{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2CMPZYAL5GI652OFBDTWOJ22SR","short_pith_number":"pith:2CMPZYAL","canonical_record":{"source":{"id":"2604.24226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-04-27T09:33:52Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"b9ba38886e8889554d2873d35066f686e51ff0418e689d3e959dd55108cdaa1a","abstract_canon_sha256":"c98b952905cd45dd57b2459e06b31141d6343958f8153e3f27cc5f52bff80e7c"},"schema_version":"1.0"},"canonical_sha256":"d098fce00be991eee9c508e767275a944613f532112459d0d6a324a23270a213","source":{"kind":"arxiv","id":"2604.24226","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24226","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24226v2","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24226","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"2CMPZYAL5GI6","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"2CMPZYAL5GI652OF","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"2CMPZYAL","created_at":"2026-06-03T01:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2CMPZYAL5GI652OFBDTWOJ22SR","target":"record","payload":{"canonical_record":{"source":{"id":"2604.24226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-04-27T09:33:52Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"b9ba38886e8889554d2873d35066f686e51ff0418e689d3e959dd55108cdaa1a","abstract_canon_sha256":"c98b952905cd45dd57b2459e06b31141d6343958f8153e3f27cc5f52bff80e7c"},"schema_version":"1.0"},"canonical_sha256":"d098fce00be991eee9c508e767275a944613f532112459d0d6a324a23270a213","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:14.040803Z","signature_b64":"FD7zh+oeAM1HBBGqLqTnupPpJlAOINPqcN/FwT+zRlp6G/3R3TEeyev5IQrm5IMItBlUAhTPnTSl3vU3jwK5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d098fce00be991eee9c508e767275a944613f532112459d0d6a324a23270a213","last_reissued_at":"2026-06-03T01:05:14.040404Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:14.040404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.24226","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbJuIREuDeViUdNNlnZzlEYYnjA0GtTxX4N1kWi+0JDU/U3TEw8cen93x5H5VlqxEYPtLL9AzX36ekDJCUCOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T16:44:34.471476Z"},"content_sha256":"1a4fe420b0efe358fc10d4cb7d5022dbbab5fe8393c84172b5b5d17755b8ffce","schema_version":"1.0","event_id":"sha256:1a4fe420b0efe358fc10d4cb7d5022dbbab5fe8393c84172b5b5d17755b8ffce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2CMPZYAL5GI652OFBDTWOJ22SR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuum-marginal optimal transport: a mesh-free kernel method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals.","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Yumiharu Nakano","submitted_at":"2026-04-27T09:33:52Z","abstract_excerpt":"In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field whose flow reproduces every marginal. This problem is the continuum limit of the classical two-marginal Benamou--Brenier formulation, and also the deterministic limit of the Nelson problem of stochastic optimal transport. We propose a practical mesh-free solver for this problem. The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial disc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial discretization. The velocity is parametrized by any linear-in-parameters dictionary or neural network, and is optimized by mini-batch stochastic methods. Synthetic experiments confirm that the method achieves accurate drift recovery and marginal consistency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embedding the weak continuity equation in an RKHS produces an objective whose minimizer recovers the true velocity field from finite samples without additional regularization or post-hoc corrections.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A reproducing kernel Hilbert space embedding yields a sample-only objective for solving continuum-marginal optimal transport without spatial discretization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7605404ee5a00bcbc589a9bb9cc8cbf3ef0bf2c13c1ca33b1c96054c1d6f54f0"},"source":{"id":"2604.24226","kind":"arxiv","version":2},"verdict":{"id":"1d4933b6-d1b0-46ad-80e4-c122f7f3a719","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T02:39:28.080096Z","strongest_claim":"The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial discretization. The velocity is parametrized by any linear-in-parameters dictionary or neural network, and is optimized by mini-batch stochastic methods. Synthetic experiments confirm that the method achieves accurate drift recovery and marginal consistency.","one_line_summary":"A reproducing kernel Hilbert space embedding yields a sample-only objective for solving continuum-marginal optimal transport without spatial discretization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embedding the weak continuity equation in an RKHS produces an objective whose minimizer recovers the true velocity field from finite samples without additional regularization or post-hoc corrections.","pith_extraction_headline":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24226/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T07:35:45.909032Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:17:08.829833Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"32d1345abf9ed08bc81f7c3567c1b8499c073f8e8b8a8a5949219013d832596c"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1d4933b6-d1b0-46ad-80e4-c122f7f3a719"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEGt/fMz/zrDGl+MchjxYXRSdf8NpruHZ6Q+Y0ielmhDAId7nN5ZlNriQPNXkvV1l5/PKawr5qPcn4U8HG3RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T16:44:34.471978Z"},"content_sha256":"ef27fcbdd57ad0758eaf0302673f7a380f21f1cbcb950b055cc62a77af9f885f","schema_version":"1.0","event_id":"sha256:ef27fcbdd57ad0758eaf0302673f7a380f21f1cbcb950b055cc62a77af9f885f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CMPZYAL5GI652OFBDTWOJ22SR/bundle.json","state_url":"https://pith.science/pith/2CMPZYAL5GI652OFBDTWOJ22SR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CMPZYAL5GI652OFBDTWOJ22SR/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