{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RLKZRKBED3JEIIO2ZCIMVEFO6N","short_pith_number":"pith:RLKZRKBE","canonical_record":{"source":{"id":"2408.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T03:31:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"f9231c95845dbcd029b674156e1f11c417c734dd2cf83eb8646586c8e9200e44","abstract_canon_sha256":"e1828827bf86b670b5a2d0f1302b167ad17f74d5a64d6b7e550a4fd0531b7b48"},"schema_version":"1.0"},"canonical_sha256":"8ad598a8241ed24421dac890ca90aef35e81da205c53042c4197718e3ebd798b","source":{"kind":"arxiv","id":"2408.14764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14764","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14764v1","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14764","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"RLKZRKBED3JE","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"RLKZRKBED3JEIIO2","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"RLKZRKBE","created_at":"2026-07-05T08:59:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RLKZRKBED3JEIIO2ZCIMVEFO6N","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T03:31:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"f9231c95845dbcd029b674156e1f11c417c734dd2cf83eb8646586c8e9200e44","abstract_canon_sha256":"e1828827bf86b670b5a2d0f1302b167ad17f74d5a64d6b7e550a4fd0531b7b48"},"schema_version":"1.0"},"canonical_sha256":"8ad598a8241ed24421dac890ca90aef35e81da205c53042c4197718e3ebd798b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:38.724986Z","signature_b64":"mW+PiWgYxwYLDd85seV1p5txXSRxKRQYLi5SsKT7Yd3FBMSOd91lZOkOw/JAwmWIlM9A2WWTZ9IkmyrZnHb6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad598a8241ed24421dac890ca90aef35e81da205c53042c4197718e3ebd798b","last_reissued_at":"2026-07-05T08:59:38.724565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:38.724565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14764","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NjToeOuCtc4oycG7t/Sc8I26fj6rz/TPLbFJa1EVY38IivTLjUPFphwkpVPf0HXYkFuAqY5rKGZLMpDXkTHfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:24:20.971441Z"},"content_sha256":"2f5c3800cc0ce30e4ec7abdb0991d481b901e9007a0cb17e7370eb9d35c33d4c","schema_version":"1.0","event_id":"sha256:2f5c3800cc0ce30e4ec7abdb0991d481b901e9007a0cb17e7370eb9d35c33d4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RLKZRKBED3JEIIO2ZCIMVEFO6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Cam-Tu Nguyen, Chuanghao Ding, Fei Tan, Juan Li, Rui Zhao, Wei Tang, Xiaoliang Wang, Xuejing Liu","submitted_at":"2024-08-27T03:31:24Z","abstract_excerpt":"This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets that include text, images, tables, and charts. Addressing the challenges of data acquisition and the limitations of existing datasets, SynthDoc leverages publicly available corpora and advanced rendering tools to create a comprehensive and versatile dataset. Our experiments, conducted using the Donut model, demonstrate that models trained with SynthDoc's data achieve superior performance in pre-training read tasks an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14764","kind":"arxiv","version":1},"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/2408.14764/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":"2026-07-05T08:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBWZG/jouqNphv8SgEorAyElR69RKZQcFPUCxPlKRyMGkbb2wM+QQtsQRcdrKmvU2nKsUzUz+te0U3OHihdNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:24:20.971950Z"},"content_sha256":"da858336c80c2da217b934f47e7fc6c28c0ca2a921908c85dd3d1797b800c5a4","schema_version":"1.0","event_id":"sha256:da858336c80c2da217b934f47e7fc6c28c0ca2a921908c85dd3d1797b800c5a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/bundle.json","state_url":"https://pith.science/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/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":"2026-08-03T20:24:20Z","links":{"resolver":"https://pith.science/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N","bundle":"https://pith.science/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/bundle.json","state":"https://pith.science/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLKZRKBED3JEIIO2ZCIMVEFO6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLKZRKBED3JEIIO2ZCIMVEFO6N","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":"e1828827bf86b670b5a2d0f1302b167ad17f74d5a64d6b7e550a4fd0531b7b48","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T03:31:24Z","title_canon_sha256":"f9231c95845dbcd029b674156e1f11c417c734dd2cf83eb8646586c8e9200e44"},"schema_version":"1.0","source":{"id":"2408.14764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14764","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14764v1","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14764","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"RLKZRKBED3JE","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"RLKZRKBED3JEIIO2","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"RLKZRKBE","created_at":"2026-07-05T08:59:38Z"}],"graph_snapshots":[{"event_id":"sha256:da858336c80c2da217b934f47e7fc6c28c0ca2a921908c85dd3d1797b800c5a4","target":"graph","created_at":"2026-07-05T08:59:38Z","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/2408.14764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets that include text, images, tables, and charts. Addressing the challenges of data acquisition and the limitations of existing datasets, SynthDoc leverages publicly available corpora and advanced rendering tools to create a comprehensive and versatile dataset. Our experiments, conducted using the Donut model, demonstrate that models trained with SynthDoc's data achieve superior performance in pre-training read tasks an","authors_text":"Cam-Tu Nguyen, Chuanghao Ding, Fei Tan, Juan Li, Rui Zhao, Wei Tang, Xiaoliang Wang, Xuejing Liu","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T03:31:24Z","title":"SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14764","kind":"arxiv","version":1},"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":"sha256:2f5c3800cc0ce30e4ec7abdb0991d481b901e9007a0cb17e7370eb9d35c33d4c","target":"record","created_at":"2026-07-05T08:59:38Z","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":"e1828827bf86b670b5a2d0f1302b167ad17f74d5a64d6b7e550a4fd0531b7b48","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T03:31:24Z","title_canon_sha256":"f9231c95845dbcd029b674156e1f11c417c734dd2cf83eb8646586c8e9200e44"},"schema_version":"1.0","source":{"id":"2408.14764","kind":"arxiv","version":1}},"canonical_sha256":"8ad598a8241ed24421dac890ca90aef35e81da205c53042c4197718e3ebd798b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad598a8241ed24421dac890ca90aef35e81da205c53042c4197718e3ebd798b","first_computed_at":"2026-07-05T08:59:38.724565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:38.724565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mW+PiWgYxwYLDd85seV1p5txXSRxKRQYLi5SsKT7Yd3FBMSOd91lZOkOw/JAwmWIlM9A2WWTZ9IkmyrZnHb6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:38.724986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f5c3800cc0ce30e4ec7abdb0991d481b901e9007a0cb17e7370eb9d35c33d4c","sha256:da858336c80c2da217b934f47e7fc6c28c0ca2a921908c85dd3d1797b800c5a4"],"state_sha256":"fec9b0f222c64bac25395ae037e1b915ca50562b0e44906a9b8826ef24753d91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RavaNeqPBpX6Mo2OZOmEDhU+unNtWAOAYDO0ae7RjCavkWi4ix4qlrzK3+IkSktJIoMWvAsi67eX1sAgT0xHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:24:20.975490Z","bundle_sha256":"2cd841219b8043cb543b8850574d678a9e138d5eff34deb21b3d9703a4667d43"}}