{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4S255XSSSWSDS7MYG5BNJY265X","short_pith_number":"pith:4S255XSS","schema_version":"1.0","canonical_sha256":"e4b5dede5295a4397d983742d4e35eede36ff93b3f8b4f7199cbd0873c802533","source":{"kind":"arxiv","id":"2508.18966","version":1},"attestation_state":"computed","paper":{"title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Ding, Jiahe Tian, Mengqi Huang, Qian He, Shaojin Wu, Wenxu Wu, Yiming Luo, Yufeng Cheng","submitted_at":"2025-08-26T12:10:24Z","abstract_excerpt":"Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency, resulting in an apparent antagonism. We argue that both objectives can be unified under a single framework because they ultimately concern the disentanglement and re-composition of content and style, a long-standing theme in style-driven research. To this end, we present USO, a Unified Style-Subject Optimized customization model. First, we construct a large-scale triplet dataset consisting of conte"},"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":"2508.18966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T12:10:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a67c696676e13bd4f3e6e76c0726580e78aa6ccc376db2ad343813dbdfec050","abstract_canon_sha256":"3a3d3c1674490e446e19e202b147c8b41bb408c577755395ee7dac7cd5a08596"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:34.620396Z","signature_b64":"NVSwlXADp39MYAfgpIwHPbd4O2kecPXDuhHYf+8mGjTXcsAHmI0rZeo1dLEslenEoX4eYAJSYfoUvigw4wCUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4b5dede5295a4397d983742d4e35eede36ff93b3f8b4f7199cbd0873c802533","last_reissued_at":"2026-07-05T11:59:34.619894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:34.619894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Ding, Jiahe Tian, Mengqi Huang, Qian He, Shaojin Wu, Wenxu Wu, Yiming Luo, Yufeng Cheng","submitted_at":"2025-08-26T12:10:24Z","abstract_excerpt":"Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency, resulting in an apparent antagonism. We argue that both objectives can be unified under a single framework because they ultimately concern the disentanglement and re-composition of content and style, a long-standing theme in style-driven research. To this end, we present USO, a Unified Style-Subject Optimized customization model. First, we construct a large-scale triplet dataset consisting of conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18966","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/2508.18966/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":"2508.18966","created_at":"2026-07-05T11:59:34.619953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18966v1","created_at":"2026-07-05T11:59:34.619953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18966","created_at":"2026-07-05T11:59:34.619953+00:00"},{"alias_kind":"pith_short_12","alias_value":"4S255XSSSWSD","created_at":"2026-07-05T11:59:34.619953+00:00"},{"alias_kind":"pith_short_16","alias_value":"4S255XSSSWSDS7MY","created_at":"2026-07-05T11:59:34.619953+00:00"},{"alias_kind":"pith_short_8","alias_value":"4S255XSS","created_at":"2026-07-05T11:59:34.619953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26947","citing_title":"Scaling Multi-Reference Image Generation with Dynamic Reward Optimization","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20506","citing_title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12088","citing_title":"UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12088","citing_title":"UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X","json":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X.json","graph_json":"https://pith.science/api/pith-number/4S255XSSSWSDS7MYG5BNJY265X/graph.json","events_json":"https://pith.science/api/pith-number/4S255XSSSWSDS7MYG5BNJY265X/events.json","paper":"https://pith.science/paper/4S255XSS"},"agent_actions":{"view_html":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X","download_json":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X.json","view_paper":"https://pith.science/paper/4S255XSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18966&json=true","fetch_graph":"https://pith.science/api/pith-number/4S255XSSSWSDS7MYG5BNJY265X/graph.json","fetch_events":"https://pith.science/api/pith-number/4S255XSSSWSDS7MYG5BNJY265X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X/action/storage_attestation","attest_author":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X/action/author_attestation","sign_citation":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X/action/citation_signature","submit_replication":"https://pith.science/pith/4S255XSSSWSDS7MYG5BNJY265X/action/replication_record"}},"created_at":"2026-07-05T11:59:34.619953+00:00","updated_at":"2026-07-05T11:59:34.619953+00:00"}