{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:63BVLHCD6J25ADKYGTBKPALHDM","short_pith_number":"pith:63BVLHCD","canonical_record":{"source":{"id":"2410.09871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-13T15:11:31Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"8df3428527f52a5549c1e27e595fa88c6b058f9036f66b917d86658fcaf0b2f6","abstract_canon_sha256":"abc6838b8854b27abb4bc1cdcdc5687f51c5f37eb5b385256f789f483aac42e2"},"schema_version":"1.0"},"canonical_sha256":"f6c3559c43f275d00d5834c2a781671b24911bc7823407dcb4b6d790cbe4dbcd","source":{"kind":"arxiv","id":"2410.09871","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09871","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09871v2","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09871","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"63BVLHCD6J25","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"63BVLHCD6J25ADKY","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"63BVLHCD","created_at":"2026-07-05T10:43:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:63BVLHCD6J25ADKYGTBKPALHDM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-13T15:11:31Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"8df3428527f52a5549c1e27e595fa88c6b058f9036f66b917d86658fcaf0b2f6","abstract_canon_sha256":"abc6838b8854b27abb4bc1cdcdc5687f51c5f37eb5b385256f789f483aac42e2"},"schema_version":"1.0"},"canonical_sha256":"f6c3559c43f275d00d5834c2a781671b24911bc7823407dcb4b6d790cbe4dbcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:40.140891Z","signature_b64":"+APUzZ3kAZNTe0XRSor7nUWEGRNKJSNWJ/69pRblCJeqOLsSA6+DUvL0VLXEU4ojHLuX0QRbulbgIaMGmgehBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6c3559c43f275d00d5834c2a781671b24911bc7823407dcb4b6d790cbe4dbcd","last_reissued_at":"2026-07-05T10:43:40.140431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:40.140431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09871","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMPlkq7GiTU9il8ZRK2rPjmEL8UYjyWnAU9W/XJCAk20VzcGTpaN+JKlD6CGHZxXL6JQHuDva9+KPHntLqQMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:00:26.799086Z"},"content_sha256":"49d69406bd069a70c587ccb807b43fa9e734808367e021eefe148af965e4b447","schema_version":"1.0","event_id":"sha256:49d69406bd069a70c587ccb807b43fa9e734808367e021eefe148af965e4b447"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:63BVLHCD6J25ADKYGTBKPALHDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of PDF Parsing Tools Across Diverse Document Categories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.IR","authors_text":"Narayan S. Adhikari, Shradha Agarwal","submitted_at":"2024-10-13T15:11:31Z","abstract_excerpt":"PDF is one of the most prominent data formats, making PDF parsing crucial for information extraction and retrieval, particularly with the rise of RAG systems. While various PDF parsing tools exist, their effectiveness across different document types remains understudied, especially beyond academic papers. Our research aims to address this gap by comparing 10 popular PDF parsing tools across 6 document categories using the DocLayNet dataset. These tools include PyPDF, pdfminer-six, PyMuPDF, pdfplumber, pypdfium2, Unstructured, Tabula, Camelot, as well as the deep learning-based tools Nougat and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09871","kind":"arxiv","version":2},"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/2410.09871/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":"2026-07-05T10:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9B6KyHNIr9Uc3b6PWKJ4Fgvhs3H0nik++s1hoXTnH7fwDxbXMXvRgVj9AsyPMixaRHItdAiKbfwMaWqLaZNlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:00:26.799634Z"},"content_sha256":"75ff8e72bd8fce81f6b3b0d4e26f9e9f4cff69ac56c73bc290c9da48c20b2bac","schema_version":"1.0","event_id":"sha256:75ff8e72bd8fce81f6b3b0d4e26f9e9f4cff69ac56c73bc290c9da48c20b2bac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63BVLHCD6J25ADKYGTBKPALHDM/bundle.json","state_url":"https://pith.science/pith/63BVLHCD6J25ADKYGTBKPALHDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