{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:23CI3LEOVWIAVPIAN2OU5BG67T","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":"1de58fb383e6c75c187e54e14ca903815ad05507e6bf991b12a8eea73d637f5d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T00:45:25Z","title_canon_sha256":"d7686646e4b04db14d1cf5f017ad90e2b8bafea701d7627639cc6fa8b65bb28c"},"schema_version":"1.0","source":{"id":"2605.30698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30698","created_at":"2026-06-01T01:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30698v1","created_at":"2026-06-01T01:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30698","created_at":"2026-06-01T01:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"23CI3LEOVWIA","created_at":"2026-06-01T01:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"23CI3LEOVWIAVPIA","created_at":"2026-06-01T01:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"23CI3LEO","created_at":"2026-06-01T01:03:09Z"}],"graph_snapshots":[{"event_id":"sha256:5246bddab35dafb74bbbc0e75e278aa73829acd9730c4b453c835926d300c850","target":"graph","created_at":"2026-06-01T01:03:09Z","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/2605.30698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising paradigm. While this approach has shown great success in textual QA, its potential in the multimodal domain remains under-explored. Existing multi-agent VQA methods predominantly adapt text-centric protocols, focusing on textual discussions while ignoring the alignment of visual information. In this work, we reveal a key insight: answer-level agreement i","authors_text":"Dongsheng Ma, Shaoxu Sun, Shuochen Chang, Wentao Zhang, Yalin Feng, Yikang Wang, Yinglong Yang, Yuanzi Li, Yufei Chen, Yuhan Wang, Zhengren Wang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T00:45:25Z","title":"Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30698","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":"sha256:8bfbdf8bc662289529e78613902473dabdc20b05cbb237791ae1e25d589a831f","target":"record","created_at":"2026-06-01T01:03:09Z","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":"1de58fb383e6c75c187e54e14ca903815ad05507e6bf991b12a8eea73d637f5d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T00:45:25Z","title_canon_sha256":"d7686646e4b04db14d1cf5f017ad90e2b8bafea701d7627639cc6fa8b65bb28c"},"schema_version":"1.0","source":{"id":"2605.30698","kind":"arxiv","version":1}},"canonical_sha256":"d6c48dac8ead900abd006e9d4e84defcd81b302d8067c42ee82c6295a14c3050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6c48dac8ead900abd006e9d4e84defcd81b302d8067c42ee82c6295a14c3050","first_computed_at":"2026-06-01T01:03:09.114332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:09.114332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HBi8gL6v090ksWC0H8sPyLz8FP+KjDMsMwTIgLVaEsTPCLw37wLrWcngTcxlb2EfFgURgiAunoNBNekL1N69BA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:09.115001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bfbdf8bc662289529e78613902473dabdc20b05cbb237791ae1e25d589a831f","sha256:5246bddab35dafb74bbbc0e75e278aa73829acd9730c4b453c835926d300c850"],"state_sha256":"708925c15bc709894c95e8b271658235f684ef9db02be13b860c883fc961578e"}