{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RXKEBUEL2NWMWNKBGWN2GU3XRO","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":"04a709f127ff18f618693da008a494d6e3768cb9a9e8607c415c86e307526448","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T22:52:34Z","title_canon_sha256":"3051db0db20e7dcc7f1b613603abff087992b4954869baf3f4bcd8147a4b8909"},"schema_version":"1.0","source":{"id":"2607.26326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26326","created_at":"2026-07-30T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26326v1","created_at":"2026-07-30T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26326","created_at":"2026-07-30T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"RXKEBUEL2NWM","created_at":"2026-07-30T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"RXKEBUEL2NWMWNKB","created_at":"2026-07-30T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"RXKEBUEL","created_at":"2026-07-30T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:17536b1587718e16ac85ee9b29703775b94194afb7362e3fc0786074ab7a7f0d","target":"graph","created_at":"2026-07-30T01:18:02Z","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/2607.26326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge. We explore these failures separately using two diagnostic paradigms: (1) probing whether visual information is available, via image reconstruction, and (2) measuring multimodal context sensitivity, the extent to which the model follows visual context versus the language prior. To support the second, we introduce the WhatIfVis, a b","authors_text":"Chengzu Li, Jiaang Li, Serge Belongie, V\\'esteinn Sn{\\ae}bjarnarson, Xi Liu, Yifei Yuan, Zhaochong An","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T22:52:34Z","title":"Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26326","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":"sha256:192bd1fe44fe179c0f0efd8b4627b62a0fb9eb996984cacb6375b544ccfbaf2d","target":"record","created_at":"2026-07-30T01:18:02Z","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":"04a709f127ff18f618693da008a494d6e3768cb9a9e8607c415c86e307526448","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T22:52:34Z","title_canon_sha256":"3051db0db20e7dcc7f1b613603abff087992b4954869baf3f4bcd8147a4b8909"},"schema_version":"1.0","source":{"id":"2607.26326","kind":"arxiv","version":1}},"canonical_sha256":"8dd440d08bd36ccb3541359ba353778bb827ddb4398ab2776dcafc4c1b663547","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dd440d08bd36ccb3541359ba353778bb827ddb4398ab2776dcafc4c1b663547","first_computed_at":"2026-07-30T01:18:02.531789Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:18:02.531789Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:192bd1fe44fe179c0f0efd8b4627b62a0fb9eb996984cacb6375b544ccfbaf2d","sha256:17536b1587718e16ac85ee9b29703775b94194afb7362e3fc0786074ab7a7f0d"],"state_sha256":"7f663fc6a6acce2409a3e544320e781124b0caa96aa5522f08c814b0c9050075"}