{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NJVJJDOV5EPCDZXOBD3HPG3GIR","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":"0369cff2b46dfc98f73941001b6b470924691358df0aba2931e2bdb02bcc9de3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T13:44:56Z","title_canon_sha256":"2e876e60467288a297a5abf8412eddf1442c165e4d863b812e52882bb6333556"},"schema_version":"1.0","source":{"id":"2605.31312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31312","created_at":"2026-06-01T01:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31312v1","created_at":"2026-06-01T01:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31312","created_at":"2026-06-01T01:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"NJVJJDOV5EPC","created_at":"2026-06-01T01:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"NJVJJDOV5EPCDZXO","created_at":"2026-06-01T01:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"NJVJJDOV","created_at":"2026-06-01T01:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:ddc5936893c81192822495e8c3dc997be94ff946ff677aab7dfb575cca72aa22","target":"graph","created_at":"2026-06-01T01:04:10Z","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/2605.31312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often fails to mitigate it due to a lack of explicit visual supervision. While existing works introduce visual preference DPO by contrasting original images against negative ones, they suffer from a theoretically inconsistent objective caused by partition function mismatches and rely on coarse-grained negatives that could enable shortcut learning. In this work, we propose In-Context Visual Contrastive Optimization (IC-VCO). By placing contrastive imag","authors_text":"Chen Chen, Haolin Deng, Haonan Lu, Xin Zou, Xuming Hu, Zhiwei Jin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T13:44:56Z","title":"Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31312","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":"sha256:468ad7ae28599dbf6120039a6b7b599f2ce3c111de0d6027d7e8fe47924bcef4","target":"record","created_at":"2026-06-01T01:04:10Z","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":"0369cff2b46dfc98f73941001b6b470924691358df0aba2931e2bdb02bcc9de3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T13:44:56Z","title_canon_sha256":"2e876e60467288a297a5abf8412eddf1442c165e4d863b812e52882bb6333556"},"schema_version":"1.0","source":{"id":"2605.31312","kind":"arxiv","version":1}},"canonical_sha256":"6a6a948dd5e91e21e6ee08f6779b66447bd8f9cb7a04d4e7e49d84cade664607","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6a948dd5e91e21e6ee08f6779b66447bd8f9cb7a04d4e7e49d84cade664607","first_computed_at":"2026-06-01T01:04:10.330957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:10.330957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TSx/EYjrpDr3SzmdPGvF3JCRJlIcfI6+Ju4mBMH9+AEmh3c5QuxvlsuBbu0r25D/56L1TW7PiMNq2zUGPTt7Bg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:10.331591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:468ad7ae28599dbf6120039a6b7b599f2ce3c111de0d6027d7e8fe47924bcef4","sha256:ddc5936893c81192822495e8c3dc997be94ff946ff677aab7dfb575cca72aa22"],"state_sha256":"0d53313b6ba9732cea9d2a2c7fd72d76d2daa52fe8168f39d60bd8f5862b55aa"}