{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HMY3XSZXTRLJF2CF5UK76RBJTQ","short_pith_number":"pith:HMY3XSZX","schema_version":"1.0","canonical_sha256":"3b31bbcb379c5692e845ed15ff44299c3791d964f2998805926c2311d7c3b9a7","source":{"kind":"arxiv","id":"2507.06167","version":3},"attestation_state":"computed","paper":{"title":"Skywork-R1V3 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haofeng Sun, Jiangbo Pei, Jianhao Zhang, Jian Peng, Peiyu Wang, Wei Shen, Xuchen Song, Yahui Zhou, Yang Liu, Yi Peng, Yunzhuo Hao","submitted_at":"2025-07-08T16:47:16Z","abstract_excerpt":"We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cro"},"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":"2507.06167","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T16:47:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8326a001851572c8a3a4b61f9004b74668468c571366a74784699b7e4029285f","abstract_canon_sha256":"17991b20edbdd3252435ae79f78c1fddeaeac310a89edd8f2e9e1252b7d06044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:53.820559Z","signature_b64":"KAYu/blgQFDo2aNwQbm0+FXtz59T8t1eU+hFNjVZQS31AZI8b8JdKWE6coqqgoywxVLW5STCK51y55xnOYe1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b31bbcb379c5692e845ed15ff44299c3791d964f2998805926c2311d7c3b9a7","last_reissued_at":"2026-07-05T11:34:53.820071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:53.820071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skywork-R1V3 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haofeng Sun, Jiangbo Pei, Jianhao Zhang, Jian Peng, Peiyu Wang, Wei Shen, Xuchen Song, Yahui Zhou, Yang Liu, Yi Peng, Yunzhuo Hao","submitted_at":"2025-07-08T16:47:16Z","abstract_excerpt":"We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06167","kind":"arxiv","version":3},"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/2507.06167/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":"2507.06167","created_at":"2026-07-05T11:34:53.820129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06167v3","created_at":"2026-07-05T11:34:53.820129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06167","created_at":"2026-07-05T11:34:53.820129+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMY3XSZXTRLJ","created_at":"2026-07-05T11:34:53.820129+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMY3XSZXTRLJF2CF","created_at":"2026-07-05T11:34:53.820129+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMY3XSZX","created_at":"2026-07-05T11:34:53.820129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30217","citing_title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ","json":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ.json","graph_json":"https://pith.science/api/pith-number/HMY3XSZXTRLJF2CF5UK76RBJTQ/graph.json","events_json":"https://pith.science/api/pith-number/HMY3XSZXTRLJF2CF5UK76RBJTQ/events.json","paper":"https://pith.science/paper/HMY3XSZX"},"agent_actions":{"view_html":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ","download_json":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ.json","view_paper":"https://pith.science/paper/HMY3XSZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06167&json=true","fetch_graph":"https://pith.science/api/pith-number/HMY3XSZXTRLJF2CF5UK76RBJTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HMY3XSZXTRLJF2CF5UK76RBJTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ/action/storage_attestation","attest_author":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ/action/author_attestation","sign_citation":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ/action/citation_signature","submit_replication":"https://pith.science/pith/HMY3XSZXTRLJF2CF5UK76RBJTQ/action/replication_record"}},"created_at":"2026-07-05T11:34:53.820129+00:00","updated_at":"2026-07-05T11:34:53.820129+00:00"}