{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5BMW67GENTTZR4PJSFDCR7MIR","short_pith_number":"pith:M5BMW67G","schema_version":"1.0","canonical_sha256":"6742cb7be623673cc78f4c8a3147ec44733e26dc43f97bbb07503ad3053615d0","source":{"kind":"arxiv","id":"2505.14028","version":1},"attestation_state":"computed","paper":{"title":"OmniStyle: Filtering High Quality Style Transfer Data at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Liu, Jiang Lin, Rui Ma, Ruiqi Liu, Ye Wang, Yilin Wang, Zili Yi","submitted_at":"2025-05-20T07:29:21Z","abstract_excerpt":"In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-qualit"},"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":"2505.14028","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T07:29:21Z","cross_cats_sorted":[],"title_canon_sha256":"1052f24f4c55db18c92e46cc33bb877772a87152a937de291ebaaddc9443d5f9","abstract_canon_sha256":"60cdbe2905fb42e1f370b1136f7fc42620e82fefb0983a266ef5c978f44173ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:54.990904Z","signature_b64":"yQsTls42kpBahsNceuErBIzRV6eKGhvz8WcG+9apfBtFkyKwj/5HV6zne+nH5kyu90Ue1xp58VxeDjyTr1k0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6742cb7be623673cc78f4c8a3147ec44733e26dc43f97bbb07503ad3053615d0","last_reissued_at":"2026-07-05T11:05:54.990408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:54.990408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniStyle: Filtering High Quality Style Transfer Data at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Liu, Jiang Lin, Rui Ma, Ruiqi Liu, Ye Wang, Yilin Wang, Zili Yi","submitted_at":"2025-05-20T07:29:21Z","abstract_excerpt":"In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-qualit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14028","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/2505.14028/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":"2505.14028","created_at":"2026-07-05T11:05:54.990478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14028v1","created_at":"2026-07-05T11:05:54.990478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14028","created_at":"2026-07-05T11:05:54.990478+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5BMW67GENTT","created_at":"2026-07-05T11:05:54.990478+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5BMW67GENTTZR4P","created_at":"2026-07-05T11:05:54.990478+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5BMW67G","created_at":"2026-07-05T11:05:54.990478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20506","citing_title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR","json":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR.json","graph_json":"https://pith.science/api/pith-number/M5BMW67GENTTZR4PJSFDCR7MIR/graph.json","events_json":"https://pith.science/api/pith-number/M5BMW67GENTTZR4PJSFDCR7MIR/events.json","paper":"https://pith.science/paper/M5BMW67G"},"agent_actions":{"view_html":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR","download_json":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR.json","view_paper":"https://pith.science/paper/M5BMW67G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14028&json=true","fetch_graph":"https://pith.science/api/pith-number/M5BMW67GENTTZR4PJSFDCR7MIR/graph.json","fetch_events":"https://pith.science/api/pith-number/M5BMW67GENTTZR4PJSFDCR7MIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR/action/storage_attestation","attest_author":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR/action/author_attestation","sign_citation":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR/action/citation_signature","submit_replication":"https://pith.science/pith/M5BMW67GENTTZR4PJSFDCR7MIR/action/replication_record"}},"created_at":"2026-07-05T11:05:54.990478+00:00","updated_at":"2026-07-05T11:05:54.990478+00:00"}