{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NQCRQ7SS53WWSIA4ICKG35CVAK","short_pith_number":"pith:NQCRQ7SS","schema_version":"1.0","canonical_sha256":"6c05187e52eeed69201c40946df45502b4fed49b16cbec68dcb6ab6b00d31215","source":{"kind":"arxiv","id":"2605.15864","version":1},"attestation_state":"computed","paper":{"title":"Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Shui, Cheng Yang, Chufan Shi, Linhao Jin, Taylor Berg-Kirkpatrick, Xuezhe Ma, Yaokang Wu","submitted_at":"2026-05-15T11:31:14Z","abstract_excerpt":"Vision-Language Models (VLMs) often produce self-reflective statements like \"let me check the figure again\" during reasoning. Do such statements trigger genuine visual re-examination, or are they merely learned textual patterns? We investigate this via VisualSwap, an image-swap probing framework: after a model reasons over an image, we replace it with a visually similar but semantically different one and test whether the model notices. We introduce VS-Bench, 800 image pairs curated from MathVista, MathVerse, MathVision, and MMMU-Pro. Experiments on Qwen3-VL, Kimi-VL, and ERNIE-VL reveal a stri"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:31:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38b73dc822a2e665b465a7df570b6035e20eac5e1c5ea02d0d741315d93bcf15","abstract_canon_sha256":"86f3393a6321c6e95043c168947a4e47ab6b310fd626741a982526511807e533"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:22.625302Z","signature_b64":"5qRu83vT3kFjBhmmaoVH0peEfs70CpNFPEIX4QWGbVv1sdomSEGmcePV4u/3TsW2uS69cqQSos+YWvTXuTpABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c05187e52eeed69201c40946df45502b4fed49b16cbec68dcb6ab6b00d31215","last_reissued_at":"2026-05-20T00:01:22.624428Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:22.624428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Shui, Cheng Yang, Chufan Shi, Linhao Jin, Taylor Berg-Kirkpatrick, Xuezhe Ma, Yaokang Wu","submitted_at":"2026-05-15T11:31:14Z","abstract_excerpt":"Vision-Language Models (VLMs) often produce self-reflective statements like \"let me check the figure again\" during reasoning. Do such statements trigger genuine visual re-examination, or are they merely learned textual patterns? We investigate this via VisualSwap, an image-swap probing framework: after a model reasons over an image, we replace it with a visually similar but semantically different one and test whether the model notices. We introduce VS-Bench, 800 image pairs curated from MathVista, MathVerse, MathVision, and MMMU-Pro. Experiments on Qwen3-VL, Kimi-VL, and ERNIE-VL reveal a stri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15864","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15864/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.698655Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.813966Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5a3dd4dca01355e1aa629f19fbadcf82e2b4c0d5cf8154451675ab2b60011127"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15864","created_at":"2026-05-20T00:01:22.624579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15864v1","created_at":"2026-05-20T00:01:22.624579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15864","created_at":"2026-05-20T00:01:22.624579+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQCRQ7SS53WW","created_at":"2026-05-20T00:01:22.624579+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQCRQ7SS53WWSIA4","created_at":"2026-05-20T00:01:22.624579+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQCRQ7SS","created_at":"2026-05-20T00:01:22.624579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK","json":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK.json","graph_json":"https://pith.science/api/pith-number/NQCRQ7SS53WWSIA4ICKG35CVAK/graph.json","events_json":"https://pith.science/api/pith-number/NQCRQ7SS53WWSIA4ICKG35CVAK/events.json","paper":"https://pith.science/paper/NQCRQ7SS"},"agent_actions":{"view_html":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK","download_json":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK.json","view_paper":"https://pith.science/paper/NQCRQ7SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15864&json=true","fetch_graph":"https://pith.science/api/pith-number/NQCRQ7SS53WWSIA4ICKG35CVAK/graph.json","fetch_events":"https://pith.science/api/pith-number/NQCRQ7SS53WWSIA4ICKG35CVAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK/action/storage_attestation","attest_author":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK/action/author_attestation","sign_citation":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK/action/citation_signature","submit_replication":"https://pith.science/pith/NQCRQ7SS53WWSIA4ICKG35CVAK/action/replication_record"}},"created_at":"2026-05-20T00:01:22.624579+00:00","updated_at":"2026-05-20T00:01:22.624579+00:00"}