{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BUEPMYLWNTHAXMFFUOGZ2R6H5H","short_pith_number":"pith:BUEPMYLW","schema_version":"1.0","canonical_sha256":"0d08f661766cce0bb0a5a38d9d47c7e9e4b8bcfe122d5c533ac975bd9e08d1db","source":{"kind":"arxiv","id":"2311.05042","version":1},"attestation_state":"computed","paper":{"title":"Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"primary_cat":"cs.IR","authors_text":"Anna Giannakou, Christopher J. Mungall, Dan Gunter, Harshad Hegde, Kjiersten Fagnan, Lavanya Ramakrishnan, Neil P. Byers, Oluwamayowa O. Amusat","submitted_at":"2023-11-08T22:09:31Z","abstract_excerpt":"Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lacks the essential metadata required for researchers to find and search them effectively. The lack of metadata poses a significant challenge in the utilization of these datasets. Machine learning-based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific datasets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata"},"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":"2311.05042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-11-08T22:09:31Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"title_canon_sha256":"9dac511e2ec91baf2d8517fab6b5540562b07acee1df4d6a499f0e7c5c0fee9c","abstract_canon_sha256":"95d1dddb0fa1d6404edf1fd9c044a41b149aa47d42e5f0f06327ad24c31fa805"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:56.852749Z","signature_b64":"ac3/JTcUR56YXgOYtuELvY15eiUCHclqgYbbPPgrmna9t39akdzkYs5vBMCArQm7OxFsdde9V1/4SXkg9H2SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d08f661766cce0bb0a5a38d9d47c7e9e4b8bcfe122d5c533ac975bd9e08d1db","last_reissued_at":"2026-07-05T09:12:56.852242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:56.852242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"primary_cat":"cs.IR","authors_text":"Anna Giannakou, Christopher J. Mungall, Dan Gunter, Harshad Hegde, Kjiersten Fagnan, Lavanya Ramakrishnan, Neil P. Byers, Oluwamayowa O. Amusat","submitted_at":"2023-11-08T22:09:31Z","abstract_excerpt":"Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lacks the essential metadata required for researchers to find and search them effectively. The lack of metadata poses a significant challenge in the utilization of these datasets. Machine learning-based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific datasets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05042","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/2311.05042/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":"2311.05042","created_at":"2026-07-05T09:12:56.852304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05042v1","created_at":"2026-07-05T09:12:56.852304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05042","created_at":"2026-07-05T09:12:56.852304+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUEPMYLWNTHA","created_at":"2026-07-05T09:12:56.852304+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUEPMYLWNTHAXMFF","created_at":"2026-07-05T09:12:56.852304+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUEPMYLW","created_at":"2026-07-05T09:12:56.852304+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/BUEPMYLWNTHAXMFFUOGZ2R6H5H","json":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H.json","graph_json":"https://pith.science/api/pith-number/BUEPMYLWNTHAXMFFUOGZ2R6H5H/graph.json","events_json":"https://pith.science/api/pith-number/BUEPMYLWNTHAXMFFUOGZ2R6H5H/events.json","paper":"https://pith.science/paper/BUEPMYLW"},"agent_actions":{"view_html":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H","download_json":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H.json","view_paper":"https://pith.science/paper/BUEPMYLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05042&json=true","fetch_graph":"https://pith.science/api/pith-number/BUEPMYLWNTHAXMFFUOGZ2R6H5H/graph.json","fetch_events":"https://pith.science/api/pith-number/BUEPMYLWNTHAXMFFUOGZ2R6H5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H/action/storage_attestation","attest_author":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H/action/author_attestation","sign_citation":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H/action/citation_signature","submit_replication":"https://pith.science/pith/BUEPMYLWNTHAXMFFUOGZ2R6H5H/action/replication_record"}},"created_at":"2026-07-05T09:12:56.852304+00:00","updated_at":"2026-07-05T09:12:56.852304+00:00"}