{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7S5JAHO2JSSE3LL5RJPO6XWLBC","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":"aab3868ab8313be1a5d90700bd79fefc7b42cb712242b03c0c4bd428a429048a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T17:49:44Z","title_canon_sha256":"f4719900f1bb163b6a647f670f6bd38bc2258dbe7a45e9de221235ee64445997"},"schema_version":"1.0","source":{"id":"2309.04461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04461","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04461v2","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04461","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"7S5JAHO2JSSE","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"7S5JAHO2JSSE3LL5","created_at":"2026-07-05T07:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"7S5JAHO2","created_at":"2026-07-05T07:58:23Z"}],"graph_snapshots":[{"event_id":"sha256:ff00b599a7f6c2a5b1e8c710301ef4ba3c7e271db5afdf391709862410cc5a74","target":"graph","created_at":"2026-07-05T07:58:23Z","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/2309.04461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to demonstrate human-like reasoning based on the perceived information. To address a crucial concern regarding the extent to which their reasoning capabilities are fully consistent and grounded, we also measure the reasoning consistency of these models. We achieve this by proposing a chain-of-thought (CoT) based consistency measure. However, such an evaluation r","authors_text":"Ajay Divakaran, Heng Ji, Karan Sikka, Michael Cogswell, Yangyi Chen","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T17:49:44Z","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04461","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":"sha256:8f421c69cc6f175918a777aff3039aac9c97e4c160a3b27e33ad65ec013fd625","target":"record","created_at":"2026-07-05T07:58:23Z","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":"aab3868ab8313be1a5d90700bd79fefc7b42cb712242b03c0c4bd428a429048a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-08T17:49:44Z","title_canon_sha256":"f4719900f1bb163b6a647f670f6bd38bc2258dbe7a45e9de221235ee64445997"},"schema_version":"1.0","source":{"id":"2309.04461","kind":"arxiv","version":2}},"canonical_sha256":"fcba901dda4ca44dad7d8a5eef5ecb08a9ee8ef50afda007280df70e74218923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcba901dda4ca44dad7d8a5eef5ecb08a9ee8ef50afda007280df70e74218923","first_computed_at":"2026-07-05T07:58:23.008629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:23.008629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGqJH++sdPFlBXTnZrG+sMKa6Tgk5+DqZM7aklnZz5dTrJ7xm2lYvHS/3/wtg5OfXiIVBnr5PTCCU6PRdNWEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:23.009146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f421c69cc6f175918a777aff3039aac9c97e4c160a3b27e33ad65ec013fd625","sha256:ff00b599a7f6c2a5b1e8c710301ef4ba3c7e271db5afdf391709862410cc5a74"],"state_sha256":"daf02da95c38fe3999393fe12aca02fd17036cf1d0a2d9d1a03db4d9bdde850f"}