{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6J435JFEV4NLMP43G5M6KCYQVZ","short_pith_number":"pith:6J435JFE","canonical_record":{"source":{"id":"2512.16768","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-18T17:02:11Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"d2c2ac94d61b772aa6089a2667560162c8035f6767c8f86976629e208297ca01","abstract_canon_sha256":"1777a5b347d51d56be82ab65fde97044914f89ddff14aa6beb10ae9db2452f22"},"schema_version":"1.0"},"canonical_sha256":"f279bea4a4af1ab63f9b3759e50b10ae6a6d391e17a31605acbd355285c6e9c8","source":{"kind":"arxiv","id":"2512.16768","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.16768","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2512.16768v3","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16768","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"6J435JFEV4NL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6J435JFEV4NLMP43","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6J435JFE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6J435JFEV4NLMP43G5M6KCYQVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2512.16768","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-18T17:02:11Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"d2c2ac94d61b772aa6089a2667560162c8035f6767c8f86976629e208297ca01","abstract_canon_sha256":"1777a5b347d51d56be82ab65fde97044914f89ddff14aa6beb10ae9db2452f22"},"schema_version":"1.0"},"canonical_sha256":"f279bea4a4af1ab63f9b3759e50b10ae6a6d391e17a31605acbd355285c6e9c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.458053Z","signature_b64":"FJeMtQagfDyah9gHVs80q6Wnyf+CjPSgDlvIhIq8/dJ6PHZLnMLFPtUrpQzMmTo0zyWTA5J1Z9N3ELjc1a7SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f279bea4a4af1ab63f9b3759e50b10ae6a6d391e17a31605acbd355285c6e9c8","last_reissued_at":"2026-05-17T23:39:00.456667Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.456667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.16768","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUPrtj4fh38vdvk/wJdIe9NzM0YJ5CfIOJUCgP9eZUI0o8l/0SH9KUgDzowDClNvKDkQ2uhz/xYgAyEdKI+JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:42:33.152269Z"},"content_sha256":"e7bd255fea2909ca7bed512ff431e3cde6ec390e8eea1a5226b2ad3a5b8c60a2","schema_version":"1.0","event_id":"sha256:e7bd255fea2909ca7bed512ff431e3cde6ec390e8eea1a5226b2ad3a5b8c60a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6J435JFEV4NLMP43G5M6KCYQVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On The Hidden Biases of Flow Matching Samplers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics.","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Soon Hoe Lim","submitted_at":"2025-12-18T17:02:11Z","abstract_excerpt":"Flow matching (FM) constructs continuous-time ODE samplers by prescribing probability paths between a base distribution and a target distribution. In this note, we study FM through the lens of finite-sample plug-in estimation. In addition to replacing population expectations by sample averages, one may replace the target distribution itself by a finite-sample surrogate, ranging from the empirical measure to a smoothed estimator. This viewpoint yields a natural hierarchy of empirical FM models. For affine conditional flows, we derive the exact empirical minimizer and identify a smoothed plug-in"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For affine conditional flows, the exact empirical minimizer is derived and a smoothed plug-in regime yields a terminal law that is exactly a kernel-mixture estimator; fixed empirical marginal paths admit explicit flux-null corrections to the dynamics.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The derivations rely on the assumption that conditional flows are affine and that the plug-in hierarchy (empirical measure to smoothed estimators) is the appropriate finite-sample surrogate for the target distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2ab19ae71eca591c2dc7ca934b7efba8250ce2a252fee759024bf802c05c6b5a"},"source":{"id":"2512.16768","kind":"arxiv","version":3},"verdict":{"id":"49bf0e41-d169-4d8f-8d0a-21b5b0d6da5d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:07:49.314302Z","strongest_claim":"For affine conditional flows, the exact empirical minimizer is derived and a smoothed plug-in regime yields a terminal law that is exactly a kernel-mixture estimator; fixed empirical marginal paths admit explicit flux-null corrections to the dynamics.","one_line_summary":"Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The derivations rely on the assumption that conditional flows are affine and that the plug-in hierarchy (empirical measure to smoothed estimators) is the appropriate finite-sample surrogate for the target distribution.","pith_extraction_headline":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics."