{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEQSOJNJ5LOLKPNSPG4T56XT6H","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":"59bd57197a627a2fd7de828ccc05a3e6b868bcf0dbe60fc683dd4fcf44240ca9","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-17T08:24:27Z","title_canon_sha256":"741ef3bd9d2e33206809cb0314dcb352e06b34a44ee347c0d6abfcda3f0fb114"},"schema_version":"1.0","source":{"id":"2410.13321","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13321","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13321v3","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13321","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"YEQSOJNJ5LOL","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"YEQSOJNJ5LOLKPNS","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"YEQSOJNJ","created_at":"2026-07-05T10:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:e89735a65d89a3e89a116db877a36dcfadb0ab73c8c0ce76e5b362aa32d68a21","target":"graph","created_at":"2026-07-05T10:16:38Z","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/2410.13321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) demonstrate impressive capabilities in generating detailed and coherent responses from visual inputs. However, they are prone to generate hallucinations due to an over-reliance on language priors. To address this issue, we investigate the language priors in LVLMs and make two key observations: (1) Even when predicting the tokens associated with image-related part-of-speech (POS), models increasingly rely on linguistic priors as the token sequences grow, thereby amplifying hallucinations. (2) Methods that directly calibrate LVLM's output distribution to miti","authors_text":"Dongryeol Lee, Kang-il Lee, Kyomin Jung, Kyungmin Min, Minbeom Kim","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-17T08:24:27Z","title":"Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13321","kind":"arxiv","version":3},"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":"sha256:0e2c4ed3445ad09425a8234bcff8b6921c2d06f8a85a3ef3fce496b74ed8210e","target":"record","created_at":"2026-07-05T10:16:38Z","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":"59bd57197a627a2fd7de828ccc05a3e6b868bcf0dbe60fc683dd4fcf44240ca9","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-17T08:24:27Z","title_canon_sha256":"741ef3bd9d2e33206809cb0314dcb352e06b34a44ee347c0d6abfcda3f0fb114"},"schema_version":"1.0","source":{"id":"2410.13321","kind":"arxiv","version":3}},"canonical_sha256":"c1212725a9eadcb53db279b93efaf3f1fb2d0e3074481a21362c1807d46ce55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1212725a9eadcb53db279b93efaf3f1fb2d0e3074481a21362c1807d46ce55d","first_computed_at":"2026-07-05T10:16:38.628345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:38.628345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gfneJms37jKF8tI8BIwp2Gzh0FfIzxAP9CRXGV+VOwUMQxq8SQBfDQ8LX2suBcePX0Zwd9ieAaqJcPDS9NCrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:38.628882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13321","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e2c4ed3445ad09425a8234bcff8b6921c2d06f8a85a3ef3fce496b74ed8210e","sha256:e89735a65d89a3e89a116db877a36dcfadb0ab73c8c0ce76e5b362aa32d68a21"],"state_sha256":"88e4a166819723f3967d2421d014db556732e47ac308ae0e9a2bfff922323041"}