{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UGZFGCY6D2XO4UODSXMBNHMLLH","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":"18eae828d7527feca0e8a1658a10293ca52ca98ffdf843b53467d58fcd5b16ab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-12T17:15:45Z","title_canon_sha256":"9030ccefcfbcbe70dda6115786d5c41267d2c21545f0c2c5ea71e055a6775abd"},"schema_version":"1.0","source":{"id":"2601.07737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.07737","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.07737v2","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07737","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"UGZFGCY6D2XO","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"UGZFGCY6D2XO4UOD","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"UGZFGCY6","created_at":"2026-05-27T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:5a85373afaaa71e00b8c3e8385224ed14cb4a9de411820762cc81688e2b0ea61","target":"graph","created_at":"2026-05-27T01:05:42Z","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/2601.07737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in mainstream visual understanding tasks, but their ability to process action scenes that contradict everyday common sense remains undertested. To address this gap, we introduce CAIT, a benchmark comprising 400 high-fidelity synthetic scenes focused on counter-intuitive visual actions, such as ``a rabbit is chasing a tiger'', where visual evidence explicitly contradicts common-sense expectations. We evaluate human, leading proprietary models (e.g., Claude and Gemini), and 14 representative open-source MLLMs. Huma","authors_text":"Chen Ling, Hanqian Li, Nai Ding, Tongwei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-12T17:15:45Z","title":"Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07737","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":"sha256:41f082834adc0eebe5b1a5942d48c4e213c31435ef0feea9255981cd1b04be05","target":"record","created_at":"2026-05-27T01:05:42Z","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":"18eae828d7527feca0e8a1658a10293ca52ca98ffdf843b53467d58fcd5b16ab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-12T17:15:45Z","title_canon_sha256":"9030ccefcfbcbe70dda6115786d5c41267d2c21545f0c2c5ea71e055a6775abd"},"schema_version":"1.0","source":{"id":"2601.07737","kind":"arxiv","version":2}},"canonical_sha256":"a1b2530b1e1eaeee51c395d8169d8b59f1ea0c8e862692cbc226f3e718de1f48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1b2530b1e1eaeee51c395d8169d8b59f1ea0c8e862692cbc226f3e718de1f48","first_computed_at":"2026-05-27T01:05:42.417708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:42.417708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lGGftLnef5Hq3u+qRgVwOhjpoCR+7VY/mVSE58pMzERlhUEdJ5L1ElDl/P1zhz/tnD4zRBmFiPAOTNDiqldFCg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:42.418469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.07737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41f082834adc0eebe5b1a5942d48c4e213c31435ef0feea9255981cd1b04be05","sha256:5a85373afaaa71e00b8c3e8385224ed14cb4a9de411820762cc81688e2b0ea61"],"state_sha256":"52f88eaa03678aa9ceb381bbc633c36db66c2edbc01864f77c6c9920743a0da3"}