{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4CBHPWMYLKXKS3SOSSRMYWGPTS","short_pith_number":"pith:4CBHPWMY","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"},"canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","source":{"kind":"arxiv","id":"2501.05082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05082","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05082v1","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05082","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_12","alias_value":"4CBHPWMYLKXK","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_16","alias_value":"4CBHPWMYLKXKS3SO","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_8","alias_value":"4CBHPWMY","created_at":"2026-07-05T09:59:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4CBHPWMYLKXKS3SOSSRMYWGPTS","target":"record","payload":{"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"},"canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","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"},"source_kind":"arxiv","source_id":"2501.05082","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5isAO+Ho2mUGm1oO4canO9dxjvro7oHniPuhFMykR97mx8SxLYmErViiZs1y6J/hD4d4HOvN681E+ddlqaMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:34:58.700421Z"},"content_sha256":"491e7746b385d588bf5518ca79956a23defe222e38a9f38c81d223bccd97dcbf","schema_version":"1.0","event_id":"sha256:491e7746b385d588bf5518ca79956a23defe222e38a9f38c81d223bccd97dcbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4CBHPWMYLKXKS3SOSSRMYWGPTS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+Ys12dyCPl7Gk1UuAzfuMzIsDjcvDId/XzjyICJCtjFvng3DLo1xU8iqLdY5lTy4bmDX97EniwXH0YOUru+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:34:58.700949Z"},"content_sha256":"ea8a4e769b29bbe5334cd19205b305b61abc08fa8536132531a0a24b6ab6816b","schema_version":"1.0","event_id":"sha256:ea8a4e769b29bbe5334cd19205b305b61abc08fa8536132531a0a24b6ab6816b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/bundle.json","state_url":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T02:34:58Z","links":{"resolver":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS","bundle":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/bundle.json","state":"https://pith.science/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CBHPWMYLKXKS3SOSSRMYWGPTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4CBHPWMYLKXKS3SOSSRMYWGPTS","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":"0e52c309909ac8e3ae2611e9d075d2dcbcde4bd1910c738db79a0af8e599c84b","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-09T09:03:43Z","title_canon_sha256":"25db5009af866f66ebfa1018490e33201d14cb580edc673e827629c1963675d4"},"schema_version":"1.0","source":{"id":"2501.05082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05082","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05082v1","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05082","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_12","alias_value":"4CBHPWMYLKXK","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_16","alias_value":"4CBHPWMYLKXKS3SO","created_at":"2026-07-05T09:59:04Z"},{"alias_kind":"pith_short_8","alias_value":"4CBHPWMY","created_at":"2026-07-05T09:59:04Z"}],"graph_snapshots":[{"event_id":"sha256:ea8a4e769b29bbe5334cd19205b305b61abc08fa8536132531a0a24b6ab6816b","target":"graph","created_at":"2026-07-05T09:59:04Z","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/2501.05082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Cong Yang, Zeyd Boukhers","cross_cats":["cs.CL","cs.DL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-09T09:03:43Z","title":"Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05082","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":"sha256:491e7746b385d588bf5518ca79956a23defe222e38a9f38c81d223bccd97dcbf","target":"record","created_at":"2026-07-05T09:59:04Z","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":"0e52c309909ac8e3ae2611e9d075d2dcbcde4bd1910c738db79a0af8e599c84b","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-09T09:03:43Z","title_canon_sha256":"25db5009af866f66ebfa1018490e33201d14cb580edc673e827629c1963675d4"},"schema_version":"1.0","source":{"id":"2501.05082","kind":"arxiv","version":1}},"canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e08277d9985aaea96e4e94a2cc58cf9cbff1917ea31f30ea9561cf18eb250699","first_computed_at":"2026-07-05T09:59:04.113473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:04.113473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejx+YgTWfmqhNx7prRF6YoV7zpj63ay+JaQgIZ9IkqQxhq8GrigBT7xbo2PkApxjuJL7p7fvzasYOnVJwFAUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:04.113818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:491e7746b385d588bf5518ca79956a23defe222e38a9f38c81d223bccd97dcbf","sha256:ea8a4e769b29bbe5334cd19205b305b61abc08fa8536132531a0a24b6ab6816b"],"state_sha256":"99a927e3b215af38939ac9a5173848ec1393342f37b005f14bd28c60724b5d9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jk7owN+Y+946vkCSQkdwuwQbVhEE0I5XwijGyf7nltYMGKMgITn2zopE1/sQNnTEkYRqJqmjwW2w1a39KDm5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:34:58.705152Z","bundle_sha256":"3e61ec148563d8aa81703b27f944fa7541d67437915e02b279aba7ad7ed34d54"}}