{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D2D54AHX6CBUVOVVFADGL6LOBT","short_pith_number":"pith:D2D54AHX","canonical_record":{"source":{"id":"2504.09795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T01:50:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"title_canon_sha256":"1d5f0878cfc33879ef8275d3cc3598c43a2f8734e4640d1733b2aaa28a9bcdaf","abstract_canon_sha256":"84786a236e1156af21df912fcc35cf34af484d36737adf03f9dd33b4fdb0a10a"},"schema_version":"1.0"},"canonical_sha256":"1e87de00f7f0834abab5280665f96e0cc36f5cc600e94049d723fc3ca2e8d7a8","source":{"kind":"arxiv","id":"2504.09795","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09795","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09795v1","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09795","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"D2D54AHX6CBU","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"D2D54AHX6CBUVOVV","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"D2D54AHX","created_at":"2026-07-05T10:48:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D2D54AHX6CBUVOVVFADGL6LOBT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T01:50:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"title_canon_sha256":"1d5f0878cfc33879ef8275d3cc3598c43a2f8734e4640d1733b2aaa28a9bcdaf","abstract_canon_sha256":"84786a236e1156af21df912fcc35cf34af484d36737adf03f9dd33b4fdb0a10a"},"schema_version":"1.0"},"canonical_sha256":"1e87de00f7f0834abab5280665f96e0cc36f5cc600e94049d723fc3ca2e8d7a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:42.839230Z","signature_b64":"r5+pSp43hUAfl8SL1pN8HZkSG406rkiOBGvIAJwtZt6+yXI1clCiIdCYtqMonwXmd3ZdxGp0yWGfLWe0eh+DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e87de00f7f0834abab5280665f96e0cc36f5cc600e94049d723fc3ca2e8d7a8","last_reissued_at":"2026-07-05T10:48:42.838784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:42.838784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09795","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":"2026-07-05T10:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUPpk5yGUChEt8pBF8Z8oLxHE1mkRkIhymBaPZDkw6ho243mtSLNSYA+VMwGLluh5cKUmpBB1ScrFEmFUvkpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T03:54:32.609796Z"},"content_sha256":"43b2d83462ee656421bd50f1332356c648175a5d1f591a4c4f92ffb4d3f38e27","schema_version":"1.0","event_id":"sha256:43b2d83462ee656421bd50f1332356c648175a5d1f591a4c4f92ffb4d3f38e27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D2D54AHX6CBUVOVVFADGL6LOBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jun Suzuki, Kuniko Saito, Kyosuke Nishida, Ryota Tanaka, Taichi Iki, Taku Hasegawa","submitted_at":"2025-04-14T01:50:33Z","abstract_excerpt":"We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format to prevent missing information that occurs by parsing documents to obtain text. To improve the performance, we propose novel self-supervised pre-training tasks that adapt large vision-language models for retrieval by compressing vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09795","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/2504.09795/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":"2026-07-05T10:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEHauMIsglag20Clt4cklbMBWKkn60efoTx3DmNYbVj1dg+tCWSqmLwStvn9p0LQ8bWIjCRD92+uyOrjuSZCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T03:54:32.610174Z"},"content_sha256":"4db2c6179e0506893db9a2259f82706819d82117957e9ad93485e3c1cc8308af","schema_version":"1.0","event_id":"sha256:4db2c6179e0506893db9a2259f82706819d82117957e9ad93485e3c1cc8308af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D2D54AHX6CBUVOVVFADGL6LOBT/bundle.json","state_url":"https://pith.science/pith/D2D54AHX6CBUVOVVFADGL6LOBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D2D54AHX6CBUVOVVFADGL6LOBT/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":"2026-07-17T03:54:32Z","links":{"resolver":"https://pith.science/pith/D2D54AHX6CBUVOVVFADGL6LOBT","bundle":"https://pith.science/pith/D2D54AHX6CBUVOVVFADGL6LOBT/bundle.json","state":"https://pith.science/pith/D2D54AHX6CBUVOVVFADGL6LOBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D2D54AHX6CBUVOVVFADGL6LOBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D2D54AHX6CBUVOVVFADGL6LOBT","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":"84786a236e1156af21df912fcc35cf34af484d36737adf03f9dd33b4fdb0a10a","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T01:50:33Z","title_canon_sha256":"1d5f0878cfc33879ef8275d3cc3598c43a2f8734e4640d1733b2aaa28a9bcdaf"},"schema_version":"1.0","source":{"id":"2504.09795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09795","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09795v1","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09795","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"D2D54AHX6CBU","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_16","alias_value":"D2D54AHX6CBUVOVV","created_at":"2026-07-05T10:48:42Z"},{"alias_kind":"pith_short_8","alias_value":"D2D54AHX","created_at":"2026-07-05T10:48:42Z"}],"graph_snapshots":[{"event_id":"sha256:4db2c6179e0506893db9a2259f82706819d82117957e9ad93485e3c1cc8308af","target":"graph","created_at":"2026-07-05T10:48:42Z","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/2504.09795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format to prevent missing information that occurs by parsing documents to obtain text. To improve the performance, we propose novel self-supervised pre-training tasks that adapt large vision-language models for retrieval by compressing vi","authors_text":"Jun Suzuki, Kuniko Saito, Kyosuke Nishida, Ryota Tanaka, Taichi Iki, Taku Hasegawa","cross_cats":["cs.AI","cs.CV","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T01:50:33Z","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09795","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":"sha256:43b2d83462ee656421bd50f1332356c648175a5d1f591a4c4f92ffb4d3f38e27","target":"record","created_at":"2026-07-05T10:48:42Z","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":"84786a236e1156af21df912fcc35cf34af484d36737adf03f9dd33b4fdb0a10a","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T01:50:33Z","title_canon_sha256":"1d5f0878cfc33879ef8275d3cc3598c43a2f8734e4640d1733b2aaa28a9bcdaf"},"schema_version":"1.0","source":{"id":"2504.09795","kind":"arxiv","version":1}},"canonical_sha256":"1e87de00f7f0834abab5280665f96e0cc36f5cc600e94049d723fc3ca2e8d7a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e87de00f7f0834abab5280665f96e0cc36f5cc600e94049d723fc3ca2e8d7a8","first_computed_at":"2026-07-05T10:48:42.838784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:42.838784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r5+pSp43hUAfl8SL1pN8HZkSG406rkiOBGvIAJwtZt6+yXI1clCiIdCYtqMonwXmd3ZdxGp0yWGfLWe0eh+DCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:42.839230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43b2d83462ee656421bd50f1332356c648175a5d1f591a4c4f92ffb4d3f38e27","sha256:4db2c6179e0506893db9a2259f82706819d82117957e9ad93485e3c1cc8308af"],"state_sha256":"cb0effd8cf449eee19782f83d96b832b6730e4acff90d5247e45302b05d58738"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6X+Iwu5HB/dLEXBp70PDDepEAg1oQJ3Ytd9OHO9DwauffpAXH/Dzoh2fSxBE33oWeT0Cscot3BIzqE+vCG8CBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T03:54:32.612623Z","bundle_sha256":"d03e379ef185305baacec5e175950635ea6eacfc27315a65ea47157daa241d03"}}