{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4QYG4AAMOGYV5DZBJAWGLI2M43","short_pith_number":"pith:4QYG4AAM","schema_version":"1.0","canonical_sha256":"e4306e000c71b15e8f21482c65a34ce6c869107f4848054d25cd0a0a9baeb108","source":{"kind":"arxiv","id":"2606.09393","version":1},"attestation_state":"computed","paper":{"title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-06-08T12:09:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T12:09:20Z","cross_cats_sorted":[],"title_canon_sha256":"34592c8ff2385f992bbd7a4aaae3aa92d240544b768a2ec200cb79e5d2034f84","abstract_canon_sha256":"8aa1a28d76fb78f3e956bebd31130f9206f7e51680c0134a258f1bf90f838dcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:19.735308Z","signature_b64":"zAwuwknRSn6xpwl6nGyZgSC0FNZ03bvd6nK/pYVaqoha5iuOrd/3WOMoeHpM9Ax1/3w6SitYG16RH3LMOul/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4306e000c71b15e8f21482c65a34ce6c869107f4848054d25cd0a0a9baeb108","last_reissued_at":"2026-06-09T02:08:19.734407Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:19.734407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-06-08T12:09:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09393","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.09393/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09393","created_at":"2026-06-09T02:08:19.734562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09393v1","created_at":"2026-06-09T02:08:19.734562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09393","created_at":"2026-06-09T02:08:19.734562+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QYG4AAMOGYV","created_at":"2026-06-09T02:08:19.734562+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QYG4AAMOGYV5DZB","created_at":"2026-06-09T02:08:19.734562+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QYG4AAM","created_at":"2026-06-09T02:08:19.734562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43","json":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43.json","graph_json":"https://pith.science/api/pith-number/4QYG4AAMOGYV5DZBJAWGLI2M43/graph.json","events_json":"https://pith.science/api/pith-number/4QYG4AAMOGYV5DZBJAWGLI2M43/events.json","paper":"https://pith.science/paper/4QYG4AAM"},"agent_actions":{"view_html":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43","download_json":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43.json","view_paper":"https://pith.science/paper/4QYG4AAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09393&json=true","fetch_graph":"https://pith.science/api/pith-number/4QYG4AAMOGYV5DZBJAWGLI2M43/graph.json","fetch_events":"https://pith.science/api/pith-number/4QYG4AAMOGYV5DZBJAWGLI2M43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43/action/storage_attestation","attest_author":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43/action/author_attestation","sign_citation":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43/action/citation_signature","submit_replication":"https://pith.science/pith/4QYG4AAMOGYV5DZBJAWGLI2M43/action/replication_record"}},"created_at":"2026-06-09T02:08:19.734562+00:00","updated_at":"2026-06-09T02:08:19.734562+00:00"}