{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EN5IBSMSXQS2ZGUIULAW4POB2K","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":"791ccb460b8f89419d283f4ed3337e634f0ba4e5eb947194218015c09d3a1557","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T08:07:46Z","title_canon_sha256":"5e8ff22d103f0767ff2f3c7ca82dbd39afd774bbe3c8651e1205a0dbee916794"},"schema_version":"1.0","source":{"id":"2504.06666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06666","created_at":"2026-07-05T10:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06666v1","created_at":"2026-07-05T10:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06666","created_at":"2026-07-05T10:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"EN5IBSMSXQS2","created_at":"2026-07-05T10:46:43Z"},{"alias_kind":"pith_short_16","alias_value":"EN5IBSMSXQS2ZGUI","created_at":"2026-07-05T10:46:43Z"},{"alias_kind":"pith_short_8","alias_value":"EN5IBSMS","created_at":"2026-07-05T10:46:43Z"}],"graph_snapshots":[{"event_id":"sha256:129f4f92c36ab1e7394ed208e310c61be10684f6ed8ccdb465c0df8f1fbf4284","target":"graph","created_at":"2026-07-05T10:46:43Z","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/2504.06666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions, many recent studies have employed multimodal large language models (MLLMs). However, current MLLMs often produce captions that lack fine-grained details or suffer from hallucinations, a challenge that persists in both open-source and closed-source models. Inspired by Feature-Integration theory, which suggests that attention must focus on specific regions to int","authors_text":"Di Hu, Haiying He, Ruotian Peng, Yake Wei, Yandong Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T08:07:46Z","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06666","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":"sha256:7b75d54fc504dbe42b0b733d4d7f866d081b67a6aa6a350f443c1c775b849060","target":"record","created_at":"2026-07-05T10:46:43Z","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":"791ccb460b8f89419d283f4ed3337e634f0ba4e5eb947194218015c09d3a1557","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T08:07:46Z","title_canon_sha256":"5e8ff22d103f0767ff2f3c7ca82dbd39afd774bbe3c8651e1205a0dbee916794"},"schema_version":"1.0","source":{"id":"2504.06666","kind":"arxiv","version":1}},"canonical_sha256":"237a80c992bc25ac9a88a2c16e3dc1d2a2a7b1cedbee9f502b297c5afe824540","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"237a80c992bc25ac9a88a2c16e3dc1d2a2a7b1cedbee9f502b297c5afe824540","first_computed_at":"2026-07-05T10:46:43.782397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:43.782397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6t/YxMemXPsoDJ4x5jMOY3b3TLabJnok0QAe1v527wlQAGHU59NlDXCASkcuuDX4a6Mlv0MUp5gQU/HKOC6GBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:43.782906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b75d54fc504dbe42b0b733d4d7f866d081b67a6aa6a350f443c1c775b849060","sha256:129f4f92c36ab1e7394ed208e310c61be10684f6ed8ccdb465c0df8f1fbf4284"],"state_sha256":"b3f9ba4c5167c45f75633c8ffc21bf4e18bec4f4ab24bfbc1062c75523c2c2c4"}