":"2026-06-20T16:44:34Z","links":{"resolver":"https://pith.science/pith/2CMPZYAL5GI652OFBDTWOJ22SR","bundle":"https://pith.science/pith/2CMPZYAL5GI652OFBDTWOJ22SR/bundle.json","state":"https://pith.science/pith/2CMPZYAL5GI652OFBDTWOJ22SR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CMPZYAL5GI652OFBDTWOJ22SR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CMPZYAL5GI652OFBDTWOJ22SR","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":"c98b952905cd45dd57b2459e06b31141d6343958f8153e3f27cc5f52bff80e7c","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-04-27T09:33:52Z","title_canon_sha256":"b9ba38886e8889554d2873d35066f686e51ff0418e689d3e959dd55108cdaa1a"},"schema_version":"1.0","source":{"id":"2604.24226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24226","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24226v2","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24226","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"2CMPZYAL5GI6","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"2CMPZYAL5GI652OF","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"2CMPZYAL","created_at":"2026-06-03T01:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:ef27fcbdd57ad0758eaf0302673f7a380f21f1cbcb950b055cc62a77af9f885f","target":"graph","created_at":"2026-06-03T01:05:14Z","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":"The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial discretization. The velocity is parametrized by any linear-in-parameters dictionary or neural network, and is optimized by mini-batch stochastic methods. Synthetic experiments confirm that the method achieves accurate drift recovery and marginal consistency."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That embedding the weak continuity equation in an RKHS produces an objective whose minimizer recovers the true velocity field from finite samples without additional regularization or post-hoc corrections."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A reproducing kernel Hilbert space embedding yields a sample-only objective for solving continuum-marginal optimal transport without spatial discretization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals."}],"snapshot_sha256":"7605404ee5a00bcbc589a9bb9cc8cbf3ef0bf2c13c1ca33b1c96054c1d6f54f0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T07:35:45.909032Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:17:08.829833Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.24226/integrity.json","findings":[],"snapshot_sha256":"32d1345abf9ed08bc81f7c3567c1b8499c073f8e8b8a8a5949219013d832596c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field whose flow reproduces every marginal. This problem is the continuum limit of the classical two-marginal Benamou--Brenier formulation, and also the deterministic limit of the Nelson problem of stochastic optimal transport. We propose a practical mesh-free solver for this problem. The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial disc","authors_text":"Yumiharu Nakano","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-04-27T09:33:52Z","title":"Continuum-marginal optimal transport: a mesh-free kernel method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.24226","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T02:39:28.080096Z","id":"1d4933b6-d1b0-46ad-80e4-c122f7f3a719","model_set":{"reader":"grok-4.3"},"one_line_summary":"A reproducing kernel Hilbert space embedding yields a sample-only objective for solving continuum-marginal optimal transport without spatial discretization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A reproducing kernel Hilbert space embedding of the weak continuity equation yields a sample-only objective for recovering minimum-energy velocity fields that match a continuum of probability marginals.","strongest_claim":"The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial discretization. The velocity is parametrized by any linear-in-parameters dictionary or neural network, and is optimized by mini-batch stochastic methods. Synthetic experiments confirm that the method achieves accurate drift recovery and marginal consistency.","weakest_assumption":"That embedding the weak continuity equation in an RKHS produces an objective whose minimizer recovers the true velocity field from finite samples without additional regularization or post-hoc corrections."}},"verdict_id":"1d4933b6-d1b0-46ad-80e4-c122f7f3a719"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1a4fe420b0efe358fc10d4cb7d5022dbbab5fe8393c84172b5b5d17755b8ffce","target":"record","created_at":"2026-06-03T01:05:14Z","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":"c98b952905cd45dd57b2459e06b31141d6343958f8153e3f27cc5f52bff80e7c","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-04-27T09:33:52Z","title_canon_sha256":"b9ba38886e8889554d2873d35066f686e51ff0418e689d3e959dd55108cdaa1a"},"schema_version":"1.0","source":{"id":"2604.24226","kind":"arxiv","version":2}},"canonical_sha256":"d098fce00be991eee9c508e767275a944613f532112459d0d6a324a23270a213","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d098fce00be991eee9c508e767275a944613f532112459d0d6a324a23270a213","first_computed_at":"2026-06-03T01:05:14.040404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:14.040404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FD7zh+oeAM1HBBGqLqTnupPpJlAOINPqcN/FwT+zRlp6G/3R3TEeyev5IQrm5IMItBlUAhTPnTSl3vU3jwK5DQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:14.040803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.24226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a4fe420b0efe358fc10d4cb7d5022dbbab5fe8393c84172b5b5d17755b8ffce","sha256:ef27fcbdd57ad0758eaf0302673f7a380f21f1cbcb950b055cc62a77af9f885f"],"state_sha256":"7fe2c946a51b9d4808653c35821f91fd194663d53fe10441b98354682e2cfa42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GxeEANR0ItdJrQUVHMqkW5etLzelLZ7AvBwAYxEx6QJQPVvVAJqqPlpMLwNChNBFypaLueXKWiDJt4ySDMLEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T16:44:34.474259Z","bundle_sha256":"9b2cbfda872113bfe2c3af84537d5eea9c2a341f5ed5fc9ff5cd234fced93582"}}