{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CWH2HKLQFRHMJTY7JS2BSY3LLL","short_pith_number":"pith:CWH2HKLQ","canonical_record":{"source":{"id":"2203.06947","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T09:19:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"19c455aaee8b37eb469ceb25a4a7e0ac496d68db4899a8f0ec988c7f07ac2e00","abstract_canon_sha256":"35768adbc5da61c6f681d05c0fc70b278e3114463a2cf1f1275167e4a31b759a"},"schema_version":"1.0"},"canonical_sha256":"158fa3a9702c4ec4cf1f4cb419636b5ae3fc43cd9ec93b27efce1bf77ce221c8","source":{"kind":"arxiv","id":"2203.06947","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06947","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06947v2","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06947","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"CWH2HKLQFRHM","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"CWH2HKLQFRHMJTY7","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"CWH2HKLQ","created_at":"2026-07-05T04:05:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CWH2HKLQFRHMJTY7JS2BSY3LLL","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06947","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T09:19:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"19c455aaee8b37eb469ceb25a4a7e0ac496d68db4899a8f0ec988c7f07ac2e00","abstract_canon_sha256":"35768adbc5da61c6f681d05c0fc70b278e3114463a2cf1f1275167e4a31b759a"},"schema_version":"1.0"},"canonical_sha256":"158fa3a9702c4ec4cf1f4cb419636b5ae3fc43cd9ec93b27efce1bf77ce221c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:18.353861Z","signature_b64":"PjEF1ExCwBQUoIXSn3HY/j3YFnQKAvAvJ2kLDGPeHt2rTMLqnU9foK4i52j/Mwn6IFI8dZlJcGwIH99hpfDvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158fa3a9702c4ec4cf1f4cb419636b5ae3fc43cd9ec93b27efce1bf77ce221c8","last_reissued_at":"2026-07-05T04:05:18.353376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:18.353376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06947","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":"2026-07-05T04:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifJjfuNx9vg2n3gh+AWQSJ8yvRNkeghRbNSoVThotd6bYNv5cT7kq2/UrkYpgp7j83RiwxeYRXHFW6UY9YnAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T01:49:42.958545Z"},"content_sha256":"dedd6532a555a43d553883ac10204691daa5e300ea53df37b5b357fd81d28f4e","schema_version":"1.0","event_id":"sha256:dedd6532a555a43d553883ac10204691daa5e300ea53df37b5b357fd81d28f4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CWH2HKLQFRHMJTY7JS2BSY3LLL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changhua Meng, Jun Lan, Ke Wang, Liqing Zhang, Ming Gu, Weiqiang Wang, Zhangxuan Gu","submitted_at":"2022-03-14T09:19:12Z","abstract_excerpt":"Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06947","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/2203.06947/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":"2026-07-05T04:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCmqJ99YX4U+htVkJATxLI/CIUMR90qNrYwNG+4zjMDEnml54TVkFZ6CXtN++M/atrKFadT0JycupBTE5wfeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T01:49:42.958903Z"},"content_sha256":"df93adef552c38136eea14e42bcd21e9489068b174bfb43496204149e8c54686","schema_version":"1.0","event_id":"sha256:df93adef552c38136eea14e42bcd21e9489068b174bfb43496204149e8c54686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/bundle.json","state_url":"https://pith.science/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/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":"2026-07-22T01:49:42Z","links":{"resolver":"https://pith.science/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL","bundle":"https://pith.science/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/bundle.json","state":"https://pith.science/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWH2HKLQFRHMJTY7JS2BSY3LLL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CWH2HKLQFRHMJTY7JS2BSY3LLL","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":"35768adbc5da61c6f681d05c0fc70b278e3114463a2cf1f1275167e4a31b759a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T09:19:12Z","title_canon_sha256":"19c455aaee8b37eb469ceb25a4a7e0ac496d68db4899a8f0ec988c7f07ac2e00"},"schema_version":"1.0","source":{"id":"2203.06947","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06947","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06947v2","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06947","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"CWH2HKLQFRHM","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"CWH2HKLQFRHMJTY7","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"CWH2HKLQ","created_at":"2026-07-05T04:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:df93adef552c38136eea14e42bcd21e9489068b174bfb43496204149e8c54686","target":"graph","created_at":"2026-07-05T04:05:18Z","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/2203.06947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated","authors_text":"Changhua Meng, Jun Lan, Ke Wang, Liqing Zhang, Ming Gu, Weiqiang Wang, Zhangxuan Gu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T09:19:12Z","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06947","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:dedd6532a555a43d553883ac10204691daa5e300ea53df37b5b357fd81d28f4e","target":"record","created_at":"2026-07-05T04:05:18Z","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":"35768adbc5da61c6f681d05c0fc70b278e3114463a2cf1f1275167e4a31b759a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T09:19:12Z","title_canon_sha256":"19c455aaee8b37eb469ceb25a4a7e0ac496d68db4899a8f0ec988c7f07ac2e00"},"schema_version":"1.0","source":{"id":"2203.06947","kind":"arxiv","version":2}},"canonical_sha256":"158fa3a9702c4ec4cf1f4cb419636b5ae3fc43cd9ec93b27efce1bf77ce221c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"158fa3a9702c4ec4cf1f4cb419636b5ae3fc43cd9ec93b27efce1bf77ce221c8","first_computed_at":"2026-07-05T04:05:18.353376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:18.353376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PjEF1ExCwBQUoIXSn3HY/j3YFnQKAvAvJ2kLDGPeHt2rTMLqnU9foK4i52j/Mwn6IFI8dZlJcGwIH99hpfDvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:18.353861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06947","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dedd6532a555a43d553883ac10204691daa5e300ea53df37b5b357fd81d28f4e","sha256:df93adef552c38136eea14e42bcd21e9489068b174bfb43496204149e8c54686"],"state_sha256":"9190f29c330a16719c4a2933fbe9fce083f411777253ed6996a33724609f65ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4rnOHKWQprgkOWq5cMDW97f69lTxiE8KX2mNcjcUfGzOXq9T7wwZxZCG9OtIr9sLK4FgzefFJalFi/0+2CjmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T01:49:42.960830Z","bundle_sha256":"c28a65e0b602af546ab6a135e5c334cbf6505a39e03ef8f50868d148311a1312"}}