{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UI5O5LZYHODE2GTPLL3MPA7JYO","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":"8152fabc43c0d8ac26acf4aff87461351dcb1a8e9f499cd08b7194e7fc1e6700","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T03:34:40Z","title_canon_sha256":"d2aaa81a9bcb98c658dcf83cbc55d11939f28260ca6c1d6e1581fd48a82a8fac"},"schema_version":"1.0","source":{"id":"2605.12951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12951","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12951v1","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12951","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"UI5O5LZYHODE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UI5O5LZYHODE2GTP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UI5O5LZY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1385372ff17c018645526ad3046277293295adf01df5428da7567fd43080240c","target":"graph","created_at":"2026-05-18T03:09:09Z","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":"We prove that the surrogate transport cost equals the target--surrogate Wasserstein gap under an explicit compression assumption, whereas the noise-source analogue has a dimension-scale lower bound. We further characterize the conditional second moment of the direct surrogate-source training target and show that its source-dependent excess is small when the surrogate conditional law is close to the true conditional velocity law in mean and covariance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The explicit compression assumption that the coreset-derived Gaussian mixture surrogate sufficiently approximates the target velocity distribution so that the residual correction remains lightweight and the second-moment excess stays small."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CCVFM replaces the inner noise source in hierarchical rectified flow matching with a data-informed Gaussian mixture surrogate from a Sinkhorn coreset, yielding a closed-form conditional velocity law and competitive few-step generation on MNIST, CIFAR-10, ImageNet-32, and CelebA-HQ."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A coreset-derived Gaussian mixture surrogate replaces isotropic noise in conditional velocity flow matching and equals the target-surrogate Wasserstein gap as transport cost."}],"snapshot_sha256":"1e0dfafb39063b24f95df5ef567e219b1da279b851558731a50d56579037b6fe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"594e919564e51f6fa5e21db8893ec24572fec0003b5ac24bcff2cf2ba60f48f5"},"paper":{"abstract_excerpt":"We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution. Hierarchical flow matching models the full conditional velocity law in velocity space, but its inner flow is asked to transport isotropic Gaussian noise to a multimodal target velocity distribution from scratch. Our key observation is that this inner source can be replaced by a closed-form surrogate built from a coreset of the target. CCVFM first compresses the target into weighted atoms using an entropic Sinkhorn coreset ","authors_text":"Jianxi Su, Xiao Wang, Zihua She","cross_cats":["cs.LG"],"headline":"A coreset-derived Gaussian mixture surrogate replaces isotropic noise in conditional velocity flow matching and equals the target-surrogate Wasserstein gap as transport cost.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T03:34:40Z","title":"Coreset-Induced Conditional Velocity Flow Matching"},"references":{"count":33,"internal_anchors":2,"resolved_work":33,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Stochastic interpolants: A unifying framework for flows and diffusions.Journal of Machine Learning Research, 26(209):1–80, 2025","work_id":"de67e3e2-0833-42ff-9811-8e8aba9ce4c7","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Reconstructing training data with informed adversaries","work_id":"7114b5ec-863a-4a52-a373-1fd855ec2bbc","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Pros and cons of GAN evaluation measures","work_id":"6b163ab9-b909-4947-9e26-b1c169457ee6","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Extracting training data from diffusion models","work_id":"06d16fb5-0847-44cf-9994-315dbbc65150","year":2023},{"cited_arxiv_id":"1707.08819","doi":"","is_internal_anchor":true,"ref_index":5,"title":"A downsampled variant of imagenet as an alternative to the CIFAR datasets","work_id":"b28da76e-30a0-4103-a956-55ca47f3e243","year":2017}],"snapshot_sha256":"5a7d15e1971cb900ec2d686a8ed63320674634ab65f119c9a063999ed599a51c"},"source":{"id":"2605.12951","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:52:26.806431Z","id":"ed2ac339-632b-452d-bbfc-92b0c32cd570","model_set":{"reader":"grok-4.3"},"one_line_summary":"CCVFM replaces the inner noise source in hierarchical rectified flow matching with a data-informed Gaussian mixture surrogate from a Sinkhorn coreset, yielding a closed-form conditional velocity law and competitive few-step generation on MNIST, CIFAR-10, ImageNet-32, and CelebA-HQ.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A coreset-derived Gaussian mixture surrogate replaces isotropic noise in conditional velocity flow matching and equals the target-surrogate Wasserstein gap as transport cost.","strongest_claim":"We prove that the surrogate transport cost equals the target--surrogate Wasserstein gap under an explicit compression assumption, whereas the noise-source analogue has a dimension-scale lower bound. We further characterize the conditional second moment of the direct surrogate-source training target and show that its source-dependent excess is small when the surrogate conditional law is close to the true conditional velocity law in mean and covariance.","weakest_assumption":"The explicit compression assumption that the coreset-derived Gaussian mixture surrogate sufficiently approximates the target velocity distribution so that the residual correction remains lightweight and the second-moment excess stays small."}},"verdict_id":"ed2ac339-632b-452d-bbfc-92b0c32cd570"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b078d499fa9207bfc855538dc2a6011911d7d75020a957138681e8bde03a1e54","target":"record","created_at":"2026-05-18T03:09:09Z","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":"8152fabc43c0d8ac26acf4aff87461351dcb1a8e9f499cd08b7194e7fc1e6700","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T03:34:40Z","title_canon_sha256":"d2aaa81a9bcb98c658dcf83cbc55d11939f28260ca6c1d6e1581fd48a82a8fac"},"schema_version":"1.0","source":{"id":"2605.12951","kind":"arxiv","version":1}},"canonical_sha256":"a23aeeaf383b864d1a6f5af6c783e9c39f826d5db7efcd3923355576dc0dce87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a23aeeaf383b864d1a6f5af6c783e9c39f826d5db7efcd3923355576dc0dce87","first_computed_at":"2026-05-18T03:09:09.405626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:09.405626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GZp3+3s9gOs4YziDXQCikmC1igipC2W1XPQOZH+IK17vs96tGT9RnWW8ax4g2sU3DRveKicTCE4eTvYiIPWjBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:09.406531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b078d499fa9207bfc855538dc2a6011911d7d75020a957138681e8bde03a1e54","sha256:1385372ff17c018645526ad3046277293295adf01df5428da7567fd43080240c"],"state_sha256":"0ea1de9c9458b8df282643a965ce09a7c99c596312b599b4b3e7c27ad7030146"}