{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IV3NXBRGAXW6HHFQBETQGF4EMJ","short_pith_number":"pith:IV3NXBRG","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"},"canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","source":{"kind":"arxiv","id":"2308.12896","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12896","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12896v3","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12896","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_12","alias_value":"IV3NXBRGAXW6","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_16","alias_value":"IV3NXBRGAXW6HHFQ","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_8","alias_value":"IV3NXBRG","created_at":"2026-07-05T07:07:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IV3NXBRGAXW6HHFQBETQGF4EMJ","target":"record","payload":{"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"},"canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","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"},"source_kind":"arxiv","source_id":"2308.12896","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KfvXXuxYwRRhEamgVQ7p8kMk9V6afRsgKuVThqB05YQM2UjcBFKOXeUZmfiBmNN6/EJPhIOwvFGo0mbg1F9oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:29:59.173152Z"},"content_sha256":"22d21334296f926e0f0cea6fc880d200f727fa0e9c7d9da73baa32e955e62023","schema_version":"1.0","event_id":"sha256:22d21334296f926e0f0cea6fc880d200f727fa0e9c7d9da73baa32e955e62023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IV3NXBRGAXW6HHFQBETQGF4EMJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZ7xqTL6NXFgvhVUpbbXKE0V22pqglDTDOE13ivAiBUeY4f66F3MBCYZ1gvlRIBUAFxy3dj6paJxhabXkCUiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:29:59.173726Z"},"content_sha256":"3221e2ddc91ece2f3a9c6cd9af7a651a56e453bf8abb68eaf74985a1865be01b","schema_version":"1.0","event_id":"sha256:3221e2ddc91ece2f3a9c6cd9af7a651a56e453bf8abb68eaf74985a1865be01b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/bundle.json","state_url":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/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":"2026-08-03T16:29:59Z","links":{"resolver":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ","bundle":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/bundle.json","state":"https://pith.science/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV3NXBRGAXW6HHFQBETQGF4EMJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IV3NXBRGAXW6HHFQBETQGF4EMJ","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":"2bb380d6ae6941a4afcdfb54ebe41cc26757a90cae2cbc1cbd849654d50ec77f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T16:16:47Z","title_canon_sha256":"29bdcfa963ab0380178c8699bcf6753d3d4309f80c9e5625827af1bec85a740b"},"schema_version":"1.0","source":{"id":"2308.12896","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12896","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12896v3","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12896","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_12","alias_value":"IV3NXBRGAXW6","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_16","alias_value":"IV3NXBRGAXW6HHFQ","created_at":"2026-07-05T07:07:14Z"},{"alias_kind":"pith_short_8","alias_value":"IV3NXBRG","created_at":"2026-07-05T07:07:14Z"}],"graph_snapshots":[{"event_id":"sha256:3221e2ddc91ece2f3a9c6cd9af7a651a56e453bf8abb68eaf74985a1865be01b","target":"graph","created_at":"2026-07-05T07:07:14Z","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/2308.12896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jordy Van Landeghem, Marie-Francine Moens, Matthew B. Blaschko, Sanket Biswas","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T16:16:47Z","title":"Beyond Document Page Classification: Design, Datasets, and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12896","kind":"arxiv","version":3},"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":"sha256:22d21334296f926e0f0cea6fc880d200f727fa0e9c7d9da73baa32e955e62023","target":"record","created_at":"2026-07-05T07:07:14Z","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":"2bb380d6ae6941a4afcdfb54ebe41cc26757a90cae2cbc1cbd849654d50ec77f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T16:16:47Z","title_canon_sha256":"29bdcfa963ab0380178c8699bcf6753d3d4309f80c9e5625827af1bec85a740b"},"schema_version":"1.0","source":{"id":"2308.12896","kind":"arxiv","version":3}},"canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4576db862605ede39cb009270317846260af7ceac098cb7af3b8c86f5979ed32","first_computed_at":"2026-07-05T07:07:14.863925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:14.863925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aeeYB3Azhb7YraLwYlR+q3SLPIYoLQqT+ijbTY/LUWm4bSK/xgovs02yXFRUQmEOSdMasUlEi3Mu6jnhyiSICg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:14.864382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12896","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22d21334296f926e0f0cea6fc880d200f727fa0e9c7d9da73baa32e955e62023","sha256:3221e2ddc91ece2f3a9c6cd9af7a651a56e453bf8abb68eaf74985a1865be01b"],"state_sha256":"5c197694ff9d1a3ed985f08b50b49d9d82ea53a50c58c9057b75df1598b7b04e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqcedKQE6ajgTTtG8BpJDxypHKkweLfgc+Ms7O5Ml53u4lLOgIpd0vBbrNtyd/9Rk9tEb1POvKzdiG6LZ5dOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:29:59.179640Z","bundle_sha256":"4fe48e811ad9eadaf23c9ae1c10f54d7b29f0f7db87fa67ef9fd6194e8e7b39f"}}