{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NJVJJDOV5EPCDZXOBD3HPG3GIR","short_pith_number":"pith:NJVJJDOV","canonical_record":{"source":{"id":"2605.31312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T13:44:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2e876e60467288a297a5abf8412eddf1442c165e4d863b812e52882bb6333556","abstract_canon_sha256":"0369cff2b46dfc98f73941001b6b470924691358df0aba2931e2bdb02bcc9de3"},"schema_version":"1.0"},"canonical_sha256":"6a6a948dd5e91e21e6ee08f6779b66447bd8f9cb7a04d4e7e49d84cade664607","source":{"kind":"arxiv","id":"2605.31312","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NJVJJDOV5EPCDZXOBD3HPG3GIR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.31312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T13:44:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2e876e60467288a297a5abf8412eddf1442c165e4d863b812e52882bb6333556","abstract_canon_sha256":"0369cff2b46dfc98f73941001b6b470924691358df0aba2931e2bdb02bcc9de3"},"schema_version":"1.0"},"canonical_sha256":"6a6a948dd5e91e21e6ee08f6779b66447bd8f9cb7a04d4e7e49d84cade664607","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:10.331591Z","signature_b64":"TSx/EYjrpDr3SzmdPGvF3JCRJlIcfI6+Ju4mBMH9+AEmh3c5QuxvlsuBbu0r25D/56L1TW7PiMNq2zUGPTt7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6a948dd5e91e21e6ee08f6779b66447bd8f9cb7a04d4e7e49d84cade664607","last_reissued_at":"2026-06-01T01:04:10.330957Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:10.330957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.31312","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mz2Pd6cN9oVpal2LCVRit4ZJuTj9d5ZgHD1D5LV5HG6ysrIERGiYDFxoDd16l2ZRx5x+iJujND8OUoRMnJD4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:27:09.607589Z"},"content_sha256":"468ad7ae28599dbf6120039a6b7b599f2ce3c111de0d6027d7e8fe47924bcef4","schema_version":"1.0","event_id":"sha256:468ad7ae28599dbf6120039a6b7b599f2ce3c111de0d6027d7e8fe47924bcef4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NJVJJDOV5EPCDZXOBD3HPG3GIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen Chen, Haolin Deng, Haonan Lu, Xin Zou, Xuming Hu, Zhiwei Jin","submitted_at":"2026-05-29T13:44:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31312","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.31312/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SqI40c3RF/vuVfAV4lAKJPOgzVhNbkHeY632kRp5N4fjnb3czqQ5Oey/fJflYvV75IqQNKBBlfF6tNKeZqMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:27:09.607968Z"},"content_sha256":"ddc5936893c81192822495e8c3dc997be94ff946ff677aab7dfb575cca72aa22","schema_version":"1.0","event_id":"sha256:ddc5936893c81192822495e8c3dc997be94ff946ff677aab7dfb575cca72aa22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/bundle.json","state_url":"https://pith.science/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T13:27:09Z","links":{"resolver":"https://pith.science/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR","bundle":"https://pith.science/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/bundle.json","state":"https://pith.science/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJVJJDOV5EPCDZXOBD3HPG3GIR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pVxEqmOKbzw4EI/dIngN8iupYxn7vSelO03ZVOXlUNxx++zeqzTs1lpK9Rte+CCY5OLejwpxownNzb3Gb+WKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T13:27:09.609973Z","bundle_sha256":"fe37a695b6ed0d180dd13860333a5facdba61e94181b1dab0413d721c7d46988"}}