{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VEJ4LBZ4RMCQ3RTCMPMQEDBI6M","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":"9d0ba279b38a52df0be0d1d81c72f610d26e480e46684c9ecb166a9649a1167d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T15:27:16Z","title_canon_sha256":"d9b049cebc82350ba330cff99dd707b580d3f75c0c739fb75351f9c6aaecd011"},"schema_version":"1.0","source":{"id":"2506.05146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05146","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05146v2","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05146","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"VEJ4LBZ4RMCQ","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"VEJ4LBZ4RMCQ3RTC","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"VEJ4LBZ4","created_at":"2026-07-05T11:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:5740f41401def4bf7911cc717c8d07fee5c5cd10673d217e8ac2408198d6437e","target":"graph","created_at":"2026-07-05T11:24:22Z","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/2506.05146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study their capability regarding object properties and relations in a controlled and interpretable manner. To this scope, we introduce CIVET, a novel and extensible framework for systematiC evaluatIon Via controllEd sTimuli. CIVET addresses the lack of standardized systematic evaluation for assessing VLMs' understanding, enabling researchers to test hypotheses with ","authors_text":"Gabriel Roccabruna, Giuseppe Riccardi, Massimo Rizzoli, Olha Khomyn, Seyed Mahed Mousavi, Simone Alghisi","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T15:27:16Z","title":"CIVET: Systematic Evaluation of Understanding in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05146","kind":"arxiv","version":2},"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":"sha256:63402b12f991da59b80fb4c41cdeca29fe2c306c6c517cb8821e7c3c991196ec","target":"record","created_at":"2026-07-05T11:24:22Z","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":"9d0ba279b38a52df0be0d1d81c72f610d26e480e46684c9ecb166a9649a1167d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T15:27:16Z","title_canon_sha256":"d9b049cebc82350ba330cff99dd707b580d3f75c0c739fb75351f9c6aaecd011"},"schema_version":"1.0","source":{"id":"2506.05146","kind":"arxiv","version":2}},"canonical_sha256":"a913c5873c8b050dc66263d9020c28f32aedb6ae239ed6f4ce0cf34023adc92b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a913c5873c8b050dc66263d9020c28f32aedb6ae239ed6f4ce0cf34023adc92b","first_computed_at":"2026-07-05T11:24:22.112481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:22.112481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ot7Soyt69Eq0TrZwMj/ZNo0BD5siJI/O5G3wg6SugcktWqJrqFHspxCGLoI47+7EyKD+T/FUxpip6g87sa53Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:22.112988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63402b12f991da59b80fb4c41cdeca29fe2c306c6c517cb8821e7c3c991196ec","sha256:5740f41401def4bf7911cc717c8d07fee5c5cd10673d217e8ac2408198d6437e"],"state_sha256":"93d1c94398dc88b54c50c83ba6c94243ee8020275d3fee60d6e675eb449845f4"}