{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RG3XJSYD5PUAEMF234MPGQUIY2","short_pith_number":"pith:RG3XJSYD","schema_version":"1.0","canonical_sha256":"89b774cb03ebe80230badf18f34288c6babfc0f8e865260e41a78a016e131469","source":{"kind":"arxiv","id":"2601.22725","version":4},"attestation_state":"computed","paper":{"title":"OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhui Wu, Jingwen Luo, Jin Li, Kai Wen, Shuai Jiang, Siqi Yin, Tao Chen, Weijie Wang","submitted_at":"2026-01-30T08:58:00Z","abstract_excerpt":"Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \\times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and G"},"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":true},"canonical_record":{"source":{"id":"2601.22725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T08:58:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"153d867e7aa22f49f77187f72a699dde2824253fb7478a2501ff7eedd11633cb","abstract_canon_sha256":"510d882433074fcf4883058bb9337632f1fe0ffad9a7065fe2d90c8a3a76fb9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:27.886990Z","signature_b64":"fBBq9wiNKFdwLwOG6obfRGIQROat/InOW6At8Y2/hvn+sDczIYq7EVtzcD+7RQF9Nm1rN3+R98heFKfA9zZTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b774cb03ebe80230badf18f34288c6babfc0f8e865260e41a78a016e131469","last_reissued_at":"2026-06-11T01:09:27.885897Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:27.885897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhui Wu, Jingwen Luo, Jin Li, Kai Wen, Shuai Jiang, Siqi Yin, Tao Chen, Weijie Wang","submitted_at":"2026-01-30T08:58:00Z","abstract_excerpt":"Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \\times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and G"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show strong agreement with human judgments (Kendall's τ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the VLM-based semantic reasoning combined with the Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion accurately and without bias measures the five dimensions of VTON quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenVTON-Bench supplies a large-scale high-resolution dataset and multi-modal protocol for virtual try-on evaluation that correlates more strongly with human judgments than standard metrics like SSIM.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ad857c3c766956369858fe77661d09771cc11962c3b8dcb68f7c53171b6d9c8f"},"source":{"id":"2601.22725","kind":"arxiv","version":4},"verdict":{"id":"6c9ffc3d-7792-4c2d-801b-16d49faeccb0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:44:52.030002Z","strongest_claim":"Experimental results show strong agreement with human judgments (Kendall's τ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.","one_line_summary":"OpenVTON-Bench supplies a large-scale high-resolution dataset and multi-modal protocol for virtual try-on evaluation that correlates more strongly with human judgments than standard metrics like SSIM.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the VLM-based semantic reasoning combined with the Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion accurately and without bias measures the five dimensions of VTON quality.","pith_extraction_headline":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.22725/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":2,"snapshot_sha256":"7226196ab3f7a2ddf4d1d3c5e8e92af1d311906687f81573cf8ca4727afa6af2"},"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":"2601.22725","created_at":"2026-06-11T01:09:27.886046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22725v4","created_at":"2026-06-11T01:09:27.886046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22725","created_at":"2026-06-11T01:09:27.886046+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG3XJSYD5PUA","created_at":"2026-06-11T01:09:27.886046+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG3XJSYD5PUAEMF2","created_at":"2026-06-11T01:09:27.886046+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG3XJSYD","created_at":"2026-06-11T01:09:27.886046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2","json":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2.json","graph_json":"https://pith.science/api/pith-number/RG3XJSYD5PUAEMF234MPGQUIY2/graph.json","events_json":"https://pith.science/api/pith-number/RG3XJSYD5PUAEMF234MPGQUIY2/events.json","paper":"https://pith.science/paper/RG3XJSYD"},"agent_actions":{"view_html":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2","download_json":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2.json","view_paper":"https://pith.science/paper/RG3XJSYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22725&json=true","fetch_graph":"https://pith.science/api/pith-number/RG3XJSYD5PUAEMF234MPGQUIY2/graph.json","fetch_events":"https://pith.science/api/pith-number/RG3XJSYD5PUAEMF234MPGQUIY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2/action/storage_attestation","attest_author":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2/action/author_attestation","sign_citation":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2/action/citation_signature","submit_replication":"https://pith.science/pith/RG3XJSYD5PUAEMF234MPGQUIY2/action/replication_record"}},"created_at":"2026-06-11T01:09:27.886046+00:00","updated_at":"2026-06-11T01:09:27.886046+00:00"}