{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3UJQ4IUIDXD6SQLFT3ZM5O3EPO","short_pith_number":"pith:3UJQ4IUI","schema_version":"1.0","canonical_sha256":"dd130e22881dc7e941659ef2cebb647b99a570eca3b025d209148e2cb1cb9e78","source":{"kind":"arxiv","id":"2508.03320","version":1},"attestation_state":"computed","paper":{"title":"Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhu, Changshi Li, Chuanxin Tang, Eric Li, Hongyang Wei, Liang Hu, Peiyu Wang, Tianyidan Xie, Xiaokun Wang, Xuchen Song, Yahui Zhou, Yang Liu, Yichen Wei, Yimeng Gan, Yi Peng","submitted_at":"2025-08-05T10:59:01Z","abstract_excerpt":"We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generat"},"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":"2508.03320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T10:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"9d95ab1cb086c81e008e760eb00ab02c6d27ac4e74f8cadefb1fd4b3bbb87cf6","abstract_canon_sha256":"cab1016de79adedcd8205fa4a2042c35e5b6866e0c943d94192947e15cc5ae07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:54.267865Z","signature_b64":"2z0gsrooV09jJMVZNPeEDEAxK0G6adka3yGalas5Re8MKVP2U4p/9lDn+rc8su2oa+Sa9NEcefUqXKKVZhpOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd130e22881dc7e941659ef2cebb647b99a570eca3b025d209148e2cb1cb9e78","last_reissued_at":"2026-07-05T11:48:54.267473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:54.267473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhu, Changshi Li, Chuanxin Tang, Eric Li, Hongyang Wei, Liang Hu, Peiyu Wang, Tianyidan Xie, Xiaokun Wang, Xuchen Song, Yahui Zhou, Yang Liu, Yichen Wei, Yimeng Gan, Yi Peng","submitted_at":"2025-08-05T10:59:01Z","abstract_excerpt":"We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03320","kind":"arxiv","version":1},"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/2508.03320/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":"2508.03320","created_at":"2026-07-05T11:48:54.267530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03320v1","created_at":"2026-07-05T11:48:54.267530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03320","created_at":"2026-07-05T11:48:54.267530+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UJQ4IUIDXD6","created_at":"2026-07-05T11:48:54.267530+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UJQ4IUIDXD6SQLF","created_at":"2026-07-05T11:48:54.267530+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UJQ4IUI","created_at":"2026-07-05T11:48:54.267530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18714","citing_title":"Semantic Generative Tuning for Unified Multimodal Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18714","citing_title":"Semantic Generative Tuning for Unified Multimodal Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12305","citing_title":"Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO","json":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO.json","graph_json":"https://pith.science/api/pith-number/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/graph.json","events_json":"https://pith.science/api/pith-number/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/events.json","paper":"https://pith.science/paper/3UJQ4IUI"},"agent_actions":{"view_html":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO","download_json":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO.json","view_paper":"https://pith.science/paper/3UJQ4IUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03320&json=true","fetch_graph":"https://pith.science/api/pith-number/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/graph.json","fetch_events":"https://pith.science/api/pith-number/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/action/storage_attestation","attest_author":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/action/author_attestation","sign_citation":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/action/citation_signature","submit_replication":"https://pith.science/pith/3UJQ4IUIDXD6SQLFT3ZM5O3EPO/action/replication_record"}},"created_at":"2026-07-05T11:48:54.267530+00:00","updated_at":"2026-07-05T11:48:54.267530+00:00"}