{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDCQ5IT2DPZZVVSS6XRUJC7UOL","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":"10abfdef1b415dff3ab1aa5ed9c64aca67dd2a3207110c238a4689c3cfa17cac","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:29:44Z","title_canon_sha256":"13d37a7846389cfcca67d31a522784abbd975f8b5b32ab3b1e014d8df87ba55f"},"schema_version":"1.0","source":{"id":"2605.11755","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11755","created_at":"2026-05-28T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11755v2","created_at":"2026-05-28T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11755","created_at":"2026-05-28T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"GDCQ5IT2DPZZ","created_at":"2026-05-28T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"GDCQ5IT2DPZZVVSS","created_at":"2026-05-28T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"GDCQ5IT2","created_at":"2026-05-28T01:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:77f629ef36a528c314585e01ec49c47eb453b9ac45b474b355bce08351086c55","target":"graph","created_at":"2026-05-28T01:04:42Z","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":"W-Flow sets a new state of the art for one-step ImageNet 256×256 generation, achieving 1.29 FID, with improved mode coverage and domain transfer. Compared to multi-step diffusion models with similar FID scores, our method yields approximately 100× faster sampling."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The finite-sample training dynamics converge to the continuous-time distributional dynamics under suitable assumptions. The abstract does not specify what those assumptions are or how restrictive they become for high-dimensional image data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x faster sampling than comparable multi-step models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"W-Flow achieves one-step ImageNet 256x256 generation at 1.29 FID by training a neural network to compress a Wasserstein gradient flow."}],"snapshot_sha256":"f49202fd16680ff92c1e7a0541d7d09da39a86c0e243932cbe5011af1b8c1b19"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5eeb61be50437f2a8759e6004c47fc79a351107ed377f67c11d7a1fa4d357efb"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-26T16:44:37.194405Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T23:01:32.129423Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T13:35:05.618476Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T03:42:00.372557Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.11755/integrity.json","findings":[],"snapshot_sha256":"60b651350770a5e68272ec22fb204f4b8b311cefe7e932da65750a7886ec2cf1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updates. We introduce W-Flow, a framework for training a generator that transforms samples from a simple reference distribution into samples from a target data distribution in a single step. This is achieved in two steps: we first define an evolution from the reference distribution to the target distribution through a Wasserstein gradient flow that minimizes an energy functional; second, we train a static neural generator","authors_text":"Emmanuel J. Cand\\`es, Jiaqi Han, Puheng Li, Qiushan Guo, Renyuan Xu, Stefano Ermon","cross_cats":["cs.CV","stat.ML"],"headline":"W-Flow achieves one-step ImageNet 256x256 generation at 1.29 FID by training a neural network to compress a Wasserstein gradient flow.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:29:44Z","title":"One-Step Generative Modeling via Wasserstein Gradient Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11755","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T07:41:20.795142Z","id":"2f08913a-a3ad-4db0-ada8-0f78ec4869ed","model_set":{"reader":"grok-4.3"},"one_line_summary":"W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x faster sampling than comparable multi-step models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"W-Flow achieves one-step ImageNet 256x256 generation at 1.29 FID by training a neural network to compress a Wasserstein gradient flow.","strongest_claim":"W-Flow sets a new state of the art for one-step ImageNet 256×256 generation, achieving 1.29 FID, with improved mode coverage and domain transfer. Compared to multi-step diffusion models with similar FID scores, our method yields approximately 100× faster sampling.","weakest_assumption":"The finite-sample training dynamics converge to the continuous-time distributional dynamics under suitable assumptions. The abstract does not specify what those assumptions are or how restrictive they become for high-dimensional image data."}},"verdict_id":"2f08913a-a3ad-4db0-ada8-0f78ec4869ed"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a02488b4927a3c1c60bc4679e4c236a963e7018f8a27bea41e434038fbfd6a1e","target":"record","created_at":"2026-05-28T01:04:42Z","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":"10abfdef1b415dff3ab1aa5ed9c64aca67dd2a3207110c238a4689c3cfa17cac","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:29:44Z","title_canon_sha256":"13d37a7846389cfcca67d31a522784abbd975f8b5b32ab3b1e014d8df87ba55f"},"schema_version":"1.0","source":{"id":"2605.11755","kind":"arxiv","version":2}},"canonical_sha256":"30c50ea27a1bf39ad652f5e3448bf472de9df646ee9eea9bfaadf0cc6be1a80a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c50ea27a1bf39ad652f5e3448bf472de9df646ee9eea9bfaadf0cc6be1a80a","first_computed_at":"2026-05-28T01:04:42.241787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:42.241787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11UQ5KWogOsxKFMLOLvGGQAGTvUrPYRf2Ofq4cI9n1ndowmUaHj550sV7/wPeC3wt6E8AVKp/i7FBghND4YPBg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:42.242236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11755","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a02488b4927a3c1c60bc4679e4c236a963e7018f8a27bea41e434038fbfd6a1e","sha256:77f629ef36a528c314585e01ec49c47eb453b9ac45b474b355bce08351086c55"],"state_sha256":"e940a76e67a0b03c41464a0ee27729e034c6d423d588a9de5ecb424abbb33287"}