{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GSIYGV6YQT26IPYBTV2MPUHBBO","short_pith_number":"pith:GSIYGV6Y","canonical_record":{"source":{"id":"2412.00151","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T06:17:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ef08e515ed21f9ffb014072e32962a8ea76029e273bb0c48e79c138622ecd15","abstract_canon_sha256":"7650bb5abb0153f52edcd9de824118b48cfb0a929c69fcccd888b7c59918147e"},"schema_version":"1.0"},"canonical_sha256":"34918357d884f5e43f019d74c7d0e10bbb0366aaee1cd9940d76b97086c09dea","source":{"kind":"arxiv","id":"2412.00151","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00151","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00151v2","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00151","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"GSIYGV6YQT26","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"GSIYGV6YQT26IPYB","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"GSIYGV6Y","created_at":"2026-07-05T11:34:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GSIYGV6YQT26IPYBTV2MPUHBBO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00151","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T06:17:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ef08e515ed21f9ffb014072e32962a8ea76029e273bb0c48e79c138622ecd15","abstract_canon_sha256":"7650bb5abb0153f52edcd9de824118b48cfb0a929c69fcccd888b7c59918147e"},"schema_version":"1.0"},"canonical_sha256":"34918357d884f5e43f019d74c7d0e10bbb0366aaee1cd9940d76b97086c09dea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:45.393819Z","signature_b64":"HHzy9fWrmpzsQjhcH2kZLtBprIouhMfzi6vIK7GlHe0brY1bfTLJmwUC937UoxvKjoTNNFmdl2Zloht1hTmECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34918357d884f5e43f019d74c7d0e10bbb0366aaee1cd9940d76b97086c09dea","last_reissued_at":"2026-07-05T11:34:45.393301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:45.393301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00151","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":"2026-07-05T11:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66tyZ1Iputaf0GQd4cZhDNW5Fo5PE041lVziWQwutJlJ/649FYUb4o2f10WPzYmbCI2JzqBFq9AR1c3eOmvsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:47:56.286028Z"},"content_sha256":"f6b5c4ac3d246c08c8b63ab7f6a6c322a6a9be1b7a23bf4ba66c2a5bb6494b81","schema_version":"1.0","event_id":"sha256:f6b5c4ac3d246c08c8b63ab7f6a6c322a6a9be1b7a23bf4ba66c2a5bb6494b81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GSIYGV6YQT26IPYBTV2MPUHBBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath, Ser-Nam Lim","submitted_at":"2024-11-29T06:17:11Z","abstract_excerpt":"Document Visual Question Answering (VQA) demands robust integration of text detection, recognition, and spatial reasoning to interpret complex document layouts. In this work, we introduce DLaVA, a novel, training-free pipeline that leverages Multimodal Large Language Models (MLLMs) for zero-shot answer localization in order to improve trustworthiness, interpretability, and explainability. By leveraging an innovative OCR-free approach that organizes text regions with unique bounding box IDs, the proposed method preserves spatial contexts without relying on iterative OCR or chain-of-thought reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00151","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/2412.00151/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":"2026-07-05T11:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPR5ddr8aXWXmbRV77McEmsGb14GzqovHxEA9JaZ3b/Xv2bgGb1MIaLN0w3MuJY16LscSfkbp+Zu0rx2Xd1TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:47:56.286511Z"},"content_sha256":"11bd1c8a2bb0d74f684fd74384f4c87f04dec906bd461a013b7e5703dc1ad782","schema_version":"1.0","event_id":"sha256:11bd1c8a2bb0d74f684fd74384f4c87f04dec906bd461a013b7e5703dc1ad782"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/bundle.json","state_url":"https://pith.science/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/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":"2026-08-08T20:47:56Z","links":{"resolver":"https://pith.science/pith/GSIYGV6YQT26IPYBTV2MPUHBBO","bundle":"https://pith.science/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/bundle.json","state":"https://pith.science/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSIYGV6YQT26IPYBTV2MPUHBBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GSIYGV6YQT26IPYBTV2MPUHBBO","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":"7650bb5abb0153f52edcd9de824118b48cfb0a929c69fcccd888b7c59918147e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T06:17:11Z","title_canon_sha256":"4ef08e515ed21f9ffb014072e32962a8ea76029e273bb0c48e79c138622ecd15"},"schema_version":"1.0","source":{"id":"2412.00151","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00151","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00151v2","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00151","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"GSIYGV6YQT26","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"GSIYGV6YQT26IPYB","created_at":"2026-07-05T11:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"GSIYGV6Y","created_at":"2026-07-05T11:34:45Z"}],"graph_snapshots":[{"event_id":"sha256:11bd1c8a2bb0d74f684fd74384f4c87f04dec906bd461a013b7e5703dc1ad782","target":"graph","created_at":"2026-07-05T11:34:45Z","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/2412.00151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Visual Question Answering (VQA) demands robust integration of text detection, recognition, and spatial reasoning to interpret complex document layouts. In this work, we introduce DLaVA, a novel, training-free pipeline that leverages Multimodal Large Language Models (MLLMs) for zero-shot answer localization in order to improve trustworthiness, interpretability, and explainability. By leveraging an innovative OCR-free approach that organizes text regions with unique bounding box IDs, the proposed method preserves spatial contexts without relying on iterative OCR or chain-of-thought reas","authors_text":"Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath, Ser-Nam Lim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T06:17:11Z","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00151","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:f6b5c4ac3d246c08c8b63ab7f6a6c322a6a9be1b7a23bf4ba66c2a5bb6494b81","target":"record","created_at":"2026-07-05T11:34:45Z","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":"7650bb5abb0153f52edcd9de824118b48cfb0a929c69fcccd888b7c59918147e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T06:17:11Z","title_canon_sha256":"4ef08e515ed21f9ffb014072e32962a8ea76029e273bb0c48e79c138622ecd15"},"schema_version":"1.0","source":{"id":"2412.00151","kind":"arxiv","version":2}},"canonical_sha256":"34918357d884f5e43f019d74c7d0e10bbb0366aaee1cd9940d76b97086c09dea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34918357d884f5e43f019d74c7d0e10bbb0366aaee1cd9940d76b97086c09dea","first_computed_at":"2026-07-05T11:34:45.393301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:45.393301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHzy9fWrmpzsQjhcH2kZLtBprIouhMfzi6vIK7GlHe0brY1bfTLJmwUC937UoxvKjoTNNFmdl2Zloht1hTmECg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:45.393819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00151","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6b5c4ac3d246c08c8b63ab7f6a6c322a6a9be1b7a23bf4ba66c2a5bb6494b81","sha256:11bd1c8a2bb0d74f684fd74384f4c87f04dec906bd461a013b7e5703dc1ad782"],"state_sha256":"537e2f15878a76eaf33ef34c4e5e9ef2be1ed5809f22b720f1397f0e253816e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hca7nqJdhyUrCdnF7YIIikIs6G7di7ya4/ZCD9I9PvchqG6l73C6iUV1E8bqYwM3awYYvGKxGvk2ZJH/ZWygAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:47:56.290995Z","bundle_sha256":"6f5bf23378a4643ced6a25f41dd09729c4e033804654c7b20d0fe958fb1578f5"}}