63BVLHCD6J25ADKYGTBKPALHDM/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":"2026-08-21T13:00:26Z","links":{"resolver":"https://pith.science/pith/63BVLHCD6J25ADKYGTBKPALHDM","bundle":"https://pith.science/pith/63BVLHCD6J25ADKYGTBKPALHDM/bundle.json","state":"https://pith.science/pith/63BVLHCD6J25ADKYGTBKPALHDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63BVLHCD6J25ADKYGTBKPALHDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:63BVLHCD6J25ADKYGTBKPALHDM","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":"abc6838b8854b27abb4bc1cdcdc5687f51c5f37eb5b385256f789f483aac42e2","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-13T15:11:31Z","title_canon_sha256":"8df3428527f52a5549c1e27e595fa88c6b058f9036f66b917d86658fcaf0b2f6"},"schema_version":"1.0","source":{"id":"2410.09871","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09871","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09871v2","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09871","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"63BVLHCD6J25","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"63BVLHCD6J25ADKY","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"63BVLHCD","created_at":"2026-07-05T10:43:40Z"}],"graph_snapshots":[{"event_id":"sha256:75ff8e72bd8fce81f6b3b0d4e26f9e9f4cff69ac56c73bc290c9da48c20b2bac","target":"graph","created_at":"2026-07-05T10:43:40Z","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/2410.09871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"PDF is one of the most prominent data formats, making PDF parsing crucial for information extraction and retrieval, particularly with the rise of RAG systems. While various PDF parsing tools exist, their effectiveness across different document types remains understudied, especially beyond academic papers. Our research aims to address this gap by comparing 10 popular PDF parsing tools across 6 document categories using the DocLayNet dataset. These tools include PyPDF, pdfminer-six, PyMuPDF, pdfplumber, pypdfium2, Unstructured, Tabula, Camelot, as well as the deep learning-based tools Nougat and","authors_text":"Narayan S. Adhikari, Shradha Agarwal","cross_cats":["cs.DL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-13T15:11:31Z","title":"A Comparative Study of PDF Parsing Tools Across Diverse Document Categories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09871","kind":"arxiv","version":2},"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":"sha256:49d69406bd069a70c587ccb807b43fa9e734808367e021eefe148af965e4b447","target":"record","created_at":"2026-07-05T10:43:40Z","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":"abc6838b8854b27abb4bc1cdcdc5687f51c5f37eb5b385256f789f483aac42e2","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-13T15:11:31Z","title_canon_sha256":"8df3428527f52a5549c1e27e595fa88c6b058f9036f66b917d86658fcaf0b2f6"},"schema_version":"1.0","source":{"id":"2410.09871","kind":"arxiv","version":2}},"canonical_sha256":"f6c3559c43f275d00d5834c2a781671b24911bc7823407dcb4b6d790cbe4dbcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6c3559c43f275d00d5834c2a781671b24911bc7823407dcb4b6d790cbe4dbcd","first_computed_at":"2026-07-05T10:43:40.140431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:40.140431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+APUzZ3kAZNTe0XRSor7nUWEGRNKJSNWJ/69pRblCJeqOLsSA6+DUvL0VLXEU4ojHLuX0QRbulbgIaMGmgehBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:40.140891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09871","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d69406bd069a70c587ccb807b43fa9e734808367e021eefe148af965e4b447","sha256:75ff8e72bd8fce81f6b3b0d4e26f9e9f4cff69ac56c73bc290c9da48c20b2bac"],"state_sha256":"ef41891e5599dee12fb06e0f28a54a860394ccbd68d8b95f3187ba186734279e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OzQCIqVyiOvHAePqWRWbeieaLbPVSLtxkS5DbDHl4SlAhJe30lubM39cMuMXl9vzEa2vzTcYCOPPtROyPRxNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:00:26.803987Z","bundle_sha256":"b244ffa485b30b9c5d26c5795348fc1512a90597ff04f9752e415a29d17bb094"}}