{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:57OKZUAEQDIOUZXUD63RFAERQV","short_pith_number":"pith:57OKZUAE","canonical_record":{"source":{"id":"2402.02379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T07:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"6e4e88f847f3ae8076768afdaa70b3a7b5d607b2afce3e8350153b15bdc588f9","abstract_canon_sha256":"b3d3417bd63b4af022ba6940c6c22462debc08da0f511ebafe532250f419a5d4"},"schema_version":"1.0"},"canonical_sha256":"efdcacd00480d0ea66f41fb7128091856cdbe8d572b0a43af9803788f7d0d797","source":{"kind":"arxiv","id":"2402.02379","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02379","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02379v2","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02379","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"57OKZUAEQDIO","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"57OKZUAEQDIOUZXU","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"57OKZUAE","created_at":"2026-07-05T10:48:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:57OKZUAEQDIOUZXUD63RFAERQV","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T07:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"6e4e88f847f3ae8076768afdaa70b3a7b5d607b2afce3e8350153b15bdc588f9","abstract_canon_sha256":"b3d3417bd63b4af022ba6940c6c22462debc08da0f511ebafe532250f419a5d4"},"schema_version":"1.0"},"canonical_sha256":"efdcacd00480d0ea66f41fb7128091856cdbe8d572b0a43af9803788f7d0d797","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:14.448769Z","signature_b64":"YqXZjQrFADDaAObIrDvTKtsDmkFz+4kwZEI/+wqEwkd8A/OJOolsxJ52G0zVS6sunU7TEbXJDlqmW4Vx/Ou+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efdcacd00480d0ea66f41fb7128091856cdbe8d572b0a43af9803788f7d0d797","last_reissued_at":"2026-07-05T10:48:14.448260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:14.448260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02379","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":"2026-07-05T10:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAlNyjvFr7Kv7dp6CBVvyXRwl1pBpwTTY/tFqqPXi/AkpT7OpNbnaJtzlCeTcBOXlIyUFRCZRpA40uFiB7M+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:01:02.033798Z"},"content_sha256":"b9590f5bf3b00507a1f0a45b50383b06b1f01fd3b735bdc12b425e716887e69b","schema_version":"1.0","event_id":"sha256:b9590f5bf3b00507a1f0a45b50383b06b1f01fd3b735bdc12b425e716887e69b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:57OKZUAEQDIOUZXUD63RFAERQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenshu Yuan, Chong Zhang, Mingxu Chai, Qi Zhang, Ya Guo, Yi Tu, Yixi Zhao, Yue Zhang, Yulu Xie, Ziyu Shen","submitted_at":"2024-02-04T07:33:45Z","abstract_excerpt":"Recently developed pre-trained text-and-layout models (PTLMs) have shown remarkable success in multiple information extraction tasks on visually-rich documents (VrDs). However, despite achieving extremely high performance on benchmarks, their real-world performance falls short of expectations. Owing to this issue, we investigate the prevailing evaluation pipeline to reveal that: (1) The inadequate annotations within benchmark datasets introduce spurious correlations between task inputs and labels, which would lead to overly-optimistic estimation of model performance. (2) The evaluation solely "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02379","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/2402.02379/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":"2026-07-05T10:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hemQCrWrUaK0AneeVIliI6pmmvmWrTSMpy6JCrNMRO78REJAWA8ebi25URr6cpEvFg7OXyOoJSMlLXsUsa6NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:01:02.034296Z"},"content_sha256":"dd830ae1df3fc559235df51030ede530b58832c85105971d5ed9c4cc4376b693","schema_version":"1.0","event_id":"sha256:dd830ae1df3fc559235df51030ede530b58832c85105971d5ed9c4cc4376b693"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57OKZUAEQDIOUZXUD63RFAERQV/bundle.json","state_url":"https://pith.science/pith/57OKZUAEQDIOUZXUD63RFAERQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57OKZUAEQDIOUZXUD63RFAERQV/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":"2026-08-06T01:01:02Z","links":{"resolver":"https://pith.science/pith/57OKZUAEQDIOUZXUD63RFAERQV","bundle":"https://pith.science/pith/57OKZUAEQDIOUZXUD63RFAERQV/bundle.json","state":"https://pith.science/pith/57OKZUAEQDIOUZXUD63RFAERQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57OKZUAEQDIOUZXUD63RFAERQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57OKZUAEQDIOUZXUD63RFAERQV","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":"b3d3417bd63b4af022ba6940c6c22462debc08da0f511ebafe532250f419a5d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T07:33:45Z","title_canon_sha256":"6e4e88f847f3ae8076768afdaa70b3a7b5d607b2afce3e8350153b15bdc588f9"},"schema_version":"1.0","source":{"id":"2402.02379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02379","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02379v2","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02379","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"57OKZUAEQDIO","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"57OKZUAEQDIOUZXU","created_at":"2026-07-05T10:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"57OKZUAE","created_at":"2026-07-05T10:48:14Z"}],"graph_snapshots":[{"event_id":"sha256:dd830ae1df3fc559235df51030ede530b58832c85105971d5ed9c4cc4376b693","target":"graph","created_at":"2026-07-05T10:48:14Z","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/2402.02379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently developed pre-trained text-and-layout models (PTLMs) have shown remarkable success in multiple information extraction tasks on visually-rich documents (VrDs). However, despite achieving extremely high performance on benchmarks, their real-world performance falls short of expectations. Owing to this issue, we investigate the prevailing evaluation pipeline to reveal that: (1) The inadequate annotations within benchmark datasets introduce spurious correlations between task inputs and labels, which would lead to overly-optimistic estimation of model performance. (2) The evaluation solely ","authors_text":"Chenshu Yuan, Chong Zhang, Mingxu Chai, Qi Zhang, Ya Guo, Yi Tu, Yixi Zhao, Yue Zhang, Yulu Xie, Ziyu Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T07:33:45Z","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02379","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:b9590f5bf3b00507a1f0a45b50383b06b1f01fd3b735bdc12b425e716887e69b","target":"record","created_at":"2026-07-05T10:48:14Z","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":"b3d3417bd63b4af022ba6940c6c22462debc08da0f511ebafe532250f419a5d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T07:33:45Z","title_canon_sha256":"6e4e88f847f3ae8076768afdaa70b3a7b5d607b2afce3e8350153b15bdc588f9"},"schema_version":"1.0","source":{"id":"2402.02379","kind":"arxiv","version":2}},"canonical_sha256":"efdcacd00480d0ea66f41fb7128091856cdbe8d572b0a43af9803788f7d0d797","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efdcacd00480d0ea66f41fb7128091856cdbe8d572b0a43af9803788f7d0d797","first_computed_at":"2026-07-05T10:48:14.448260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:14.448260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YqXZjQrFADDaAObIrDvTKtsDmkFz+4kwZEI/+wqEwkd8A/OJOolsxJ52G0zVS6sunU7TEbXJDlqmW4Vx/Ou+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:14.448769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9590f5bf3b00507a1f0a45b50383b06b1f01fd3b735bdc12b425e716887e69b","sha256:dd830ae1df3fc559235df51030ede530b58832c85105971d5ed9c4cc4376b693"],"state_sha256":"aa92c89f587d46603a67422986dd68c0c69026e889b899e4ec32980ba490d451"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lLVk5MgDMfCeGhJCR9xOPQW7chwFsMKQigSzPMzwKtMxXp68UmDbbTgFGVq4MdYb9wvf0ODpXRETbZXbenuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:01:02.038271Z","bundle_sha256":"ed2a93d161996dee41813559248f6e36751a253819400dc42859afb3a16624b7"}}