{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RLZYC2GBW6I6IBTI34OMTPHSKM","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":"871ad13974628c3d697f55701260be96622b4c287c2f42614c676a05fd917684","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T04:39:28Z","title_canon_sha256":"d4603f743ef3271e0e5cbc32a0c65712a34f8bc5213ba582bd3469561460cc8e"},"schema_version":"1.0","source":{"id":"2605.20278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20278","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20278v1","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20278","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"RLZYC2GBW6I6","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"RLZYC2GBW6I6IBTI","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"RLZYC2GB","created_at":"2026-05-21T00:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:0f28a7896d592e0e84d79180114df044e7641283bc06c490bf7726b163393f64","target":"graph","created_at":"2026-05-21T00:04:23Z","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/2605.20278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and informative, avoiding hallucination without omitting salient details. Yet pairwise preferences, reference-based metrics, and holistic scalar rewards compress these local errors into a single sequence-level signal, obscuring the tradeoff between factuality and coverage. We introduce ClaimDiff-RL, a framework that uses reference-conditioned atomic claim differences","authors_text":"Haochen Wang, Hongyang Tang, Jiacheng Chen, Rongxin Guo, Shaoxiang Chen, Tianle Li, Xuyang Shen, Yan Ma, Yu Cheng, Yucong Zhou","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T04:39:28Z","title":"ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20278","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:c44f8f5ace4c151d9fbfadd6e93836871d58243abe8f665d5e40d6855bc41f8d","target":"record","created_at":"2026-05-21T00:04:23Z","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":"871ad13974628c3d697f55701260be96622b4c287c2f42614c676a05fd917684","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T04:39:28Z","title_canon_sha256":"d4603f743ef3271e0e5cbc32a0c65712a34f8bc5213ba582bd3469561460cc8e"},"schema_version":"1.0","source":{"id":"2605.20278","kind":"arxiv","version":1}},"canonical_sha256":"8af38168c1b791e40668df1cc9bcf25319335a9a6caf11cd8da7e6e694d738a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af38168c1b791e40668df1cc9bcf25319335a9a6caf11cd8da7e6e694d738a3","first_computed_at":"2026-05-21T00:04:23.787244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:23.787244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Odscn8JqrfsGzAcBWVh87dq4RueqXxaoiH57le1m3/kfxHJO8Aur66yjCXF9Mdh6LG4cNyBKny5Hg/GVWnHaCQ==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:23.787715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c44f8f5ace4c151d9fbfadd6e93836871d58243abe8f665d5e40d6855bc41f8d","sha256:0f28a7896d592e0e84d79180114df044e7641283bc06c490bf7726b163393f64"],"state_sha256":"aaa72db3ad812e244b5dfb32a00e6cb9c2a71b0291d60b64776df686475e1808"}