},"references":{"count":51,"sample":[{"doi":"","year":2023,"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","ref_index":1,"cited_arxiv_id":"2303.08797","is_internal_anchor":true},{"doi":"","year":2024,"title":"Learning to sample better.Journal of Sta- tistical Mechanics: Theory and Experiment, 2024(10):104014, 2024","work_id":"3a28ec8d-e876-4551-9765-a963959c2595","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Luigi Ambrosio, Nicola Gigli, and Giuseppe Savar´ e.Gradient Flows: In Metric Spaces And In the Space of Probability Measures. Springer, 2005","work_id":"ff0367eb-04df-49e7-b46f-98256146af93","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Bronstein, Pierre Vandergheynst, and Adam Gosztolai","work_id":"ee05999c-81fb-4b6a-9c95-17162e808ef0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Memorization and regularization in generative diffusion models.arXiv preprint arXiv:2501.15785","work_id":"75eadb61-366e-4504-8594-81b162cdb5d7","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":51,"snapshot_sha256":"d44f3c32292c883a0972487576f65f6588fcc1fedd24357f167ca6a673c244b8","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2171e4cae468b9d0a93c8dfc9a7073102242e4bcb15dac490cecacce1ab323ab"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"49bf0e41-d169-4d8f-8d0a-21b5b0d6da5d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UY0PyE/O3s9whLeV379GgiLv0v2i/gvVm9CzrfQAad1ydmaGxnlbw0cDykI2GjfSddzoy+4ZmqhzxS4m0rzdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:42:33.153485Z"},"content_sha256":"6dae79140775000fb1443d0b8182d2cbdbac814b441542645532d4e08d6a748b","schema_version":"1.0","event_id":"sha256:6dae79140775000fb1443d0b8182d2cbdbac814b441542645532d4e08d6a748b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6J435JFEV4NLMP43G5M6KCYQVZ/bundle.json","state_url":"https://pith.science/pith/6J435JFEV4NLMP43G5M6KCYQVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6J435JFEV4NLMP43G5M6KCYQVZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T08:42:33Z","links":{"resolver":"https://pith.science/pith/6J435JFEV4NLMP43G5M6KCYQVZ","bundle":"https://pith.science/pith/6J435JFEV4NLMP43G5M6KCYQVZ/bundle.json","state":"https://pith.science/pith/6J435JFEV4NLMP43G5M6KCYQVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6J435JFEV4NLMP43G5M6KCYQVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6J435JFEV4NLMP43G5M6KCYQVZ","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":"1777a5b347d51d56be82ab65fde97044914f89ddff14aa6beb10ae9db2452f22","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-18T17:02:11Z","title_canon_sha256":"d2c2ac94d61b772aa6089a2667560162c8035f6767c8f86976629e208297ca01"},"schema_version":"1.0","source":{"id":"2512.16768","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.16768","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2512.16768v3","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16768","created_at":"2026-05-17T23:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"6J435JFEV4NL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6J435JFEV4NLMP43","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6J435JFE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6dae79140775000fb1443d0b8182d2cbdbac814b441542645532d4e08d6a748b","target":"graph","created_at":"2026-05-17T23:39:00Z","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":"For affine conditional flows, the exact empirical minimizer is derived and a smoothed plug-in regime yields a terminal law that is exactly a kernel-mixture estimator; fixed empirical marginal paths admit explicit flux-null corrections to the dynamics."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The derivations rely on the assumption that conditional flows are affine and that the plug-in hierarchy (empirical measure to smoothed estimators) is the appropriate finite-sample surrogate for the target distribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics."