{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BUEPMYLWNTHAXMFFUOGZ2R6H5H","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":"95d1dddb0fa1d6404edf1fd9c044a41b149aa47d42e5f0f06327ad24c31fa805","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-11-08T22:09:31Z","title_canon_sha256":"9dac511e2ec91baf2d8517fab6b5540562b07acee1df4d6a499f0e7c5c0fee9c"},"schema_version":"1.0","source":{"id":"2311.05042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05042","created_at":"2026-07-05T09:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05042v1","created_at":"2026-07-05T09:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05042","created_at":"2026-07-05T09:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"BUEPMYLWNTHA","created_at":"2026-07-05T09:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"BUEPMYLWNTHAXMFF","created_at":"2026-07-05T09:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"BUEPMYLW","created_at":"2026-07-05T09:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:56074892636629277f32af99da9595b32805bd97b14f970f34ee072f0719105b","target":"graph","created_at":"2026-07-05T09:12:56Z","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/2311.05042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anna Giannakou, Christopher J. Mungall, Dan Gunter, Harshad Hegde, Kjiersten Fagnan, Lavanya Ramakrishnan, Neil P. Byers, Oluwamayowa O. Amusat","cross_cats":["cs.AI","cs.LG","q-bio.GN"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-11-08T22:09:31Z","title":"Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05042","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":"sha256:68da5900a91884110afec16cf3ee1ca5e492762a5179da7de659cee175b02c63","target":"record","created_at":"2026-07-05T09:12:56Z","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":"95d1dddb0fa1d6404edf1fd9c044a41b149aa47d42e5f0f06327ad24c31fa805","cross_cats_sorted":["cs.AI","cs.LG","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-11-08T22:09:31Z","title_canon_sha256":"9dac511e2ec91baf2d8517fab6b5540562b07acee1df4d6a499f0e7c5c0fee9c"},"schema_version":"1.0","source":{"id":"2311.05042","kind":"arxiv","version":1}},"canonical_sha256":"0d08f661766cce0bb0a5a38d9d47c7e9e4b8bcfe122d5c533ac975bd9e08d1db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d08f661766cce0bb0a5a38d9d47c7e9e4b8bcfe122d5c533ac975bd9e08d1db","first_computed_at":"2026-07-05T09:12:56.852242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:56.852242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ac3/JTcUR56YXgOYtuELvY15eiUCHclqgYbbPPgrmna9t39akdzkYs5vBMCArQm7OxFsdde9V1/4SXkg9H2SCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:56.852749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68da5900a91884110afec16cf3ee1ca5e492762a5179da7de659cee175b02c63","sha256:56074892636629277f32af99da9595b32805bd97b14f970f34ee072f0719105b"],"state_sha256":"34b0a099db457327f64da02e9ac1a91a12b4271d9d34e307e44874112b5d5a98"}