{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B5ZHZSXGU3XNEJR4GI56MJZ6RV","short_pith_number":"pith:B5ZHZSXG","schema_version":"1.0","canonical_sha256":"0f727ccae6a6eed2263c323be6273e8d749e1417204f61d4e80c5c9790a73bc6","source":{"kind":"arxiv","id":"2607.24651","version":1},"attestation_state":"computed","paper":{"title":"Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Yao Zhang, Yu Xiao, Zhuchenyang Liu","submitted_at":"2026-07-27T16:49:36Z","abstract_excerpt":"Reliable visual document understanding requires a model to attribute each answer to the evidence regions that support it. Recent benchmarks and systems express this step through a coordinate interface: the model outputs the coordinates of bounding boxes that mark the evidence regions in the document. Under this interface, vision-language models often fail to identify the right regions even when the answer is correct, a failure known as Attribution Hallucination. We present a study that investigates whether this failure is partially limited by what the model can express through coordinates. On "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.24651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T16:49:36Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"3acf86ebe59578a9aca16d830772b732e6ca766640e4c4310f7b23f8f9e2fd33","abstract_canon_sha256":"65634e4f207dbea85908e6719eb574afb82bf328db41d4c6cc45bb9f26273870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:20.746847Z","signature_b64":"01Z8TGUOBwX9qD4RoM5Q6OQdHRXnis8rq9VYc09A1eKIXdHV49E5b6652H1zXwmO1121h2GYIctZDuYmv6R6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f727ccae6a6eed2263c323be6273e8d749e1417204f61d4e80c5c9790a73bc6","last_reissued_at":"2026-07-28T02:24:20.745982Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:20.745982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Yao Zhang, Yu Xiao, Zhuchenyang Liu","submitted_at":"2026-07-27T16:49:36Z","abstract_excerpt":"Reliable visual document understanding requires a model to attribute each answer to the evidence regions that support it. Recent benchmarks and systems express this step through a coordinate interface: the model outputs the coordinates of bounding boxes that mark the evidence regions in the document. Under this interface, vision-language models often fail to identify the right regions even when the answer is correct, a failure known as Attribution Hallucination. We present a study that investigates whether this failure is partially limited by what the model can express through coordinates. On "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24651","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/2607.24651/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24651","created_at":"2026-07-28T02:24:20.746430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24651v1","created_at":"2026-07-28T02:24:20.746430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24651","created_at":"2026-07-28T02:24:20.746430+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5ZHZSXGU3XN","created_at":"2026-07-28T02:24:20.746430+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5ZHZSXGU3XNEJR4","created_at":"2026-07-28T02:24:20.746430+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5ZHZSXG","created_at":"2026-07-28T02:24:20.746430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV","json":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV.json","graph_json":"https://pith.science/api/pith-number/B5ZHZSXGU3XNEJR4GI56MJZ6RV/graph.json","events_json":"https://pith.science/api/pith-number/B5ZHZSXGU3XNEJR4GI56MJZ6RV/events.json","paper":"https://pith.science/paper/B5ZHZSXG"},"agent_actions":{"view_html":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV","download_json":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV.json","view_paper":"https://pith.science/paper/B5ZHZSXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24651&json=true","fetch_graph":"https://pith.science/api/pith-number/B5ZHZSXGU3XNEJR4GI56MJZ6RV/graph.json","fetch_events":"https://pith.science/api/pith-number/B5ZHZSXGU3XNEJR4GI56MJZ6RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV/action/storage_attestation","attest_author":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV/action/author_attestation","sign_citation":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV/action/citation_signature","submit_replication":"https://pith.science/pith/B5ZHZSXGU3XNEJR4GI56MJZ6RV/action/replication_record"}},"created_at":"2026-07-28T02:24:20.746430+00:00","updated_at":"2026-07-28T02:24:20.746430+00:00"}