{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4CBHPWMYLKXKS3SOSSRMYWGPTS","short_pith_number":"pith:4CBHPWMY","schema_version":"1.0","canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","source":{"kind":"arxiv","id":"2501.05082","version":1},"attestation_state":"computed","paper":{"title":"Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Cong Yang, Zeyd Boukhers","submitted_at":"2025-01-09T09:03:43Z","abstract_excerpt":"The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility, Interoperability, and Reusability) of research findings. However, the lack of sufficient metadata in published documents, particularly those from smaller and mid-sized publishers, hinders their accessibility. This issue is widespread in some disciplines, such as the German Social Sciences, where publications often employ diverse templates. To address this challenge, our study evaluates various feature learning and "},"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":"2501.05082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-09T09:03:43Z","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"title_canon_sha256":"25db5009af866f66ebfa1018490e33201d14cb580edc673e827629c1963675d4","abstract_canon_sha256":"0e52c309909ac8e3ae2611e9d075d2dcbcde4bd1910c738db79a0af8e599c84b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:04.113818Z","signature_b64":"ejx+YgTWfmqhNx7prRF6YoV7zpj63ay+JaQgIZ9IkqQxhq8GrigBT7xbo2PkApxjuJL7p7fvzasYOnVJwFAUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","last_reissued_at":"2026-07-05T09:59:04.113473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:04.113473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Cong Yang, Zeyd Boukhers","submitted_at":"2025-01-09T09:03:43Z","abstract_excerpt":"The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility, Interoperability, and Reusability) of research findings. However, the lack of sufficient metadata in published documents, particularly those from smaller and mid-sized publishers, hinders their accessibility. This issue is widespread in some disciplines, such as the German Social Sciences, where publications often employ diverse templates. To address this challenge, our study evaluates various feature learning and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05082","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/2501.05082/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":"2501.05082","created_at":"2026-07-05T09:59:04.113528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05082v1","created_at":"2026-07-05T09:59:04.113528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05082","created_at":"2026-07-05T09:59:04.113528+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CBHPWMYLKXK","created_at":"2026-07-05T09:59:04.113528+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CBHPWMYLKXKS3SO","created_at":"2026-07-05T09:59:04.113528+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CBHPWMY","created_at":"2026-07-05T09:59:04.113528+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/4CBHPWMYLKXKS3SOSSRMYWGPTS","json":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS.json","graph_json":"https://pith.science/api/pith-number/4CBHPWMYLKXKS3SOSSRMYWGPTS/graph.json","events_json":"https://pith.science/api/pith-number/4CBHPWMYLKXKS3SOSSRMYWGPTS/events.json","paper":"https://pith.science/paper/4CBHPWMY"},"agent_actions":{"view_html":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS","download_json":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS.json","view_paper":"https://pith.science/paper/4CBHPWMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05082&json=true","fetch_graph":"https://pith.science/api/pith-number/4CBHPWMYLKXKS3SOSSRMYWGPTS/graph.json","fetch_events":"https://pith.science/api/pith-number/4CBHPWMYLKXKS3SOSSRMYWGPTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/action/storage_attestation","attest_author":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/action/author_attestation","sign_citation":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/action/citation_signature","submit_replication":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/action/replication_record"}},"created_at":"2026-07-05T09:59:04.113528+00:00","updated_at":"2026-07-05T09:59:04.113528+00:00"}