{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2008:LGHRYD3FHFNQL6XRGJKYRDB5P7","short_pith_number":"pith:LGHRYD3F","schema_version":"1.0","canonical_sha256":"598f1c0f65395b05faf13255888c3d7fdceb94842e719e71d8903eda3231ee87","source":{"kind":"arxiv","id":"0804.0317","version":1},"attestation_state":"computed","paper":{"title":"Parts-of-Speech Tagger Errors Do Not Necessarily Degrade Accuracy in Extracting Information from Biomedical Text","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Christophe Lefevre, Kevin R. Nicholas, Maurice HT Ling","submitted_at":"2008-04-02T09:34:13Z","abstract_excerpt":"A recent study reported development of Muscorian, a generic text processing tool for extracting protein-protein interactions from text that achieved comparable performance to biomedical-specific text processing tools. This result was unexpected since potential errors from a series of text analysis processes is likely to adversely affect the outcome of the entire process. Most biomedical entity relationship extraction tools have used biomedical-specific parts-of-speech (POS) tagger as errors in POS tagging and are likely to affect subsequent semantic analysis of the text, such as shallow parsin"},"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":"0804.0317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2008-04-02T09:34:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"db71bd8b1a3b7918ac06d1aea389baa9522b90e875f719bc6006966f59596df3","abstract_canon_sha256":"d0b192461b7e911865a1f910f745e491f41d52803f5398335ebd91d2258d8ab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:10:34.797962Z","signature_b64":"AgBttbs0bSCJBtc/fvEiWCbzY+C435fV/Mc/mrs9X7cbl+OzGQSjRHh/3E4vI11hf4/fLM576PWkYoxiknYLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"598f1c0f65395b05faf13255888c3d7fdceb94842e719e71d8903eda3231ee87","last_reissued_at":"2026-07-04T15:10:34.797564Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:10:34.797564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parts-of-Speech Tagger Errors Do Not Necessarily Degrade Accuracy in Extracting Information from Biomedical Text","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Christophe Lefevre, Kevin R. Nicholas, Maurice HT Ling","submitted_at":"2008-04-02T09:34:13Z","abstract_excerpt":"A recent study reported development of Muscorian, a generic text processing tool for extracting protein-protein interactions from text that achieved comparable performance to biomedical-specific text processing tools. This result was unexpected since potential errors from a series of text analysis processes is likely to adversely affect the outcome of the entire process. Most biomedical entity relationship extraction tools have used biomedical-specific parts-of-speech (POS) tagger as errors in POS tagging and are likely to affect subsequent semantic analysis of the text, such as shallow parsin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0804.0317","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/0804.0317/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"0804.0317","created_at":"2026-07-04T15:10:34.797626+00:00"},{"alias_kind":"arxiv_version","alias_value":"0804.0317v1","created_at":"2026-07-04T15:10:34.797626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0804.0317","created_at":"2026-07-04T15:10:34.797626+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGHRYD3FHFNQ","created_at":"2026-07-04T15:10:34.797626+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGHRYD3FHFNQL6XR","created_at":"2026-07-04T15:10:34.797626+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGHRYD3F","created_at":"2026-07-04T15:10:34.797626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7","json":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7.json","graph_json":"https://pith.science/api/pith-number/LGHRYD3FHFNQL6XRGJKYRDB5P7/graph.json","events_json":"https://pith.science/api/pith-number/LGHRYD3FHFNQL6XRGJKYRDB5P7/events.json","paper":"https://pith.science/paper/LGHRYD3F"},"agent_actions":{"view_html":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7","download_json":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7.json","view_paper":"https://pith.science/paper/LGHRYD3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0804.0317&json=true","fetch_graph":"https://pith.science/api/pith-number/LGHRYD3FHFNQL6XRGJKYRDB5P7/graph.json","fetch_events":"https://pith.science/api/pith-number/LGHRYD3FHFNQL6XRGJKYRDB5P7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7/action/storage_attestation","attest_author":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7/action/author_attestation","sign_citation":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7/action/citation_signature","submit_replication":"https://pith.science/pith/LGHRYD3FHFNQL6XRGJKYRDB5P7/action/replication_record"}},"created_at":"2026-07-04T15:10:34.797626+00:00","updated_at":"2026-07-04T15:10:34.797626+00:00"}