}],"snapshot_sha256":"2ab19ae71eca591c2dc7ca934b7efba8250ce2a252fee759024bf802c05c6b5a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2171e4cae468b9d0a93c8dfc9a7073102242e4bcb15dac490cecacce1ab323ab"},"paper":{"abstract_excerpt":"Flow matching (FM) constructs continuous-time ODE samplers by prescribing probability paths between a base distribution and a target distribution. In this note, we study FM through the lens of finite-sample plug-in estimation. In addition to replacing population expectations by sample averages, one may replace the target distribution itself by a finite-sample surrogate, ranging from the empirical measure to a smoothed estimator. This viewpoint yields a natural hierarchy of empirical FM models. For affine conditional flows, we derive the exact empirical minimizer and identify a smoothed plug-in","authors_text":"Soon Hoe Lim","cross_cats":["cs.LG","math.PR"],"headline":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-18T17:02:11Z","title":"On The Hidden Biases of Flow Matching Samplers"},"references":{"count":51,"internal_anchors":7,"resolved_work":51,"sample":[{"cited_arxiv_id":"2303.08797","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Learning to sample better.Journal of Sta- tistical Mechanics: Theory and Experiment, 2024(10):104014, 2024","work_id":"3a28ec8d-e876-4551-9765-a963959c2595","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Luigi Ambrosio, Nicola Gigli, and Giuseppe Savar´ e.Gradient Flows: In Metric Spaces And In the Space of Probability Measures. Springer, 2005","work_id":"ff0367eb-04df-49e7-b46f-98256146af93","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bronstein, Pierre Vandergheynst, and Adam Gosztolai","work_id":"ee05999c-81fb-4b6a-9c95-17162e808ef0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Memorization and regularization in generative diffusion models.arXiv preprint arXiv:2501.15785","work_id":"75eadb61-366e-4504-8594-81b162cdb5d7","year":2025}],"snapshot_sha256":"d44f3c32292c883a0972487576f65f6588fcc1fedd24357f167ca6a673c244b8"},"source":{"id":"2512.16768","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T21:07:49.314302Z","id":"49bf0e41-d169-4d8f-8d0a-21b5b0d6da5d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Replacing the target distribution with finite-sample surrogates in flow matching introduces three coupled biases that alter learned paths and dynamics.","strongest_claim":"For affine conditional flows, the exact empirical minimizer is derived and a smoothed plug-in regime yields a terminal law that is exactly a kernel-mixture estimator; fixed empirical marginal paths admit explicit flux-null corrections to the dynamics.","weakest_assumption":"The derivations rely on the assumption that conditional flows are affine and that the plug-in hierarchy (empirical measure to smoothed estimators) is the appropriate finite-sample surrogate for the target distribution."}},"verdict_id":"49bf0e41-d169-4d8f-8d0a-21b5b0d6da5d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e7bd255fea2909ca7bed512ff431e3cde6ec390e8eea1a5226b2ad3a5b8c60a2","target":"record","created_at":"2026-05-17T23:39:00Z","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":"1777a5b347d51d56be82ab65fde97044914f89ddff14aa6beb10ae9db2452f22","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-12-18T17:02:11Z","title_canon_sha256":"d2c2ac94d61b772aa6089a2667560162c8035f6767c8f86976629e208297ca01"},"schema_version":"1.0","source":{"id":"2512.16768","kind":"arxiv","version":3}},"canonical_sha256":"f279bea4a4af1ab63f9b3759e50b10ae6a6d391e17a31605acbd355285c6e9c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f279bea4a4af1ab63f9b3759e50b10ae6a6d391e17a31605acbd355285c6e9c8","first_computed_at":"2026-05-17T23:39:00.456667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:00.456667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJeMtQagfDyah9gHVs80q6Wnyf+CjPSgDlvIhIq8/dJ6PHZLnMLFPtUrpQzMmTo0zyWTA5J1Z9N3ELjc1a7SCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:00.458053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.16768","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7bd255fea2909ca7bed512ff431e3cde6ec390e8eea1a5226b2ad3a5b8c60a2","sha256:6dae79140775000fb1443d0b8182d2cbdbac814b441542645532d4e08d6a748b"],"state_sha256":"624c1a590477a8ae31097828461c91635efdd383b6983971a9eaa77c65c80b33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZT92hMznRR8OzIl3mKS4tmexltQMK/cnYELuFmYwgx4dhX2+hf6mAC7yph/lJl9NTDcvbpLUEweGhvLKwHUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T08:42:33.159731Z","bundle_sha256":"7a606fdb588a57ace506c4a724fae959003e7bb5f40ec76ba9eada306dd6d7f7"}}