{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYWUEZUWDBF7RDVLLGG67JORDR","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":"6401117bf8be9ccb420d807b3325308cd3d88daa3bbc5441b516935360dec324","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T12:46:51Z","title_canon_sha256":"d6212a03bb01e6c0d7978124b8306038302410e1a2fdfc5b389bdda936dd2af4"},"schema_version":"1.0","source":{"id":"2507.17467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17467","created_at":"2026-07-05T11:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17467v1","created_at":"2026-07-05T11:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17467","created_at":"2026-07-05T11:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"XYWUEZUWDBF7","created_at":"2026-07-05T11:42:08Z"},{"alias_kind":"pith_short_16","alias_value":"XYWUEZUWDBF7RDVL","created_at":"2026-07-05T11:42:08Z"},{"alias_kind":"pith_short_8","alias_value":"XYWUEZUW","created_at":"2026-07-05T11:42:08Z"}],"graph_snapshots":[{"event_id":"sha256:07d7a59789695f4b10fd19553cdff3f45b9c22149e03c9cc6edb99af2b2b58a0","target":"graph","created_at":"2026-07-05T11:42:08Z","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/2507.17467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates the extent to which the Visual Entailment (VE) task serves as a reliable probe of vision-language understanding in multimodal language models, using the LLaMA 3.2 11B Vision model as a test case. Beyond reporting performance metrics, we aim to interpret what these results reveal about the underlying possibilities and limitations of the VE task. We conduct a series of experiments across zero-shot, few-shot, and fine-tuning settings, exploring how factors such as prompt design, the number and order of in-context examples and access to visual information might affect VE pe","authors_text":"Elena Pitta, Tessa Verhoef, Tom Kouwenhoven","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T12:46:51Z","title":"Probing Vision-Language Understanding through the Visual Entailment Task: promises and pitfalls"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17467","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":"sha256:0a5e959fd9e37dec57b9b846ebe6eee1cde9328f8f2d7e80fed26d3922348a9a","target":"record","created_at":"2026-07-05T11:42:08Z","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":"6401117bf8be9ccb420d807b3325308cd3d88daa3bbc5441b516935360dec324","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T12:46:51Z","title_canon_sha256":"d6212a03bb01e6c0d7978124b8306038302410e1a2fdfc5b389bdda936dd2af4"},"schema_version":"1.0","source":{"id":"2507.17467","kind":"arxiv","version":1}},"canonical_sha256":"be2d426696184bf88eab598defa5d11c722f6c1edc5e53256baee727b86b5d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be2d426696184bf88eab598defa5d11c722f6c1edc5e53256baee727b86b5d20","first_computed_at":"2026-07-05T11:42:08.345666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:08.345666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"As7unOdEQsp2RehA7w2oaOC/di61l5ePJhNjbZ3+buhojB/RlpBYZ2RV7OBmPiVQQUwAw6OXvGSn9EmRkH3WBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:08.346159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5e959fd9e37dec57b9b846ebe6eee1cde9328f8f2d7e80fed26d3922348a9a","sha256:07d7a59789695f4b10fd19553cdff3f45b9c22149e03c9cc6edb99af2b2b58a0"],"state_sha256":"da31e1a03ee95c4e589b0c015a9ad340bd111a9fd81d118ac1dc507ed8f207a5"}