{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B7A6DTJJBHY32HYGZNGQ6CBKMD","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":"cdbaa4efa1cd368137545686e055d129c00bccee915951a58a83f17abd9c71db","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T17:35:04Z","title_canon_sha256":"43e2b10bc66e7716d03acffde29e0916315107cb7e0aac36ce9e7b21101219be"},"schema_version":"1.0","source":{"id":"2605.22903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22903","created_at":"2026-05-25T02:01:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22903v1","created_at":"2026-05-25T02:01:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22903","created_at":"2026-05-25T02:01:29Z"},{"alias_kind":"pith_short_12","alias_value":"B7A6DTJJBHY3","created_at":"2026-05-25T02:01:29Z"},{"alias_kind":"pith_short_16","alias_value":"B7A6DTJJBHY32HYG","created_at":"2026-05-25T02:01:29Z"},{"alias_kind":"pith_short_8","alias_value":"B7A6DTJJ","created_at":"2026-05-25T02:01:29Z"}],"graph_snapshots":[{"event_id":"sha256:fb108c20af46530c8bf8ec4761e9ff8919baa6a31fe02791506813247827fbe4","target":"graph","created_at":"2026-05-25T02:01:29Z","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/2605.22903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising observation that removing a substantial fraction of image tokens only degrades model performance very slightly on a widely used hallucination benchmark, we systematically investigate this mismatch in a set of open-source VLMs. Our analysis spans multiple levels of granularity, spanning global visual degradation, localized occlusion, question reformulation, ","authors_text":"Jiawei Zhou, Luzhe Sun, Matthew R. Walter, Zixuan Lan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T17:35:04Z","title":"Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22903","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:fbd11e9865d011a379995efd9c24d1f3b69b8d791b7b09387c9c35d2a51a4614","target":"record","created_at":"2026-05-25T02:01:29Z","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":"cdbaa4efa1cd368137545686e055d129c00bccee915951a58a83f17abd9c71db","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T17:35:04Z","title_canon_sha256":"43e2b10bc66e7716d03acffde29e0916315107cb7e0aac36ce9e7b21101219be"},"schema_version":"1.0","source":{"id":"2605.22903","kind":"arxiv","version":1}},"canonical_sha256":"0fc1e1cd2909f1bd1f06cb4d0f082a60ea35f9a30a7de7b6ff5bd56eb20a9393","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fc1e1cd2909f1bd1f06cb4d0f082a60ea35f9a30a7de7b6ff5bd56eb20a9393","first_computed_at":"2026-05-25T02:01:29.319099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:29.319099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gt/HGOf2r0Vv4s84arMCGb/kDzHMN/kFn6iUysz5+QD2Z00bSp+ATGF7FQPBfc6rnIQjlyTdN6+beIyJLNUrDA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:29.319773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbd11e9865d011a379995efd9c24d1f3b69b8d791b7b09387c9c35d2a51a4614","sha256:fb108c20af46530c8bf8ec4761e9ff8919baa6a31fe02791506813247827fbe4"],"state_sha256":"10bd63c18a54c66c5e4b226390d684a9e2bfddad13c6f6158e90e5fc5e887a0a"}