{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6WX5G4MAKVA57BVQWVEQR7SCB2","short_pith_number":"pith:6WX5G4MA","schema_version":"1.0","canonical_sha256":"f5afd371805541df86b0b54908fe420e956f729ec414e1298d0a399be5bad892","source":{"kind":"arxiv","id":"2508.01215","version":1},"attestation_state":"computed","paper":{"title":"StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Wang, Quanjian Song, Shanshan Li, Xiaoyan Zhang, Yuanlin Yang, Zhexian Gao","submitted_at":"2025-08-02T06:17:23Z","abstract_excerpt":"Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for th"},"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":"2508.01215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-02T06:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"99651544bda4a1c6677cf40e529447843ffec86f2be9bf4d3d5468163f9dd44f","abstract_canon_sha256":"58258a57b90d00cd9bac52c4b68e2fe70f6efd30ab66c4223f803c0e76278b1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:34.986785Z","signature_b64":"vvBeWyElfC9RKaSg47FEgdFqVJ6o87idLCusuLLtT50+TlE4cXF0xxsGIBLtJSAvvtZQpD/WQP4UI3TPsmFADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5afd371805541df86b0b54908fe420e956f729ec414e1298d0a399be5bad892","last_reissued_at":"2026-07-05T11:47:34.986278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:34.986278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Wang, Quanjian Song, Shanshan Li, Xiaoyan Zhang, Yuanlin Yang, Zhexian Gao","submitted_at":"2025-08-02T06:17:23Z","abstract_excerpt":"Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01215","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/2508.01215/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":"2508.01215","created_at":"2026-07-05T11:47:34.986342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01215v1","created_at":"2026-07-05T11:47:34.986342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01215","created_at":"2026-07-05T11:47:34.986342+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WX5G4MAKVA5","created_at":"2026-07-05T11:47:34.986342+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WX5G4MAKVA57BVQ","created_at":"2026-07-05T11:47:34.986342+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WX5G4MA","created_at":"2026-07-05T11:47:34.986342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12598","citing_title":"Setting the Stage: Text-Driven Scene-Consistent Image Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2","json":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2.json","graph_json":"https://pith.science/api/pith-number/6WX5G4MAKVA57BVQWVEQR7SCB2/graph.json","events_json":"https://pith.science/api/pith-number/6WX5G4MAKVA57BVQWVEQR7SCB2/events.json","paper":"https://pith.science/paper/6WX5G4MA"},"agent_actions":{"view_html":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2","download_json":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2.json","view_paper":"https://pith.science/paper/6WX5G4MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01215&json=true","fetch_graph":"https://pith.science/api/pith-number/6WX5G4MAKVA57BVQWVEQR7SCB2/graph.json","fetch_events":"https://pith.science/api/pith-number/6WX5G4MAKVA57BVQWVEQR7SCB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2/action/storage_attestation","attest_author":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2/action/author_attestation","sign_citation":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2/action/citation_signature","submit_replication":"https://pith.science/pith/6WX5G4MAKVA57BVQWVEQR7SCB2/action/replication_record"}},"created_at":"2026-07-05T11:47:34.986342+00:00","updated_at":"2026-07-05T11:47:34.986342+00:00"}