{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TMV55LEK5NFHIIXBMYWELEL47T","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":"632c10731c896d421678576382cfffebf9fb7a96867c30e62c377be64e86960c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T17:09:44Z","title_canon_sha256":"e85b0eedd279d357df9d74ec7365f5cfe1fd26003749935c3c6104b0d1276039"},"schema_version":"1.0","source":{"id":"2506.22395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22395","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22395v1","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22395","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"TMV55LEK5NFH","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"TMV55LEK5NFHIIXB","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"TMV55LEK","created_at":"2026-07-05T11:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:c95bd9549ab0d749ee458671d7897e90734f2ed95a6da0f648a8ed880baad52b","target":"graph","created_at":"2026-07-05T11:28:26Z","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/2506.22395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and robustness. Recent benchmarks, such as MM-R3, highlight that even state-of-the-art VLMs can produce divergent predictions across semantically equivalent inputs, despite maintaining high average accuracy. Prior work addresses this issue by modifying model architectures or conducting large-scale fine-tuning on curated datasets. In contrast, we propose a simple and ","authors_text":"James J. Little, Leonid Sigal, Shih-Han Chou, Shivam Chandhok","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T17:09:44Z","title":"Test-Time Consistency in Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22395","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":"sha256:44591e84d9323cce7975adb6c8f887868df6f1cea6e2c0b960faf6c9e3757034","target":"record","created_at":"2026-07-05T11:28:26Z","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":"632c10731c896d421678576382cfffebf9fb7a96867c30e62c377be64e86960c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T17:09:44Z","title_canon_sha256":"e85b0eedd279d357df9d74ec7365f5cfe1fd26003749935c3c6104b0d1276039"},"schema_version":"1.0","source":{"id":"2506.22395","kind":"arxiv","version":1}},"canonical_sha256":"9b2bdeac8aeb4a7422e1662c45917cfcd8abe9fbf5ba934c3b935f1c457a01a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b2bdeac8aeb4a7422e1662c45917cfcd8abe9fbf5ba934c3b935f1c457a01a7","first_computed_at":"2026-07-05T11:28:26.733004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:26.733004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Q076r3OdpiO1hwNnaq2SOLdODyvP2plWy+Yovd5y559yZY9hrnONd4r1hcgoLGsYW7XMmXdKPALkdPN8DusBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:26.733486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44591e84d9323cce7975adb6c8f887868df6f1cea6e2c0b960faf6c9e3757034","sha256:c95bd9549ab0d749ee458671d7897e90734f2ed95a6da0f648a8ed880baad52b"],"state_sha256":"bcc9a19c2f41f78fb38fde10e3ffc8e0cedeca08fda25d663a2216b28f888fbb"}