{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OMLEIK4VZFYNX7P2WONTZZPMSF","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":"f50a35db572b894b33f3ac94b5c4cf62a1ab82a83beb0fb975c42a2be1122cc9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T21:56:20Z","title_canon_sha256":"b4a87e32097f7725f6121f3be04ff3600dbab873146fae794a5e6f128c2fca0f"},"schema_version":"1.0","source":{"id":"2408.10433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10433","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10433v1","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10433","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"OMLEIK4VZFYN","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_16","alias_value":"OMLEIK4VZFYNX7P2","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_8","alias_value":"OMLEIK4V","created_at":"2026-07-05T08:57:11Z"}],"graph_snapshots":[{"event_id":"sha256:5bc6c8aabb016563df30d4ec08db20cf452179142b1fffcf3e2a9bd030bd1d1c","target":"graph","created_at":"2026-07-05T08:57:11Z","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/2408.10433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent successes, LVLMs or Large Vision Language Models are prone to hallucinating details like objects and their properties or relations, limiting their real-world deployment. To address this and improve their robustness, we present CLIP-DPO, a preference optimization method that leverages contrastively pre-trained Vision-Language (VL) embedding models, such as CLIP, for DPO-based optimization of LVLMs. Unlike prior works tackling LVLM hallucinations, our method does not rely on paid-for APIs, and does not require additional training data or the deployment of other external LVLMs. Ins","authors_text":"Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos, Yassine Ouali","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T21:56:20Z","title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10433","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":"sha256:5aa93a4ef5172dbdddeabd2a4e1e07baedfb53e66e995446806bcdb7a79245e1","target":"record","created_at":"2026-07-05T08:57:11Z","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":"f50a35db572b894b33f3ac94b5c4cf62a1ab82a83beb0fb975c42a2be1122cc9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T21:56:20Z","title_canon_sha256":"b4a87e32097f7725f6121f3be04ff3600dbab873146fae794a5e6f128c2fca0f"},"schema_version":"1.0","source":{"id":"2408.10433","kind":"arxiv","version":1}},"canonical_sha256":"7316442b95c970dbfdfab39b3ce5ec916cf6b8d569708d975fb9233081c743b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7316442b95c970dbfdfab39b3ce5ec916cf6b8d569708d975fb9233081c743b4","first_computed_at":"2026-07-05T08:57:11.782248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:11.782248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fyAwu1dMtNXpae3bM8jjeXHhH3HVLJbADya9hNLKuJ8cudbggi+KNo1+aBYZjfMxJv719hBg/d7GoZURSrjtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:11.782770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aa93a4ef5172dbdddeabd2a4e1e07baedfb53e66e995446806bcdb7a79245e1","sha256:5bc6c8aabb016563df30d4ec08db20cf452179142b1fffcf3e2a9bd030bd1d1c"],"state_sha256":"a0b35d050b1469c80896d247c2fa3a5b5c2c263f0ded60b9180cf971c376e7ff"}