{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RG3XJSYD5PUAEMF234MPGQUIY2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"510d882433074fcf4883058bb9337632f1fe0ffad9a7065fe2d90c8a3a76fb9a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T08:58:00Z","title_canon_sha256":"153d867e7aa22f49f77187f72a699dde2824253fb7478a2501ff7eedd11633cb"},"schema_version":"1.0","source":{"id":"2601.22725","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22725","created_at":"2026-06-11T01:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22725v4","created_at":"2026-06-11T01:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22725","created_at":"2026-06-11T01:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"RG3XJSYD5PUA","created_at":"2026-06-11T01:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"RG3XJSYD5PUAEMF2","created_at":"2026-06-11T01:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"RG3XJSYD","created_at":"2026-06-11T01:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:99a1e264b3c54543df26afe955fb3e0bb41182f60c6333eb2592a6ae3a7ade41","target":"graph","created_at":"2026-06-11T01:09:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments."}],"snapshot_sha256":"ad857c3c766956369858fe77661d09771cc11962c3b8dcb68f7c53171b6d9c8f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7226196ab3f7a2ddf4d1d3c5e8e92af1d311906687f81573cf8ca4727afa6af2"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.22725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenhui Wu, Jingwen Luo, Jin Li, Kai Wen, Shuai Jiang, Siqi Yin, Tao Chen, Weijie Wang","cross_cats":["cs.AI"],"headline":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T08:58:00Z","title":"OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22725","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T09:44:52.030002Z","id":"6c9ffc3d-7792-4c2d-801b-16d49faeccb0","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"OpenVTON-Bench introduces a 100K-pair dataset and five-dimension protocol that correlates 0.833 with human VTON judgments.","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.","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."}},"verdict_id":"6c9ffc3d-7792-4c2d-801b-16d49faeccb0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1a4cd1e40a84eb3b874032a53f7e9c0d13e1e17a33c72e8f7ef253cfbb9c4048","target":"record","created_at":"2026-06-11T01:09:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"510d882433074fcf4883058bb9337632f1fe0ffad9a7065fe2d90c8a3a76fb9a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-30T08:58:00Z","title_canon_sha256":"153d867e7aa22f49f77187f72a699dde2824253fb7478a2501ff7eedd11633cb"},"schema_version":"1.0","source":{"id":"2601.22725","kind":"arxiv","version":4}},"canonical_sha256":"89b774cb03ebe80230badf18f34288c6babfc0f8e865260e41a78a016e131469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89b774cb03ebe80230badf18f34288c6babfc0f8e865260e41a78a016e131469","first_computed_at":"2026-06-11T01:09:27.885897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:27.885897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fBBq9wiNKFdwLwOG6obfRGIQROat/InOW6At8Y2/hvn+sDczIYq7EVtzcD+7RQF9Nm1rN3+R98heFKfA9zZTAQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:27.886990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22725","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a4cd1e40a84eb3b874032a53f7e9c0d13e1e17a33c72e8f7ef253cfbb9c4048","sha256:99a1e264b3c54543df26afe955fb3e0bb41182f60c6333eb2592a6ae3a7ade41"],"state_sha256":"4e19e78a4073f44c2e939f5b087f14b9c9351b332042a442294cda8f8bc95d7c"}