{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CJUPYM62SS4LQKCKJFLCHBKR73","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":"940e956975999df9caac2c74f7f621587b732db0109ba6363ca381cd45dede45","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T13:34:23Z","title_canon_sha256":"e55504f8311d75cf981e3400c406f7169814140bfb7a26e8f12415ab8f50d923"},"schema_version":"1.0","source":{"id":"2510.09733","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09733","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09733v2","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09733","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"CJUPYM62SS4L","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"CJUPYM62SS4LQKCK","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"CJUPYM62","created_at":"2026-07-29T01:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:10cca68f67eb40fec700fd75243216290c63100245087a1595c821b82f32758b","target":"graph","created_at":"2026-07-29T01:25:29Z","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/2510.09733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Retrieval-Augmented Generation (VRAG) has emerged as a promising paradigm for equipping Vision-Language Models (VLMs) with external visual evidence, enabling them to go beyond parametric knowledge when answering visually grounded questions. However, in such multi-image settings, VLMs still often suffer from visual hallucinations and struggle to accurately identify the question-relevant evidence needed for reliable reasoning. Existing methods usually lack an explicit cross-image evidence collection process, and also provide limited credit assignment when jointly optimizing perception and","authors_text":"Chi Chen, Chunyi Peng, Maosong Sun, Sen Mei, Shi Yu, Yubo Sun, Yukun Yan, Zhenghao Liu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T13:34:23Z","title":"VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09733","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":"sha256:6cb45e855f6efb56385b36f9d14f3708b0f1ad568f1b20442a7e68fd104f5d2b","target":"record","created_at":"2026-07-29T01:25:29Z","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":"940e956975999df9caac2c74f7f621587b732db0109ba6363ca381cd45dede45","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T13:34:23Z","title_canon_sha256":"e55504f8311d75cf981e3400c406f7169814140bfb7a26e8f12415ab8f50d923"},"schema_version":"1.0","source":{"id":"2510.09733","kind":"arxiv","version":2}},"canonical_sha256":"1268fc33da94b8b8284a4956238551fed196ef331b70f8b0ce6b3a5da2c21fee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1268fc33da94b8b8284a4956238551fed196ef331b70f8b0ce6b3a5da2c21fee","first_computed_at":"2026-07-29T01:25:29.663693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:29.663693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WeRAX3aMpoxD89DfF0IFN1kROKF973KnM4LtFnHzQTece5e29hBwMhEMADw1vxipSW0pKekpBy0q7Xk+GayNBQ==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:29.664615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.09733","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cb45e855f6efb56385b36f9d14f3708b0f1ad568f1b20442a7e68fd104f5d2b","sha256:10cca68f67eb40fec700fd75243216290c63100245087a1595c821b82f32758b"],"state_sha256":"cf9394990534b36fc20b3636f89b57bd2accbcb9b5adcf48f405313f2c6f3d6a"}