{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T3VQWH72UZ5YEDEXYY3O4UMXHC","short_pith_number":"pith:T3VQWH72","canonical_record":{"source":{"id":"2411.04952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0a98a73e60d58e98560ed00b7c8af76fd1d7a23e6aee27ffc0313aeb25fc4ac6","abstract_canon_sha256":"c6a830a1db142fcb673c7320fa018e2b818dd5940e4f2c90955c6265d77eeb6f"},"schema_version":"1.0"},"canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","source":{"kind":"arxiv","id":"2411.04952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04952","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04952v1","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04952","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"T3VQWH72UZ5Y","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"T3VQWH72UZ5YEDEX","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"T3VQWH72","created_at":"2026-07-05T09:32:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T3VQWH72UZ5YEDEXYY3O4UMXHC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0a98a73e60d58e98560ed00b7c8af76fd1d7a23e6aee27ffc0313aeb25fc4ac6","abstract_canon_sha256":"c6a830a1db142fcb673c7320fa018e2b818dd5940e4f2c90955c6265d77eeb6f"},"schema_version":"1.0"},"canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:36.652618Z","signature_b64":"3yFs0XuJq8sVc5MY3McyBj8LJg/Ut96Y8S4vYrkuYKl23xiR3Ug7cEhosQwb3en+rar4LGf11MLG9HsZc6HqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","last_reissued_at":"2026-07-05T09:32:36.651945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:36.651945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04952","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":"2026-07-05T09:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qYf6H42ZhV78F0pOeSPDkjVbdOgp0ecvvXnXlgatcN0D2vCaBDPS0mUz3HMYmnW1FmgKNnbuLOWZSNzWjfCSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:38:25.758588Z"},"content_sha256":"ef954b63556c81b5378919c0b4e1f673886777b7fa6412771db59d2a69a88d94","schema_version":"1.0","event_id":"sha256:ef954b63556c81b5378919c0b4e1f673886777b7fa6412771db59d2a69a88d94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T3VQWH72UZ5YEDEXYY3O4UMXHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Debanjan Mahata, Jaemin Cho, Mohit Bansal, Ozan Irsoy, Yujie He","submitted_at":"2024-11-07T18:29:38Z","abstract_excerpt":"Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based retrieval-augmented generation (RAG) that uses text extraction tools such as optical character recognition (OCR). However, there are difficulties in applying these methods in real-world scenarios: (a) questions often require information across different pages or documents, where MLMs cannot handle many long documents; (b) documents often have important informati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04952","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/2411.04952/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":"2026-07-05T09:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNGDjr6FHeJXF55il5PqoL7NLbNItPTPcN2WJztoaQSAHprh/w3rFivd3STFA//NvXaelmBzj5BW+d+ibG4kCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:38:25.758884Z"},"content_sha256":"c01a979a24c041a77783db3e0017c44ff39c964d8cc6e344ad60d6e1b7dd80ed","schema_version":"1.0","event_id":"sha256:c01a979a24c041a77783db3e0017c44ff39c964d8cc6e344ad60d6e1b7dd80ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/bundle.json","state_url":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/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":"2026-08-03T01:38:25Z","links":{"resolver":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC","bundle":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/bundle.json","state":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3VQWH72UZ5YEDEXYY3O4UMXHC","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":"c6a830a1db142fcb673c7320fa018e2b818dd5940e4f2c90955c6265d77eeb6f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","title_canon_sha256":"0a98a73e60d58e98560ed00b7c8af76fd1d7a23e6aee27ffc0313aeb25fc4ac6"},"schema_version":"1.0","source":{"id":"2411.04952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04952","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04952v1","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04952","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"T3VQWH72UZ5Y","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"T3VQWH72UZ5YEDEX","created_at":"2026-07-05T09:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"T3VQWH72","created_at":"2026-07-05T09:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:c01a979a24c041a77783db3e0017c44ff39c964d8cc6e344ad60d6e1b7dd80ed","target":"graph","created_at":"2026-07-05T09:32:36Z","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/2411.04952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based retrieval-augmented generation (RAG) that uses text extraction tools such as optical character recognition (OCR). However, there are difficulties in applying these methods in real-world scenarios: (a) questions often require information across different pages or documents, where MLMs cannot handle many long documents; (b) documents often have important informati","authors_text":"Debanjan Mahata, Jaemin Cho, Mohit Bansal, Ozan Irsoy, Yujie He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04952","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:ef954b63556c81b5378919c0b4e1f673886777b7fa6412771db59d2a69a88d94","target":"record","created_at":"2026-07-05T09:32:36Z","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":"c6a830a1db142fcb673c7320fa018e2b818dd5940e4f2c90955c6265d77eeb6f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","title_canon_sha256":"0a98a73e60d58e98560ed00b7c8af76fd1d7a23e6aee27ffc0313aeb25fc4ac6"},"schema_version":"1.0","source":{"id":"2411.04952","kind":"arxiv","version":1}},"canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","first_computed_at":"2026-07-05T09:32:36.651945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:36.651945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3yFs0XuJq8sVc5MY3McyBj8LJg/Ut96Y8S4vYrkuYKl23xiR3Ug7cEhosQwb3en+rar4LGf11MLG9HsZc6HqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:36.652618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef954b63556c81b5378919c0b4e1f673886777b7fa6412771db59d2a69a88d94","sha256:c01a979a24c041a77783db3e0017c44ff39c964d8cc6e344ad60d6e1b7dd80ed"],"state_sha256":"a0b4cd9cbbf6e93c652c9a0afdace3b144de4d68c98fa7f4593a3bccec3b129d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAOiuhVu2NZMLz6oNTUUaM/uoS9kV1Hodc3iaZ/2kQk19gAKeGcPDEK76I2/PWqY6RP2yJp2tZ8zMF2f7CalDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T01:38:25.761855Z","bundle_sha256":"0c6b2298ac104103f1d446b168d422ebbf1f4326d0e1f8b2a4363fce2f86e3b1"}}