{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKMZJYJF36DCRZOVGRZLK7WR2S","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":"da3369b2c41a26d1fc56796c6afc4661487ef47657e57f4b45abf807f6aab2a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T17:00:29Z","title_canon_sha256":"b8c60bdbb3b0354879f98eb50c732eb9a7f96e37377d2f03e970029b4ba14a64"},"schema_version":"1.0","source":{"id":"2407.07840","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07840","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07840v3","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07840","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"AKMZJYJF36DC","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"AKMZJYJF36DCRZOV","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"AKMZJYJF","created_at":"2026-07-05T09:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:1272cb7528c17004acfb0b76313de1706873770e6fa989ab3a237ecdc8aff7e6","target":"graph","created_at":"2026-07-05T09:17:45Z","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/2407.07840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite tremendous advancements, current state-of-the-art Vision-Language Models (VLMs) are still far from perfect. They tend to hallucinate and may generate biased responses. In such circumstances, having a way to assess the reliability of a given response generated by a VLM is quite useful. Existing methods, such as estimating uncertainty using answer likelihoods or prompt-based confidence generation, often suffer from overconfidence. Other methods use self-consistency comparison but are affected by confirmation biases. To alleviate these, we propose Decompose and Compare Consistency (DeCC) ","authors_text":"Aishwarya Agrawal, Qian Yang, Weixiang Yan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T17:00:29Z","title":"Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07840","kind":"arxiv","version":3},"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":"sha256:46cf6336599f4526d032d440c5e4f40385848cad7ff39472a9c0520f21516f8d","target":"record","created_at":"2026-07-05T09:17:45Z","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":"da3369b2c41a26d1fc56796c6afc4661487ef47657e57f4b45abf807f6aab2a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T17:00:29Z","title_canon_sha256":"b8c60bdbb3b0354879f98eb50c732eb9a7f96e37377d2f03e970029b4ba14a64"},"schema_version":"1.0","source":{"id":"2407.07840","kind":"arxiv","version":3}},"canonical_sha256":"029994e125df8628e5d53472b57ed1d4b0b3997017f6f96d8e7817c890e316ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"029994e125df8628e5d53472b57ed1d4b0b3997017f6f96d8e7817c890e316ca","first_computed_at":"2026-07-05T09:17:45.708118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:45.708118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4LBrd0clf8RAVyOwQV2ArXIB9U0odKMzhpAsgHmqmBn8NmmHO4mMn35CWEl8swmxP9mZqnfJHn/btWE0wnGCAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:45.708657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07840","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46cf6336599f4526d032d440c5e4f40385848cad7ff39472a9c0520f21516f8d","sha256:1272cb7528c17004acfb0b76313de1706873770e6fa989ab3a237ecdc8aff7e6"],"state_sha256":"1f8f9a30f0664f6231be4634fdc04406ec95f1429e6c0c409c90b199b9fbbe34"}