{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WKEPV2Y7VQYCAVACXDMCVWY3BO","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":"49d98e28fcb0816d6ca006cb58bb0a1a3af5c1ae2fff4f7c2e7f8cc55163cd2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T22:36:15Z","title_canon_sha256":"949bc0bf7c32a362508ec0bb7bff0723a2a8717ce80999856b484ed618fa5b59"},"schema_version":"1.0","source":{"id":"2505.21547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21547","created_at":"2026-07-05T11:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21547v1","created_at":"2026-07-05T11:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21547","created_at":"2026-07-05T11:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"WKEPV2Y7VQYC","created_at":"2026-07-05T11:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"WKEPV2Y7VQYCAVAC","created_at":"2026-07-05T11:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"WKEPV2Y7","created_at":"2026-07-05T11:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:a319d0e2f80624038b7a548592b50bcfb9cb74d6c66147380631186bcf8afa68","target":"graph","created_at":"2026-07-05T11:10:59Z","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/2505.21547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiveness, we find that these models still hallucinate non-existent objects. We hypothesize that this may be due to visual priors induced during training: When certain image tokens frequently co-occur in the same spatial regions and represent shared objects, they become strongly associated with the verbalizations of those objects. As a result, the model may hallucinate by evoking visually absent tokens that often co-occur ","authors_text":"Christoph Meinel, Gerard de Melo, Haojin Yang, Jindong Gu, Rui Cao, Weixing Wang, Zifeng Ding","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T22:36:15Z","title":"Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21547","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":"sha256:4c5e0d6f1c805dfcea1dadc455948a5e37061653d7c0196f27351f1aba9cf426","target":"record","created_at":"2026-07-05T11:10:59Z","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":"49d98e28fcb0816d6ca006cb58bb0a1a3af5c1ae2fff4f7c2e7f8cc55163cd2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T22:36:15Z","title_canon_sha256":"949bc0bf7c32a362508ec0bb7bff0723a2a8717ce80999856b484ed618fa5b59"},"schema_version":"1.0","source":{"id":"2505.21547","kind":"arxiv","version":1}},"canonical_sha256":"b288faeb1fac30205402b8d82adb1b0b8d1bac4ef57e28c4364c752df8a739d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b288faeb1fac30205402b8d82adb1b0b8d1bac4ef57e28c4364c752df8a739d2","first_computed_at":"2026-07-05T11:10:59.721245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:59.721245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EoLpdZOg0c6ZG/mZn3P+BsPtDodIVn6A5rR96bdS08rM54mHV9gasj08g3XPYHEAZUPKN3h6vWMpC/cMoXh/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:59.721711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c5e0d6f1c805dfcea1dadc455948a5e37061653d7c0196f27351f1aba9cf426","sha256:a319d0e2f80624038b7a548592b50bcfb9cb74d6c66147380631186bcf8afa68"],"state_sha256":"83ae28f3113e15190578fdd1eb080c96c131a5d0a7ecba630380bd555bb1b8d7"}