{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","short_pith_number":"pith:3ZCMYJ2H","schema_version":"1.0","canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","source":{"kind":"arxiv","id":"1811.01183","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Christopher G. Stahl, Drahomira Herrmannova, Mary S. Wolfe, Nicole C. Kleinstreuer, Robert M. Patton, Steven R. Young","submitted_at":"2018-11-03T09:29:36Z","abstract_excerpt":"Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better "},"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":"1811.01183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"cf09ad5a542384f79a938f17dd4ee05ded337b34b0a567bd5e9f6b33bba87daa","abstract_canon_sha256":"1c99a53406d9366608d34dd3a1119d4fda4cd5ed920910dbfa18113fda78c45a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:35.112604Z","signature_b64":"NdwU51M4OObfUPAfOYvxUByyyzKeyAt+I/Y/n1t/3I4ixlRNNwMagGHX+ibbHETexeSA6g3pyJrTkrEegYB/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","last_reissued_at":"2026-05-18T00:01:35.112085Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:35.112085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Christopher G. Stahl, Drahomira Herrmannova, Mary S. Wolfe, Nicole C. Kleinstreuer, Robert M. Patton, Steven R. Young","submitted_at":"2018-11-03T09:29:36Z","abstract_excerpt":"Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01183","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":"1811.01183","created_at":"2026-05-18T00:01:35.112163+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01183v1","created_at":"2026-05-18T00:01:35.112163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01183","created_at":"2026-05-18T00:01:35.112163+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZCMYJ2HBMFW","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZCMYJ2HBMFWH7ZW","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZCMYJ2H","created_at":"2026-05-18T12:32:05.422762+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/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","json":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT.json","graph_json":"https://pith.science/api/pith-number/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/graph.json","events_json":"https://pith.science/api/pith-number/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/events.json","paper":"https://pith.science/paper/3ZCMYJ2H"},"agent_actions":{"view_html":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","download_json":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT.json","view_paper":"https://pith.science/paper/3ZCMYJ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01183&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/action/storage_attestation","attest_author":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/action/author_attestation","sign_citation":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/action/citation_signature","submit_replication":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/action/replication_record"}},"created_at":"2026-05-18T00:01:35.112163+00:00","updated_at":"2026-05-18T00:01:35.112163+00:00"}