{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IV3NXBRGAXW6HHFQBETQGF4EMJ","short_pith_number":"pith:IV3NXBRG","schema_version":"1.0","canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","source":{"kind":"arxiv","id":"2308.12896","version":3},"attestation_state":"computed","paper":{"title":"Beyond Document Page Classification: Design, Datasets, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jordy Van Landeghem, Marie-Francine Moens, Matthew B. Blaschko, Sanket Biswas","submitted_at":"2023-08-24T16:16:47Z","abstract_excerpt":"This paper highlights the need to bring document classification benchmarking closer to real-world applications, both in the nature of data tested ($X$: multi-channel, multi-paged, multi-industry; $Y$: class distributions and label set variety) and in classification tasks considered ($f$: multi-page document, page stream, and document bundle classification, ...). We identify the lack of public multi-page document classification datasets, formalize different classification tasks arising in application scenarios, and motivate the value of targeting efficient multi-page document representations. A"},"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":"2308.12896","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T16:16:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"29bdcfa963ab0380178c8699bcf6753d3d4309f80c9e5625827af1bec85a740b","abstract_canon_sha256":"2bb380d6ae6941a4afcdfb54ebe41cc26757a90cae2cbc1cbd849654d50ec77f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:14.864382Z","signature_b64":"aeeYB3Azhb7YraLwYlR+q3SLPIYoLQqT+ijbTY/LUWm4bSK/xgovs02yXFRUQmEOSdMasUlEi3Mu6jnhyiSICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","last_reissued_at":"2026-07-05T07:07:14.863925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:14.863925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Document Page Classification: Design, Datasets, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jordy Van Landeghem, Marie-Francine Moens, Matthew B. Blaschko, Sanket Biswas","submitted_at":"2023-08-24T16:16:47Z","abstract_excerpt":"This paper highlights the need to bring document classification benchmarking closer to real-world applications, both in the nature of data tested ($X$: multi-channel, multi-paged, multi-industry; $Y$: class distributions and label set variety) and in classification tasks considered ($f$: multi-page document, page stream, and document bundle classification, ...). We identify the lack of public multi-page document classification datasets, formalize different classification tasks arising in application scenarios, and motivate the value of targeting efficient multi-page document representations. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12896","kind":"arxiv","version":3},"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/2308.12896/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":"2308.12896","created_at":"2026-07-05T07:07:14.863986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12896v3","created_at":"2026-07-05T07:07:14.863986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12896","created_at":"2026-07-05T07:07:14.863986+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV3NXBRGAXW6","created_at":"2026-07-05T07:07:14.863986+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV3NXBRGAXW6HHFQ","created_at":"2026-07-05T07:07:14.863986+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV3NXBRG","created_at":"2026-07-05T07:07:14.863986+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/IV3NXBRGAXW6HHFQBETQGF4EMJ","json":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ.json","graph_json":"https://pith.science/api/pith-number/IV3NXBRGAXW6HHFQBETQGF4EMJ/graph.json","events_json":"https://pith.science/api/pith-number/IV3NXBRGAXW6HHFQBETQGF4EMJ/events.json","paper":"https://pith.science/paper/IV3NXBRG"},"agent_actions":{"view_html":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ","download_json":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ.json","view_paper":"https://pith.science/paper/IV3NXBRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12896&json=true","fetch_graph":"https://pith.science/api/pith-number/IV3NXBRGAXW6HHFQBETQGF4EMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IV3NXBRGAXW6HHFQBETQGF4EMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/action/storage_attestation","attest_author":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/action/author_attestation","sign_citation":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/action/citation_signature","submit_replication":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/action/replication_record"}},"created_at":"2026-07-05T07:07:14.863986+00:00","updated_at":"2026-07-05T07:07:14.863986+00:00"}