{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4DMP4G5LXYS2QGT7CDS3CPWGKK","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":"ff23f30f256bf8f9bfd71fdbba5b93cfdf03e0053a0f91d6c3efbad3a2264baa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T12:24:10Z","title_canon_sha256":"caaa7f70652aa275531c1647e66b80fe6675625294fd9f8be0f83a5b594be527"},"schema_version":"1.0","source":{"id":"2504.16656","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16656","created_at":"2026-07-05T11:16:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16656v4","created_at":"2026-07-05T11:16:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16656","created_at":"2026-07-05T11:16:57Z"},{"alias_kind":"pith_short_12","alias_value":"4DMP4G5LXYS2","created_at":"2026-07-05T11:16:57Z"},{"alias_kind":"pith_short_16","alias_value":"4DMP4G5LXYS2QGT7","created_at":"2026-07-05T11:16:57Z"},{"alias_kind":"pith_short_8","alias_value":"4DMP4G5L","created_at":"2026-07-05T11:16:57Z"}],"graph_snapshots":[{"event_id":"sha256:d5295b9dc69e07012cd1ed9cdce36450698ee840e10956507ed2fc79e64b767b","target":"graph","created_at":"2026-07-05T11:16:57Z","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/2504.16656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Skywork R1V2, a next-generation multimodal reasoning model and a major leap forward from its predecessor, Skywork R1V. At its core, R1V2 introduces a hybrid reinforcement learning paradigm that jointly leverages the Mixed Preference Optimization (MPO) and the Group Relative Policy Optimization (GRPO), which harmonizes reward-model guidance with rule-based strategies, thereby addressing the long-standing challenge of balancing sophisticated reasoning capabilities with broad generalization. To further enhance training efficiency, we propose the Selective Sample Buffer (SSB) mechanism,","authors_text":"Jiangbo Pei, Jianhao Zhang, Peiyu Wang, Tianyidan Xie, Weijie Qiu, Wei Shen, Xiaokun Wang, Xuchen Song, Yahui Zhou, Yang Liu, Yichen Wei, Yi Peng, Yunzhuo Hao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T12:24:10Z","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16656","kind":"arxiv","version":4},"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":"sha256:5280659c61c18a718dd49426d6b2cad799687f2ecbf31b4836734a145064e218","target":"record","created_at":"2026-07-05T11:16:57Z","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":"ff23f30f256bf8f9bfd71fdbba5b93cfdf03e0053a0f91d6c3efbad3a2264baa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T12:24:10Z","title_canon_sha256":"caaa7f70652aa275531c1647e66b80fe6675625294fd9f8be0f83a5b594be527"},"schema_version":"1.0","source":{"id":"2504.16656","kind":"arxiv","version":4}},"canonical_sha256":"e0d8fe1babbe25a81a7f10e5b13ec6529395a9f027efeebb765e1f18c0f6577d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0d8fe1babbe25a81a7f10e5b13ec6529395a9f027efeebb765e1f18c0f6577d","first_computed_at":"2026-07-05T11:16:57.663580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:57.663580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hG+QxWVckKAo0i3hOpKBXwWMCIVXHTFZkeEGLeALCnjHzA8UcelZN59cnGCA02pmxKwnuXOwOUflECW+2WPaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:57.664135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16656","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5280659c61c18a718dd49426d6b2cad799687f2ecbf31b4836734a145064e218","sha256:d5295b9dc69e07012cd1ed9cdce36450698ee840e10956507ed2fc79e64b767b"],"state_sha256":"fd70e77dbe4b539f975bc30c41459efe39b148b78b3ec16aa6671f107587ad8b"}