":{"id":"1502.05472","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:04:40Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"aa37c8bc02b4b2febf61a241bfde9bcbdfaa5f18e60ce43e9889243770a9430e","abstract_canon_sha256":"7d218166653ad24c95cfafcda6b4d64010e8e42c2056f8e031760b97240f86bd"},"schema_version":"1.0"},"canonical_sha256":"2a009a2cdd246e6ff76eb055c5b19d0fb078468ec8d0368477f2ab4f9e1072cf","source":{"kind":"arxiv","id":"1502.05472","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05472","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05472v2","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05472","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"FIAJULG5ERXG","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"FIAJULG5ERXG753O","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"FIAJULG5","created_at":"2026-07-05T03:15:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:FIAJULG5ERXG753OWBK4LMM5B6","target":"record","payload":{"canonical_record":{"source":{"id":"1502.05472","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:04:40Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"aa37c8bc02b4b2febf61a241bfde9bcbdfaa5f18e60ce43e9889243770a9430e","abstract_canon_sha256":"7d218166653ad24c95cfafcda6b4d64010e8e42c2056f8e031760b97240f86bd"},"schema_version":"1.0"},"canonical_sha256":"2a009a2cdd246e6ff76eb055c5b19d0fb078468ec8d0368477f2ab4f9e1072cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:24.342093Z","signature_b64":"YdlyJ9XfZgwQ2bTTujyJS8FBCR68MDNXA0G2IhgalZm82omOn6hF3+vRD8iI6rPX2f5N4LEl7XG0zaOM7zWTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a009a2cdd246e6ff76eb055c5b19d0fb078468ec8d0368477f2ab4f9e1072cf","last_reissued_at":"2026-07-05T03:15:24.341635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:24.341635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.05472","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d87cw8keFaruud69/qW38aXAfRRqM/iKfxYeCWTIRws2aw5Mm4aCYYZ4J8xe0dDvyvy19pCUa7Fz6MrEQwauAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:20:12.345291Z"},"content_sha256":"4fc8b4639f55147a5c1f83cdea578eb92cd5bd05f50c503801f4a3884f0d7caf","schema_version":"1.0","event_id":"sha256:4fc8b4639f55147a5c1f83cdea578eb92cd5bd05f50c503801f4a3884f0d7caf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:FIAJULG5ERXG753OWBK4LMM5B6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Diego Marcheggiani, Fabrizio Sebastiani","submitted_at":"2015-02-19T06:04:40Z","abstract_excerpt":"In the last five years there has been a flurry of work on information extraction from clinical documents, i.e., on algorithms capable of extracting, from the informal and unstructured texts that are generated during everyday clinical practice, mentions of concepts relevant to such practice. Most of this literature is about methods based on supervised learning, i.e., methods for training an information extraction system from manually annotated examples. While a lot of work has been devoted to devising learning methods that generate more and more accurate information extractors, no work has been"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05472","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1502.05472/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+WfMhdnx5/Kt+OR753nOWPMwlsAg29RIENyBr2qbdgqgV46JuiHEFwAqON+Lf/cknRHQWnm/majmSxLu1ILBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:20:12.345793Z"},"content_sha256":"4e114b5a02bb4c6d584a7b016d5f947467088bbb37fbbe489ed96a7f906587e6","schema_version":"1.0","event_id":"sha256:4e114b5a02bb4c6d584a7b016d5f947467088bbb37fbbe489ed96a7f906587e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIAJULG5ERXG753OWBK4LMM5B6/bundle.json","state_url":"https://pith.science/pith/FIAJULG5ERXG753OWBK4LMM5B6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIAJULG5ERXG753OWBK4LMM5B6/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":"2026-07-31T18:20:12Z","links":{"resolver":"https://pith.science/pith/FIAJULG5ERXG753OWBK4LMM5B6","bundle":"https://pith.science/pith/FIAJULG5ERXG753OWBK4LMM5B6/bundle.json","state":"https://pith.science/pith/FIAJULG5ERXG753OWBK4LMM5B6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIAJULG5ERXG753OWBK4LMM5B6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:FIAJULG5ERXG753OWBK4LMM5B6","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":"7d218166653ad24c95cfafcda6b4d64010e8e42c2056f8e031760b97240f86bd","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:04:40Z","title_canon_sha256":"aa37c8bc02b4b2febf61a241bfde9bcbdfaa5f18e60ce43e9889243770a9430e"},"schema_version":"1.0","source":{"id":"1502.05472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05472","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05472v2","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05472","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"FIAJULG5ERXG","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"FIAJULG5ERXG753O","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"FIAJULG5","created_at":"2026-07-05T03:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:4e114b5a02bb4c6d584a7b016d5f947467088bbb37fbbe489ed96a7f906587e6","target":"graph","created_at":"2026-07-05T03:15:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1502.05472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the last five years there has been a flurry of work on information extraction from clinical documents, i.e., on algorithms capable of extracting, from the informal and unstructured texts that are generated during everyday clinical practice, mentions of concepts relevant to such practice. Most of this literature is about methods based on supervised learning, i.e., methods for training an information extraction system from manually annotated examples. While a lot of work has been devoted to devising learning methods that generate more and more accurate information extractors, no work has been","authors_text":"Diego Marcheggiani, Fabrizio Sebastiani","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:04:40Z","title":"On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05472","kind":"arxiv","version":2},"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":"sha256:4fc8b4639f55147a5c1f83cdea578eb92cd5bd05f50c503801f4a3884f0d7caf","target":"record","created_at":"2026-07-05T03:15:24Z","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":"7d218166653ad24c95cfafcda6b4d64010e8e42c2056f8e031760b97240f86bd","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:04:40Z","title_canon_sha256":"aa37c8bc02b4b2febf61a241bfde9bcbdfaa5f18e60ce43e9889243770a9430e"},"schema_version":"1.0","source":{"id":"1502.05472","kind":"arxiv","version":2}},"canonical_sha256":"2a009a2cdd246e6ff76eb055c5b19d0fb078468ec8d0368477f2ab4f9e1072cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a009a2cdd246e6ff76eb055c5b19d0fb078468ec8d0368477f2ab4f9e1072cf","first_computed_at":"2026-07-05T03:15:24.341635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:24.341635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YdlyJ9XfZgwQ2bTTujyJS8FBCR68MDNXA0G2IhgalZm82omOn6hF3+vRD8iI6rPX2f5N4LEl7XG0zaOM7zWTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:24.342093Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.05472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fc8b4639f55147a5c1f83cdea578eb92cd5bd05f50c503801f4a3884f0d7caf","sha256:4e114b5a02bb4c6d584a7b016d5f947467088bbb37fbbe489ed96a7f906587e6"],"state_sha256":"1171b467028492e2d064d81c0444d030f0ac4d4ae6b3d6069665d71d7a15622d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/fn9KuNDs2bZfo1aYWDBVQ/pgOGraWSC4qOCNujh8gdyaI9lJCmc54q23ZSyN7dyZQMfJNEKhgejlMDdYjrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T18:20:12.351948Z","bundle_sha256":"d8b460bbbdd2f70f232c344107ae2bcc08da6a34e19aa00503b0d783dd6f6eef"}}