{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P2IBD7FQFTKJ3NVITNEBLJCGPB","short_pith_number":"pith:P2IBD7FQ","schema_version":"1.0","canonical_sha256":"7e9011fcb02cd49db6a89b4815a446786330738b1d86b063ac67ce65bc367230","source":{"kind":"arxiv","id":"2504.05599","version":2},"attestation_state":"computed","paper":{"title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2025-04-08T01:19:20Z","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 "},"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":"2504.05599","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T01:19:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fe6e7eb9aded187176ade82ad72811bd14083efff28dddac64d909de96619980","abstract_canon_sha256":"4a651b0f0f2a87832548caef762622213e9a4304d29ef3db23681843bba392bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:20.149428Z","signature_b64":"IZlmWd6G/YcpUMDJ4OrbBi+h0vKzH0aXBwhd6GMNXpO21LRA6mzAmBwFdjRuL0QjSUdBsqoizEFKvI0p2FFHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9011fcb02cd49db6a89b4815a446786330738b1d86b063ac67ce65bc367230","last_reissued_at":"2026-07-05T11:18:20.149002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:20.149002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2025-04-08T01:19:20Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05599","kind":"arxiv","version":2},"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/2504.05599/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":"2504.05599","created_at":"2026-07-05T11:18:20.149053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05599v2","created_at":"2026-07-05T11:18:20.149053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05599","created_at":"2026-07-05T11:18:20.149053+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2IBD7FQFTKJ","created_at":"2026-07-05T11:18:20.149053+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2IBD7FQFTKJ3NVI","created_at":"2026-07-05T11:18:20.149053+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2IBD7FQ","created_at":"2026-07-05T11:18:20.149053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02459","citing_title":"Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20332","citing_title":"Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05920","citing_title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09965","citing_title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03318","citing_title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21409","citing_title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB","json":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB.json","graph_json":"https://pith.science/api/pith-number/P2IBD7FQFTKJ3NVITNEBLJCGPB/graph.json","events_json":"https://pith.science/api/pith-number/P2IBD7FQFTKJ3NVITNEBLJCGPB/events.json","paper":"https://pith.science/paper/P2IBD7FQ"},"agent_actions":{"view_html":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB","download_json":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB.json","view_paper":"https://pith.science/paper/P2IBD7FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05599&json=true","fetch_graph":"https://pith.science/api/pith-number/P2IBD7FQFTKJ3NVITNEBLJCGPB/graph.json","fetch_events":"https://pith.science/api/pith-number/P2IBD7FQFTKJ3NVITNEBLJCGPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB/action/storage_attestation","attest_author":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB/action/author_attestation","sign_citation":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB/action/citation_signature","submit_replication":"https://pith.science/pith/P2IBD7FQFTKJ3NVITNEBLJCGPB/action/replication_record"}},"created_at":"2026-07-05T11:18:20.149053+00:00","updated_at":"2026-07-05T11:18:20.149053+00:00"}