{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LLQPAT5JLYXNBS4YAVAE622NF","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":"bf258a8230219837a3ad4c537f41327c887dc2477e528584e08591ce30819919","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-07T18:35:54Z","title_canon_sha256":"455294704e75cc6940df84e20d77a42b1c5548dd58089d8cc77c4eb5bc9352e6"},"schema_version":"1.0","source":{"id":"2403.04732","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04732","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04732v3","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04732","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"3LLQPAT5JLYX","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"3LLQPAT5JLYXNBS4","created_at":"2026-07-05T09:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"3LLQPAT5","created_at":"2026-07-05T09:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:798349a71f1db742cef8022ad08018685484e536e06409d0fdf49fa6ffaf4c3d","target":"graph","created_at":"2026-07-05T09:13:50Z","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/2403.04732/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 incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed blindspots in the current SOTA VLMs. Specifically, we leverage Raven's Progressive Matrices (RPMs), to assess VLMs' abilities to perform multi-hop relational and deductive reasoning relying solely on visual clues. We perform comprehensive evaluations of several popular VLMs employing standard strategies such as in-context learning, self-consistency, and Chain-of-tho","authors_text":"He Bai, Jiatao Gu, Josh Susskind, Navdeep Jaitly, Ruixiang Zhang, Shuangfei Zhai, Yizhe Zhang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-07T18:35:54Z","title":"How Far Are We from Intelligent Visual Deductive Reasoning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04732","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":"sha256:22cdcd3cf530a9906a881b33ca654b7a616885c19e18d83999867bc1f660dc85","target":"record","created_at":"2026-07-05T09:13:50Z","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":"bf258a8230219837a3ad4c537f41327c887dc2477e528584e08591ce30819919","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-07T18:35:54Z","title_canon_sha256":"455294704e75cc6940df84e20d77a42b1c5548dd58089d8cc77c4eb5bc9352e6"},"schema_version":"1.0","source":{"id":"2403.04732","kind":"arxiv","version":3}},"canonical_sha256":"dad707827d4af176865cc02a027b5a6945d09c2cdf5bba35c2b403f4060db6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad707827d4af176865cc02a027b5a6945d09c2cdf5bba35c2b403f4060db6a7","first_computed_at":"2026-07-05T09:13:50.483024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:50.483024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3aNRs0BbLvDQgHX1pSvk+sBNOYZ2as3LC/bxINTvGOkv2llweaC9pELqPd2j8219US7gsV+5VMSqO+EqgXYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:50.483452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04732","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22cdcd3cf530a9906a881b33ca654b7a616885c19e18d83999867bc1f660dc85","sha256:798349a71f1db742cef8022ad08018685484e536e06409d0fdf49fa6ffaf4c3d"],"state_sha256":"9543725148d7677269b3ee6852dcc6b592efb514c962581acae5ce7ae3f9adbe"}