{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BIDBUGJOSISRNGVTUCWCERJZEE","short_pith_number":"pith:BIDBUGJO","schema_version":"1.0","canonical_sha256":"0a061a192e9225169ab3a0ac2245392102d27807ef958cf6cd44e180b9ff8b62","source":{"kind":"arxiv","id":"2604.07213","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Processes on Implicit Manifolds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Point-cloud diffusions converge in law to their manifold counterparts as sample size increases.","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Adam Gosztolai, Clara Grotehans, Pierre Vandergheynst, Victor Kawasaki-Borruat","submitted_at":"2026-04-08T15:34:21Z","abstract_excerpt":"High-dimensional data are often assumed to lie on lower-dimensional manifolds. We study how to construct diffusion processes on this data manifold using only point cloud samples and without access to charts, projections, or other geometric primitives. Here, we introduce Implicit Manifold-valued Diffusions (IMDs), a data-driven mathematical formalism for defining stochastic differential equations in the original high-dimensional space that describe drifting Brownian particles evolving intrinsically on the underlying manifold. Our construction hinges on approximating the corresponding infinitesi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2604.07213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-08T15:34:21Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"2455bd6303c850c9fc4993c8f02e4eb009a9a9763e1923e57098deafdd334a47","abstract_canon_sha256":"1825f78f8d3f8fa0a9c9c5bf71aa4f12c2fec5323b512a61f5712445670690f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:18.685670Z","signature_b64":"eyDQ3MrLTqkA2oUELClCRR4QRUROOi/HXwmmUxdsb/mW74McZ90wtyY5+4GIFGu5P96EwCmln/l5Mkc3M1ENDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a061a192e9225169ab3a0ac2245392102d27807ef958cf6cd44e180b9ff8b62","last_reissued_at":"2026-05-21T01:05:18.684915Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:18.684915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Processes on Implicit Manifolds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Point-cloud diffusions converge in law to their manifold counterparts as sample size increases.","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Adam Gosztolai, Clara Grotehans, Pierre Vandergheynst, Victor Kawasaki-Borruat","submitted_at":"2026-04-08T15:34:21Z","abstract_excerpt":"High-dimensional data are often assumed to lie on lower-dimensional manifolds. We study how to construct diffusion processes on this data manifold using only point cloud samples and without access to charts, projections, or other geometric primitives. Here, we introduce Implicit Manifold-valued Diffusions (IMDs), a data-driven mathematical formalism for defining stochastic differential equations in the original high-dimensional space that describe drifting Brownian particles evolving intrinsically on the underlying manifold. Our construction hinges on approximating the corresponding infinitesi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that, as the number of samples grows, the induced process converges in law on the space of probability paths to its smooth manifold counterpart.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The point cloud is sampled from a distribution supported near a smooth low-dimensional manifold, and the proximity graph built from the data sufficiently approximates the intrinsic geometry and diffusion operator on that manifold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Implicit Manifold-valued Diffusions (IMDs) are data-driven SDEs built from proximity graphs that converge in law to smooth manifold diffusions as sample count increases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Point-cloud diffusions converge in law to their manifold counterparts as sample size increases.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0e568d31051374c0a7bb704f6cf02dcaa124cd397e74862a10ca89d812980219"},"source":{"id":"2604.07213","kind":"arxiv","version":2},"verdict":{"id":"e2778c89-337b-4abb-aa0c-88f58d537cf3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:07:46.476998Z","strongest_claim":"We show that, as the number of samples grows, the induced process converges in law on the space of probability paths to its smooth manifold counterpart.","one_line_summary":"Implicit Manifold-valued Diffusions (IMDs) are data-driven SDEs built from proximity graphs that converge in law to smooth manifold diffusions as sample count increases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The point cloud is sampled from a distribution supported near a smooth low-dimensional manifold, and the proximity graph built from the data sufficiently approximates the intrinsic geometry and diffusion operator on that manifold.","pith_extraction_headline":"Point-cloud diffusions converge in law to their manifold counterparts as sample size increases."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07213/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"920648b93467ad06a42ce6deb8627ff526e11789767089957e3c055b882c4bc4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.07213","created_at":"2026-05-21T01:05:18.685004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.07213v2","created_at":"2026-05-21T01:05:18.685004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07213","created_at":"2026-05-21T01:05:18.685004+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIDBUGJOSISR","created_at":"2026-05-21T01:05:18.685004+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIDBUGJOSISRNGVT","created_at":"2026-05-21T01:05:18.685004+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIDBUGJO","created_at":"2026-05-21T01:05:18.685004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15524","citing_title":"Neural Point-Forms","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE","json":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE.json","graph_json":"https://pith.science/api/pith-number/BIDBUGJOSISRNGVTUCWCERJZEE/graph.json","events_json":"https://pith.science/api/pith-number/BIDBUGJOSISRNGVTUCWCERJZEE/events.json","paper":"https://pith.science/paper/BIDBUGJO"},"agent_actions":{"view_html":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE","download_json":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE.json","view_paper":"https://pith.science/paper/BIDBUGJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.07213&json=true","fetch_graph":"https://pith.science/api/pith-number/BIDBUGJOSISRNGVTUCWCERJZEE/graph.json","fetch_events":"https://pith.science/api/pith-number/BIDBUGJOSISRNGVTUCWCERJZEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE/action/storage_attestation","attest_author":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE/action/author_attestation","sign_citation":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE/action/citation_signature","submit_replication":"https://pith.science/pith/BIDBUGJOSISRNGVTUCWCERJZEE/action/replication_record"}},"created_at":"2026-05-21T01:05:18.685004+00:00","updated_at":"2026-05-21T01:05:18.685004+00:00"}