{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P2IBD7FQFTKJ3NVITNEBLJCGPB","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":"4a651b0f0f2a87832548caef762622213e9a4304d29ef3db23681843bba392bb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T01:19:20Z","title_canon_sha256":"fe6e7eb9aded187176ade82ad72811bd14083efff28dddac64d909de96619980"},"schema_version":"1.0","source":{"id":"2504.05599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05599","created_at":"2026-07-05T11:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05599v2","created_at":"2026-07-05T11:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05599","created_at":"2026-07-05T11:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"P2IBD7FQFTKJ","created_at":"2026-07-05T11:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"P2IBD7FQFTKJ3NVI","created_at":"2026-07-05T11:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"P2IBD7FQ","created_at":"2026-07-05T11:18:20Z"}],"graph_snapshots":[{"event_id":"sha256:c075de5dcb4cd50e7c5e86847473eb543600225de619a1b1920e652d4e88f628","target":"graph","created_at":"2026-07-05T11:18:20Z","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/2504.05599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration ","authors_text":"Ai Jian, Jiachun Pan, Jiangbo Pei, Li Ge, Peiyu Wang, Rongxian Zhuang, Tianyidan Xie, Weijie Qiu, Xiaokun Wang, Xuchen Song, Yahui Zhou, Yang Liu, Yichen Wei, Yi Peng, Yunzhuo Hao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T01:19:20Z","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05599","kind":"arxiv","version":2},"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":"sha256:230297c32bafac399934719823b2c06636b2073a9d1fa5befd6f7c41a387f608","target":"record","created_at":"2026-07-05T11:18:20Z","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":"4a651b0f0f2a87832548caef762622213e9a4304d29ef3db23681843bba392bb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T01:19:20Z","title_canon_sha256":"fe6e7eb9aded187176ade82ad72811bd14083efff28dddac64d909de96619980"},"schema_version":"1.0","source":{"id":"2504.05599","kind":"arxiv","version":2}},"canonical_sha256":"7e9011fcb02cd49db6a89b4815a446786330738b1d86b063ac67ce65bc367230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e9011fcb02cd49db6a89b4815a446786330738b1d86b063ac67ce65bc367230","first_computed_at":"2026-07-05T11:18:20.149002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:20.149002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IZlmWd6G/YcpUMDJ4OrbBi+h0vKzH0aXBwhd6GMNXpO21LRA6mzAmBwFdjRuL0QjSUdBsqoizEFKvI0p2FFHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:20.149428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:230297c32bafac399934719823b2c06636b2073a9d1fa5befd6f7c41a387f608","sha256:c075de5dcb4cd50e7c5e86847473eb543600225de619a1b1920e652d4e88f628"],"state_sha256":"c2c6f6347e267925d9bf6b2fe2dd44bee50453ef44e21ef63fbf58d1c783d19e"}