{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GUNOICWVT5MDYR27JG3T7XQFNI","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":"00f31e2d74bfab057d1a89821c1459c9748543ccfa529d22204e50b017f5d2d9","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T06:41:28Z","title_canon_sha256":"dcd0820bc0655515050226c7246e2ef6b251304cd008659264ae12b9ffa64aa9"},"schema_version":"1.0","source":{"id":"2505.19000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19000","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19000v1","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19000","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"GUNOICWVT5MD","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_16","alias_value":"GUNOICWVT5MDYR27","created_at":"2026-07-05T11:09:23Z"},{"alias_kind":"pith_short_8","alias_value":"GUNOICWV","created_at":"2026-07-05T11:09:23Z"}],"graph_snapshots":[{"event_id":"sha256:d8f2a3984d2ac32d75c72e91f914a2330465ab850998b00a78a51e961f0485b9","target":"graph","created_at":"2026-07-05T11:09:23Z","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/2505.19000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy Optimization (GRPO), are limited by data preparation bottlenecks (e.g., noise or high cost) and exhibit unstable improvements in the quality of long chain-of-thoughts (CoTs) and downstream performance.To address these limitations, we propose VerIPO, a Verifier-guided Iterative Policy Optimization method designed to gradually improve video LLMs' capacity for ge","authors_text":"Baotian Hu, Longyue Wang, Min Zhang, Wenhan Luo, Xinyu Chen, Yunxin Li, Zhenyu Liu, Zitao Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T06:41:28Z","title":"VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19000","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":"sha256:2986d58d5cff8bc951e3685e884079da15e8b635cbaaa38c5c09e816c1a0ca0d","target":"record","created_at":"2026-07-05T11:09:23Z","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":"00f31e2d74bfab057d1a89821c1459c9748543ccfa529d22204e50b017f5d2d9","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T06:41:28Z","title_canon_sha256":"dcd0820bc0655515050226c7246e2ef6b251304cd008659264ae12b9ffa64aa9"},"schema_version":"1.0","source":{"id":"2505.19000","kind":"arxiv","version":1}},"canonical_sha256":"351ae40ad59f583c475f49b73fde056a06a40e3f16aa12475f819b6e7333b569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"351ae40ad59f583c475f49b73fde056a06a40e3f16aa12475f819b6e7333b569","first_computed_at":"2026-07-05T11:09:23.325044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:23.325044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7t2n+Du0yYlaYBfY3s2yw0iZsA/xfacG0qEYZmX31IiTjsJhffVg7pEJRvDnXXHoBRkKhDHXgQ5yueEf1r0RBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:23.325577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2986d58d5cff8bc951e3685e884079da15e8b635cbaaa38c5c09e816c1a0ca0d","sha256:d8f2a3984d2ac32d75c72e91f914a2330465ab850998b00a78a51e961f0485b9"],"state_sha256":"410a66b3e338704d2721e7252ed1dd86ce971e8b7bb1959ae835b4ea145d0a1d"}