{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7RUOSTPSJ7MYU6S62ONS7DOLRE","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":"c29c1a75dfea0d1373b27c669a628f0fee63ae331ec8eac9502a8430aa43610d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-06T10:55:21Z","title_canon_sha256":"493f781e308c566fc7c1a847bbf18f7dd889be204a2107c1be76d2ecf154211c"},"schema_version":"1.0","source":{"id":"2505.03420","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03420","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03420v2","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03420","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"7RUOSTPSJ7MY","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"7RUOSTPSJ7MYU6S6","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"7RUOSTPS","created_at":"2026-07-05T11:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:007d8f2a385ce275890a9bb7b2b62e457fe46ec7808e557d0aa31e48a7730926","target":"graph","created_at":"2026-07-05T11:17:45Z","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/2505.03420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on additional data, demand significant computational resources and labor-intensive data collection, while ensemble-based methods incur additional costs by introducing auxiliary VLMs. To address these challenges, we propose a novel test-time adaptation framework using reinforcement learning to mitigate hallucinations during inference without retraining or any aux","authors_text":"Chengcui Zhang, Fei Zhao, Runlin Zhang, Tianyang Wang, Xi Li","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-06T10:55:21Z","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03420","kind":"arxiv","version":2},"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":"sha256:6ee821afe7b01f23b1537f4dcf91fcb9f2c6e0ea329db1eeded1464cb4f8fd43","target":"record","created_at":"2026-07-05T11:17:45Z","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":"c29c1a75dfea0d1373b27c669a628f0fee63ae331ec8eac9502a8430aa43610d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-06T10:55:21Z","title_canon_sha256":"493f781e308c566fc7c1a847bbf18f7dd889be204a2107c1be76d2ecf154211c"},"schema_version":"1.0","source":{"id":"2505.03420","kind":"arxiv","version":2}},"canonical_sha256":"fc68e94df24fd98a7a5ed39b2f8dcb892810c3fecc966e4deb209cf0826c21af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc68e94df24fd98a7a5ed39b2f8dcb892810c3fecc966e4deb209cf0826c21af","first_computed_at":"2026-07-05T11:17:45.185308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:45.185308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7u8bPrZt0BdbZxUKgG/IoAM8Jx5qwSkB/mulcNWJ2EV4zSRUCqbFfAXwrCmuyXtwn0qWMaB5d1lDREralkHhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:45.185749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03420","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee821afe7b01f23b1537f4dcf91fcb9f2c6e0ea329db1eeded1464cb4f8fd43","sha256:007d8f2a385ce275890a9bb7b2b62e457fe46ec7808e557d0aa31e48a7730926"],"state_sha256":"0f30948dbf5423ce75e2db925e313752c3794050e66a6f575585e34031b5b017"}