{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K7NA5V4VOV2E74WULNJMUUJVUJ","short_pith_number":"pith:K7NA5V4V","canonical_record":{"source":{"id":"2411.02712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T01:24:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1472a6c00544cdcfdc08d20e345f4450e8cdc651309a27b0dae42bce561f52f8","abstract_canon_sha256":"9c55fa359f4ffda117b25d4234796fb915fe30eebad837422d08f75f57e41638"},"schema_version":"1.0"},"canonical_sha256":"57da0ed79575744ff2d45b52ca5135a271aa7bf5a1bb770652ef3e108e5c441c","source":{"kind":"arxiv","id":"2411.02712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02712","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02712v1","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02712","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_12","alias_value":"K7NA5V4VOV2E","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_16","alias_value":"K7NA5V4VOV2E74WU","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_8","alias_value":"K7NA5V4V","created_at":"2026-07-05T09:31:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K7NA5V4VOV2E74WULNJMUUJVUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T01:24:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1472a6c00544cdcfdc08d20e345f4450e8cdc651309a27b0dae42bce561f52f8","abstract_canon_sha256":"9c55fa359f4ffda117b25d4234796fb915fe30eebad837422d08f75f57e41638"},"schema_version":"1.0"},"canonical_sha256":"57da0ed79575744ff2d45b52ca5135a271aa7bf5a1bb770652ef3e108e5c441c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:16.741474Z","signature_b64":"AnexjhpWwViIxjjMwXrjI1oI4dv7X9TN1nCYNkocVcD5ZSD3D9SmbJNQVtuoagP9xOoS0DGfbGDJHmeELmMuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57da0ed79575744ff2d45b52ca5135a271aa7bf5a1bb770652ef3e108e5c441c","last_reissued_at":"2026-07-05T09:31:16.740994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:16.740994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02712","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":"2026-07-05T09:31:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pOppMhrGXO+nVdfMW7DvddSTdnSR3BQOunJa0VbfdS/aLOlDcguy8UAJVLKgt5OxfJEoLSGFsFu59ZQDJt4CDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:57:17.245089Z"},"content_sha256":"135a81b35c9257b98efa77601d6b81709c8a1d1c741ad1fbacd6bc8a21865487","schema_version":"1.0","event_id":"sha256:135a81b35c9257b98efa77601d6b81709c8a1d1c741ad1fbacd6bc8a21865487"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K7NA5V4VOV2E74WULNJMUUJVUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanzhen Li, Min-Yen Kan, Xiao Xu, Yuxi Xie","submitted_at":"2024-11-05T01:24:37Z","abstract_excerpt":"Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large Language Model (LLM) backbone, as one cause of the LVLM hallucination, inherently introduces bias from language priors, leading to insufficient context attention to the visual inputs.\n  We tackle this issue of hallucination by mitigating such over-reliance through preference learning. We propose Vision-guided Direct Preference Optimization (V-DPO) to enhance visual context learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02712","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/2411.02712/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":"2026-07-05T09:31:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JR8cFmX+AjMVQ7PDqvoBaEgrGTQhmYnwD0GoiH/ToNMyC1ChTMaoMpNpbIRKtUwzyvehZgL1WokgOsYjTDgXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:57:17.245994Z"},"content_sha256":"2f09d54e32894f70d8dba31514fcecd50459a3f36cdff6042239ec2f20430024","schema_version":"1.0","event_id":"sha256:2f09d54e32894f70d8dba31514fcecd50459a3f36cdff6042239ec2f20430024"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/bundle.json","state_url":"https://pith.science/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/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":"2026-08-14T21:57:17Z","links":{"resolver":"https://pith.science/pith/K7NA5V4VOV2E74WULNJMUUJVUJ","bundle":"https://pith.science/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/bundle.json","state":"https://pith.science/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7NA5V4VOV2E74WULNJMUUJVUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K7NA5V4VOV2E74WULNJMUUJVUJ","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":"9c55fa359f4ffda117b25d4234796fb915fe30eebad837422d08f75f57e41638","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T01:24:37Z","title_canon_sha256":"1472a6c00544cdcfdc08d20e345f4450e8cdc651309a27b0dae42bce561f52f8"},"schema_version":"1.0","source":{"id":"2411.02712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02712","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02712v1","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02712","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_12","alias_value":"K7NA5V4VOV2E","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_16","alias_value":"K7NA5V4VOV2E74WU","created_at":"2026-07-05T09:31:16Z"},{"alias_kind":"pith_short_8","alias_value":"K7NA5V4V","created_at":"2026-07-05T09:31:16Z"}],"graph_snapshots":[{"event_id":"sha256:2f09d54e32894f70d8dba31514fcecd50459a3f36cdff6042239ec2f20430024","target":"graph","created_at":"2026-07-05T09:31:16Z","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/2411.02712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large Language Model (LLM) backbone, as one cause of the LVLM hallucination, inherently introduces bias from language priors, leading to insufficient context attention to the visual inputs.\n  We tackle this issue of hallucination by mitigating such over-reliance through preference learning. We propose Vision-guided Direct Preference Optimization (V-DPO) to enhance visual context learni","authors_text":"Guanzhen Li, Min-Yen Kan, Xiao Xu, Yuxi Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T01:24:37Z","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02712","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":"sha256:135a81b35c9257b98efa77601d6b81709c8a1d1c741ad1fbacd6bc8a21865487","target":"record","created_at":"2026-07-05T09:31:16Z","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":"9c55fa359f4ffda117b25d4234796fb915fe30eebad837422d08f75f57e41638","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T01:24:37Z","title_canon_sha256":"1472a6c00544cdcfdc08d20e345f4450e8cdc651309a27b0dae42bce561f52f8"},"schema_version":"1.0","source":{"id":"2411.02712","kind":"arxiv","version":1}},"canonical_sha256":"57da0ed79575744ff2d45b52ca5135a271aa7bf5a1bb770652ef3e108e5c441c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57da0ed79575744ff2d45b52ca5135a271aa7bf5a1bb770652ef3e108e5c441c","first_computed_at":"2026-07-05T09:31:16.740994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:16.740994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AnexjhpWwViIxjjMwXrjI1oI4dv7X9TN1nCYNkocVcD5ZSD3D9SmbJNQVtuoagP9xOoS0DGfbGDJHmeELmMuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:16.741474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135a81b35c9257b98efa77601d6b81709c8a1d1c741ad1fbacd6bc8a21865487","sha256:2f09d54e32894f70d8dba31514fcecd50459a3f36cdff6042239ec2f20430024"],"state_sha256":"0bbb489e9885f31e23293e8a691b907ec1fa37b558763b760e726c3f55c00bc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6EgCmw4y41McAEs83aAZ5rK4UX6geiVO8PMD4WAgLRISlVlFHxP7QOExKp2aX6MIh0pUl4emM1MictKDN2dDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:57:17.252907Z","bundle_sha256":"dd8c812b9440f3c75808432a54a13118c19a76a63b911df5776dad262b07f5b7"}}