{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:U5EZZM2S4D6D3PY33T45TZSNEO","short_pith_number":"pith:U5EZZM2S","canonical_record":{"source":{"id":"2206.13155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-27T09:58:34Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"013767949ebfec1fa48df6a558feb27935bb1b0543ec94e2b96be91366e9b804","abstract_canon_sha256":"ff1020517a368bd5e932462922dd4c5a1da4481ef0ff46578af173c81e411ddc"},"schema_version":"1.0"},"canonical_sha256":"a7499cb352e0fc3dbf1bdcf9d9e64d23962c83f0aa0ea4a6bd686a4c108d37cb","source":{"kind":"arxiv","id":"2206.13155","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13155","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13155v2","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13155","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"U5EZZM2S4D6D","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"U5EZZM2S4D6D3PY3","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"U5EZZM2S","created_at":"2026-07-05T11:23:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:U5EZZM2S4D6D3PY33T45TZSNEO","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-27T09:58:34Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"013767949ebfec1fa48df6a558feb27935bb1b0543ec94e2b96be91366e9b804","abstract_canon_sha256":"ff1020517a368bd5e932462922dd4c5a1da4481ef0ff46578af173c81e411ddc"},"schema_version":"1.0"},"canonical_sha256":"a7499cb352e0fc3dbf1bdcf9d9e64d23962c83f0aa0ea4a6bd686a4c108d37cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:13.231850Z","signature_b64":"h7cvKYlODOtrPTT5QNk7Y9Wdnx5A9HZLqTrWUgcfEk58Wi3W7wTjDoF1DgkKqJ6aQz0imLGXfgpFYMkzx3Z0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7499cb352e0fc3dbf1bdcf9d9e64d23962c83f0aa0ea4a6bd686a4c108d37cb","last_reissued_at":"2026-07-05T11:23:13.231337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:13.231337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13155","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":"2026-07-05T11:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7McnyBtB3HGQc+Ett+po36HZU9KozrWuRljBv4wWuqKCJPC5R0CrHTQloNfvIf9sqtioJuZltyRsm/D0AzHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:55:48.715935Z"},"content_sha256":"43b0bf61aa95a64b0278d9961ad7431fecf7a7137a5360280a0ace4ee539cda3","schema_version":"1.0","event_id":"sha256:43b0bf61aa95a64b0278d9961ad7431fecf7a7137a5360280a0ace4ee539cda3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:U5EZZM2S4D6D3PY33T45TZSNEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chenliang Li, Chuwei Luo, Cong Yao, Guozhi Tang, Lianwen Jin, Luo Si, Qi Zheng, Yang Xue","submitted_at":"2022-06-27T09:58:34Z","abstract_excerpt":"Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard benchmarks for VrDU, the way they model and exploit the interactions between vision and language on documents has hindered them from better generalization ability and higher accuracy. In this work, we investigate the problem of vision-language joint representation learning for VrDU mainly from the perspective of supervisory signals. Specifically, a pre-training para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13155","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/2206.13155/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":"2026-07-05T11:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTJySgTn5EYUKEW9IA3n5R+WPawlhcP0pUzwIE7wN9M1VrSBsmMCdQ8rV6wlNPu+CQu8SK1urv2ENL1LSHi1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:55:48.716297Z"},"content_sha256":"2fd3c4be9f4da9d4026b141a1810946bd25ace69a6bfe974ae56a5506b49af9e","schema_version":"1.0","event_id":"sha256:2fd3c4be9f4da9d4026b141a1810946bd25ace69a6bfe974ae56a5506b49af9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5EZZM2S4D6D3PY33T45TZSNEO/bundle.json","state_url":"https://pith.science/pith/U5EZZM2S4D6D3PY33T45TZSNEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5EZZM2S4D6D3PY33T45TZSNEO/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":"2026-07-14T09:55:48Z","links":{"resolver":"https://pith.science/pith/U5EZZM2S4D6D3PY33T45TZSNEO","bundle":"https://pith.science/pith/U5EZZM2S4D6D3PY33T45TZSNEO/bundle.json","state":"https://pith.science/pith/U5EZZM2S4D6D3PY33T45TZSNEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5EZZM2S4D6D3PY33T45TZSNEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:U5EZZM2S4D6D3PY33T45TZSNEO","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":"ff1020517a368bd5e932462922dd4c5a1da4481ef0ff46578af173c81e411ddc","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-27T09:58:34Z","title_canon_sha256":"013767949ebfec1fa48df6a558feb27935bb1b0543ec94e2b96be91366e9b804"},"schema_version":"1.0","source":{"id":"2206.13155","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13155","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13155v2","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13155","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"U5EZZM2S4D6D","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"U5EZZM2S4D6D3PY3","created_at":"2026-07-05T11:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"U5EZZM2S","created_at":"2026-07-05T11:23:13Z"}],"graph_snapshots":[{"event_id":"sha256:2fd3c4be9f4da9d4026b141a1810946bd25ace69a6bfe974ae56a5506b49af9e","target":"graph","created_at":"2026-07-05T11:23:13Z","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/2206.13155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard benchmarks for VrDU, the way they model and exploit the interactions between vision and language on documents has hindered them from better generalization ability and higher accuracy. In this work, we investigate the problem of vision-language joint representation learning for VrDU mainly from the perspective of supervisory signals. Specifically, a pre-training para","authors_text":"Chenliang Li, Chuwei Luo, Cong Yao, Guozhi Tang, Lianwen Jin, Luo Si, Qi Zheng, Yang Xue","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-27T09:58:34Z","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13155","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":"sha256:43b0bf61aa95a64b0278d9961ad7431fecf7a7137a5360280a0ace4ee539cda3","target":"record","created_at":"2026-07-05T11:23:13Z","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":"ff1020517a368bd5e932462922dd4c5a1da4481ef0ff46578af173c81e411ddc","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-27T09:58:34Z","title_canon_sha256":"013767949ebfec1fa48df6a558feb27935bb1b0543ec94e2b96be91366e9b804"},"schema_version":"1.0","source":{"id":"2206.13155","kind":"arxiv","version":2}},"canonical_sha256":"a7499cb352e0fc3dbf1bdcf9d9e64d23962c83f0aa0ea4a6bd686a4c108d37cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7499cb352e0fc3dbf1bdcf9d9e64d23962c83f0aa0ea4a6bd686a4c108d37cb","first_computed_at":"2026-07-05T11:23:13.231337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:13.231337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7cvKYlODOtrPTT5QNk7Y9Wdnx5A9HZLqTrWUgcfEk58Wi3W7wTjDoF1DgkKqJ6aQz0imLGXfgpFYMkzx3Z0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:13.231850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13155","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43b0bf61aa95a64b0278d9961ad7431fecf7a7137a5360280a0ace4ee539cda3","sha256:2fd3c4be9f4da9d4026b141a1810946bd25ace69a6bfe974ae56a5506b49af9e"],"state_sha256":"0197f51b0bdbb6d735621ccf5003629a82b04b10d10027a5daae1a3dccf74b3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXgU7wCsf9Deo6mtwAiCsEJLgLvS7h3vI4Kc8Tmu76sXQW4y/N/C06HgFvPB2W5q9EcziY/uKq/NaVVuGjExCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T09:55:48.718685Z","bundle_sha256":"56f2f4d2f8b2e2b9c79d62e683e12a50e24ef69ea7b896a36525d37bf1375bdc"}}