{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PI545JQOFIFHXWIBFPX4DA45CC","short_pith_number":"pith:PI545JQO","schema_version":"1.0","canonical_sha256":"7a3bcea60e2a0a7bd9012befc1839d1090c46eb76e9a59059ed70261a254fcb1","source":{"kind":"arxiv","id":"2405.20066","version":1},"attestation_state":"computed","paper":{"title":"A theory of stratification learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.DG","stat.TH"],"primary_cat":"math.ST","authors_text":"Cl\\'ement Berenfeld, Eddie Aamari","submitted_at":"2024-05-30T13:56:55Z","abstract_excerpt":"Given i.i.d. sample from a stratified mixture of immersed manifolds of different dimensions, we study the minimax estimation of the underlying stratified structure. We provide a constructive algorithm allowing to estimate each mixture component at its optimal dimension-specific rate adaptively. The method is based on an ascending hierarchical co-detection of points belonging to different layers, which also identifies the number of layers and their dimensions, assigns each data point to a layer accurately, and estimates tangent spaces optimally. These results hold regardless of any ambient assu"},"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":false},"canonical_record":{"source":{"id":"2405.20066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2024-05-30T13:56:55Z","cross_cats_sorted":["math.DG","stat.TH"],"title_canon_sha256":"03b76cd3da5c06ca0684b7a9d957f77ae4417a7b7c9041abad73c1fa1dce9edf","abstract_canon_sha256":"042d5f6b2b7094910a6ae28ed94ae31c92a702728f2eedb6fe9e274671f1d78b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:15.778238Z","signature_b64":"f556UFoHdeMQOhUaI2HD3pTQwh5K7vGBV56tMy/N1UBk1tYn0cEIUeP4q2Dg+3VFBIBKvWif7q0vluaxWXcEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a3bcea60e2a0a7bd9012befc1839d1090c46eb76e9a59059ed70261a254fcb1","last_reissued_at":"2026-07-05T08:25:15.777819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:15.777819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A theory of stratification learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.DG","stat.TH"],"primary_cat":"math.ST","authors_text":"Cl\\'ement Berenfeld, Eddie Aamari","submitted_at":"2024-05-30T13:56:55Z","abstract_excerpt":"Given i.i.d. sample from a stratified mixture of immersed manifolds of different dimensions, we study the minimax estimation of the underlying stratified structure. We provide a constructive algorithm allowing to estimate each mixture component at its optimal dimension-specific rate adaptively. The method is based on an ascending hierarchical co-detection of points belonging to different layers, which also identifies the number of layers and their dimensions, assigns each data point to a layer accurately, and estimates tangent spaces optimally. These results hold regardless of any ambient assu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20066","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.20066/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2405.20066","created_at":"2026-07-05T08:25:15.777875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20066v1","created_at":"2026-07-05T08:25:15.777875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20066","created_at":"2026-07-05T08:25:15.777875+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI545JQOFIFH","created_at":"2026-07-05T08:25:15.777875+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI545JQOFIFHXWIB","created_at":"2026-07-05T08:25:15.777875+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI545JQO","created_at":"2026-07-05T08:25:15.777875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22356","citing_title":"Manifold Fitting: A Review of Methods and Applications","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18215","citing_title":"Tangent Blow-Ups for Processing Non-Manifold Geometry","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18215","citing_title":"Tangent Blow-Ups for Processing Non-Manifold Geometry","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC","json":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC.json","graph_json":"https://pith.science/api/pith-number/PI545JQOFIFHXWIBFPX4DA45CC/graph.json","events_json":"https://pith.science/api/pith-number/PI545JQOFIFHXWIBFPX4DA45CC/events.json","paper":"https://pith.science/paper/PI545JQO"},"agent_actions":{"view_html":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC","download_json":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC.json","view_paper":"https://pith.science/paper/PI545JQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20066&json=true","fetch_graph":"https://pith.science/api/pith-number/PI545JQOFIFHXWIBFPX4DA45CC/graph.json","fetch_events":"https://pith.science/api/pith-number/PI545JQOFIFHXWIBFPX4DA45CC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC/action/storage_attestation","attest_author":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC/action/author_attestation","sign_citation":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC/action/citation_signature","submit_replication":"https://pith.science/pith/PI545JQOFIFHXWIBFPX4DA45CC/action/replication_record"}},"created_at":"2026-07-05T08:25:15.777875+00:00","updated_at":"2026-07-05T08:25:15.777875+00:00"}