{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZXPH2UO7MAXBMEY6WJ6N2QGPYM","short_pith_number":"pith:ZXPH2UO7","canonical_record":{"source":{"id":"2403.16516","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T08:00:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"466fcc5edd9fcb56ff887d37a58b74cb1c56c57350bc97206cca433429f8d9bc","abstract_canon_sha256":"aec1b1a3a6427f801efa50ccbc907a9f10ccd4261227b913a2eacfbca40f301f"},"schema_version":"1.0"},"canonical_sha256":"cdde7d51df602e16131eb27cdd40cfc31ce59200c3439cc0876e6bd62111079b","source":{"kind":"arxiv","id":"2403.16516","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16516","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16516v2","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16516","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPH2UO7MAXB","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPH2UO7MAXBMEY6","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPH2UO7","created_at":"2026-07-05T08:01:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZXPH2UO7MAXBMEY6WJ6N2QGPYM","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16516","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T08:00:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"466fcc5edd9fcb56ff887d37a58b74cb1c56c57350bc97206cca433429f8d9bc","abstract_canon_sha256":"aec1b1a3a6427f801efa50ccbc907a9f10ccd4261227b913a2eacfbca40f301f"},"schema_version":"1.0"},"canonical_sha256":"cdde7d51df602e16131eb27cdd40cfc31ce59200c3439cc0876e6bd62111079b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:19.536694Z","signature_b64":"FgeBjNrLP86pQoy6PeIwKzH7gvwqn+6aWYMdn5YbffV1rZwOHGp6QdxoUMd/4ces1sgkOY+BLIdUHIpyVZCoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdde7d51df602e16131eb27cdd40cfc31ce59200c3439cc0876e6bd62111079b","last_reissued_at":"2026-07-05T08:01:19.536225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:19.536225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16516","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":"2026-07-05T08:01:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZVaZ2+v1pjhKcNMvydG7/hdG6CDSNBOgYGhWt8hYc4+32Hx1ZXNOOZzulqEY4ZMlnwtVR8EExt0DU7OUQpIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:02:53.890457Z"},"content_sha256":"c1f60c8e465c3e44c585603c63f8615658367b1c56a6df023adc70a69d80fb9c","schema_version":"1.0","event_id":"sha256:c1f60c8e465c3e44c585603c63f8615658367b1c56a6df023adc70a69d80fb9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZXPH2UO7MAXBMEY6WJ6N2QGPYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoli Bai, Jiansheng Wei, Kam-Fai Wong, Lu Hou, Qun Liu, Xin Jiang, Zhiming Mao","submitted_at":"2024-03-25T08:00:43Z","abstract_excerpt":"Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of texts and table-cells). To this end, we propose visually guided generative text-layout pre-training, named ViTLP. Given a document image, the model optimizes hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. In addition, to address the limitation of processing long documents by Transformers, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16516","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/2403.16516/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":"2026-07-05T08:01:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6aw+3lcRbf4oBfl6fUhUViRCQ5JaK97UdI1emVQjYLNtAT2tl4pxBkKxRxNaHydTAVENVXTbdowkCQ+gDHYaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:02:53.892058Z"},"content_sha256":"bd8f17beac80cfc70057dcbbe0b7e7b1775285dc920dc20e61a9a976af1cb1f6","schema_version":"1.0","event_id":"sha256:bd8f17beac80cfc70057dcbbe0b7e7b1775285dc920dc20e61a9a976af1cb1f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/bundle.json","state_url":"https://pith.science/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/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":"2026-08-12T05:02:53Z","links":{"resolver":"https://pith.science/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM","bundle":"https://pith.science/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/bundle.json","state":"https://pith.science/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXPH2UO7MAXBMEY6WJ6N2QGPYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZXPH2UO7MAXBMEY6WJ6N2QGPYM","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":"aec1b1a3a6427f801efa50ccbc907a9f10ccd4261227b913a2eacfbca40f301f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T08:00:43Z","title_canon_sha256":"466fcc5edd9fcb56ff887d37a58b74cb1c56c57350bc97206cca433429f8d9bc"},"schema_version":"1.0","source":{"id":"2403.16516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16516","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16516v2","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16516","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPH2UO7MAXB","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPH2UO7MAXBMEY6","created_at":"2026-07-05T08:01:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPH2UO7","created_at":"2026-07-05T08:01:19Z"}],"graph_snapshots":[{"event_id":"sha256:bd8f17beac80cfc70057dcbbe0b7e7b1775285dc920dc20e61a9a976af1cb1f6","target":"graph","created_at":"2026-07-05T08:01:19Z","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/2403.16516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of texts and table-cells). To this end, we propose visually guided generative text-layout pre-training, named ViTLP. Given a document image, the model optimizes hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. In addition, to address the limitation of processing long documents by Transformers, we introduce","authors_text":"Haoli Bai, Jiansheng Wei, Kam-Fai Wong, Lu Hou, Qun Liu, Xin Jiang, Zhiming Mao","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T08:00:43Z","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16516","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:c1f60c8e465c3e44c585603c63f8615658367b1c56a6df023adc70a69d80fb9c","target":"record","created_at":"2026-07-05T08:01:19Z","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":"aec1b1a3a6427f801efa50ccbc907a9f10ccd4261227b913a2eacfbca40f301f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T08:00:43Z","title_canon_sha256":"466fcc5edd9fcb56ff887d37a58b74cb1c56c57350bc97206cca433429f8d9bc"},"schema_version":"1.0","source":{"id":"2403.16516","kind":"arxiv","version":2}},"canonical_sha256":"cdde7d51df602e16131eb27cdd40cfc31ce59200c3439cc0876e6bd62111079b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdde7d51df602e16131eb27cdd40cfc31ce59200c3439cc0876e6bd62111079b","first_computed_at":"2026-07-05T08:01:19.536225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:19.536225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FgeBjNrLP86pQoy6PeIwKzH7gvwqn+6aWYMdn5YbffV1rZwOHGp6QdxoUMd/4ces1sgkOY+BLIdUHIpyVZCoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:19.536694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f60c8e465c3e44c585603c63f8615658367b1c56a6df023adc70a69d80fb9c","sha256:bd8f17beac80cfc70057dcbbe0b7e7b1775285dc920dc20e61a9a976af1cb1f6"],"state_sha256":"beffba2b6690a9d33b29f91bb42360d954592497d28dcc922388c2dc0b40182c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FomxWGmo4wcCaIondhM0iE6pDhsWIVSegTroT2b4ZyF43SRq1kbsRygU3t6Qqtib2dIuToe67trWJsMAdNe0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:02:53.899616Z","bundle_sha256":"382b901f1a7aa060521343adf8dc7d66635d219410cb91bc26deb30fc3e67053"}}