{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VLIURWWPU3LV4KKGCYLU3NGDC6","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":"317b2681e5c99a11bceb6c96ed2797904ced183f6cab0af5ddd672b03f6eaaf9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T01:19:18Z","title_canon_sha256":"84bb91261ce46c8d7ad175fe17c8d9430357fd7c0aa1eace9421f6996ee368cf"},"schema_version":"1.0","source":{"id":"2410.13121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13121","created_at":"2026-07-05T09:21:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13121v1","created_at":"2026-07-05T09:21:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13121","created_at":"2026-07-05T09:21:55Z"},{"alias_kind":"pith_short_12","alias_value":"VLIURWWPU3LV","created_at":"2026-07-05T09:21:55Z"},{"alias_kind":"pith_short_16","alias_value":"VLIURWWPU3LV4KKG","created_at":"2026-07-05T09:21:55Z"},{"alias_kind":"pith_short_8","alias_value":"VLIURWWP","created_at":"2026-07-05T09:21:55Z"}],"graph_snapshots":[{"event_id":"sha256:69260bc1a4207e0acd47217b324ceac78236a3c5ffeeab4f350549925aefc7f0","target":"graph","created_at":"2026-07-05T09:21:55Z","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/2410.13121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form responses to open-ended queries is challenging as it requires visually verifying each claim within the response. We propose Programmatic VLM Evaluation (PROVE), a new benchmarking paradigm for evaluating VLM responses to open-ended queries. To construct PROVE, we provide a large language model (LLM) with a high-fidelity scene-graph representation constructed from a hyper-detailed image caption, and prompt it to generate d","authors_text":"An Yan, Caiming Xiong, Ran Xu, Senthil Purushwalkam, Viraj Prabhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T01:19:18Z","title":"Trust but Verify: Programmatic VLM Evaluation in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13121","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:adce561a6a4f0fbe22e8efc143d983012cef1ecbfa007d7e9bd244aa4b8cc2e9","target":"record","created_at":"2026-07-05T09:21:55Z","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":"317b2681e5c99a11bceb6c96ed2797904ced183f6cab0af5ddd672b03f6eaaf9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T01:19:18Z","title_canon_sha256":"84bb91261ce46c8d7ad175fe17c8d9430357fd7c0aa1eace9421f6996ee368cf"},"schema_version":"1.0","source":{"id":"2410.13121","kind":"arxiv","version":1}},"canonical_sha256":"aad148dacfa6d75e294616174db4c317a0463577c6578f5b0c18e7e59d5d0eef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aad148dacfa6d75e294616174db4c317a0463577c6578f5b0c18e7e59d5d0eef","first_computed_at":"2026-07-05T09:21:55.857909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:55.857909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXfGWNOiUhwzLLeD7M84dWkG9hFd0R9LnUdM/JKZ660N5Epw4sqxo9WJBLPOFxjaky4syzKrNdDuzZszfaRrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:55.858479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adce561a6a4f0fbe22e8efc143d983012cef1ecbfa007d7e9bd244aa4b8cc2e9","sha256:69260bc1a4207e0acd47217b324ceac78236a3c5ffeeab4f350549925aefc7f0"],"state_sha256":"db788ca424d5fa77068b84bc4f56abf728d55f9140146f71086d23e3070d5f54"}