{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QYG4AAMOGYV5DZBJAWGLI2M43","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":"8aa1a28d76fb78f3e956bebd31130f9206f7e51680c0134a258f1bf90f838dcb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T12:09:20Z","title_canon_sha256":"34592c8ff2385f992bbd7a4aaae3aa92d240544b768a2ec200cb79e5d2034f84"},"schema_version":"1.0","source":{"id":"2606.09393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09393","created_at":"2026-06-09T02:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09393v1","created_at":"2026-06-09T02:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09393","created_at":"2026-06-09T02:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"4QYG4AAMOGYV","created_at":"2026-06-09T02:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"4QYG4AAMOGYV5DZB","created_at":"2026-06-09T02:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"4QYG4AAM","created_at":"2026-06-09T02:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:fbf5fd5ebeb42d2baea5e92b1b72f93ff4edbfc2c74c30272537c71e5a1410e7","target":"graph","created_at":"2026-06-09T02:08:19Z","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/2606.09393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable annotations and often causes models to memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome these limitations, we propose applying Reinforcement Learning with Verifiable Rewards (RLVR) to the ope","authors_text":"Dahua Lin, Feng Wu, Jianze Liang, Jiaqi Wang, Jiazi Bu, Long Xing, Penghui Yang, Qidong Huang, Xiaoyi Dong, Yibin Wang, Yuhang Cao, Yuhang Zang, Yujie Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T12:09:20Z","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09393","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":"sha256:89f812955782b168cfff097b4fb2c648c1bc18d3c4d3484f1eb34688fcf54e5c","target":"record","created_at":"2026-06-09T02:08:19Z","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":"8aa1a28d76fb78f3e956bebd31130f9206f7e51680c0134a258f1bf90f838dcb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T12:09:20Z","title_canon_sha256":"34592c8ff2385f992bbd7a4aaae3aa92d240544b768a2ec200cb79e5d2034f84"},"schema_version":"1.0","source":{"id":"2606.09393","kind":"arxiv","version":1}},"canonical_sha256":"e4306e000c71b15e8f21482c65a34ce6c869107f4848054d25cd0a0a9baeb108","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4306e000c71b15e8f21482c65a34ce6c869107f4848054d25cd0a0a9baeb108","first_computed_at":"2026-06-09T02:08:19.734407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:19.734407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zAwuwknRSn6xpwl6nGyZgSC0FNZ03bvd6nK/pYVaqoha5iuOrd/3WOMoeHpM9Ax1/3w6SitYG16RH3LMOul/Dw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:19.735308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89f812955782b168cfff097b4fb2c648c1bc18d3c4d3484f1eb34688fcf54e5c","sha256:fbf5fd5ebeb42d2baea5e92b1b72f93ff4edbfc2c74c30272537c71e5a1410e7"],"state_sha256":"fdf4bf2caae56f6dc52d95b37d9b4e74c947ddbcf2036b8b337fbd173d0d98c6"}