{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HK27RIZUBCXFEQWH7KAZYRH3AR","short_pith_number":"pith:HK27RIZU","schema_version":"1.0","canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","source":{"kind":"arxiv","id":"2606.31429","version":1},"attestation_state":"computed","paper":{"title":"The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guillaume Lecu\\'e, Taiji Suzuki, Tomoya Wakayama, Zong Shang","submitted_at":"2026-06-30T09:54:32Z","abstract_excerpt":"We introduce a geometric formulation of statistical feature learning for supervised regression. Feature learning is defined through a base--fiber decomposition: the base is the feature-side geometry produced by training, and the fiber is the learned feature space where estimation is performed. We prove this property for spherical mean-field Langevin dynamics, viewed as the Wasserstein gradient flow of a negative entropy-regularized empirical risk. In Gaussian multi-index models, the low-temperature stationary distribution concentrates near the hidden indices, forms a multi-spike structure, and"},"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":"2606.31429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-30T09:54:32Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"6571c5412e6514c62077b8f48f39c755f2518f4c6a0d806430bf3370037cb6ed","abstract_canon_sha256":"d73d36ffec9928cced4d8f7aa0096fc26e678134d4498ac5d00c3aebbf899461"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:02.965396Z","signature_b64":"edgtT4vNKA3LXRHaC8kqQbaj2ooz8DR9AoKaUkT52DNAQfQeaRFkVBQfGoXcgOTtG+dR5a55zlbbze5MWh8RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","last_reissued_at":"2026-07-01T01:18:02.964952Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:02.964952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guillaume Lecu\\'e, Taiji Suzuki, Tomoya Wakayama, Zong Shang","submitted_at":"2026-06-30T09:54:32Z","abstract_excerpt":"We introduce a geometric formulation of statistical feature learning for supervised regression. Feature learning is defined through a base--fiber decomposition: the base is the feature-side geometry produced by training, and the fiber is the learned feature space where estimation is performed. We prove this property for spherical mean-field Langevin dynamics, viewed as the Wasserstein gradient flow of a negative entropy-regularized empirical risk. In Gaussian multi-index models, the low-temperature stationary distribution concentrates near the hidden indices, forms a multi-spike structure, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31429","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/2606.31429/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":"2606.31429","created_at":"2026-07-01T01:18:02.965017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31429v1","created_at":"2026-07-01T01:18:02.965017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31429","created_at":"2026-07-01T01:18:02.965017+00:00"},{"alias_kind":"pith_short_12","alias_value":"HK27RIZUBCXF","created_at":"2026-07-01T01:18:02.965017+00:00"},{"alias_kind":"pith_short_16","alias_value":"HK27RIZUBCXFEQWH","created_at":"2026-07-01T01:18:02.965017+00:00"},{"alias_kind":"pith_short_8","alias_value":"HK27RIZU","created_at":"2026-07-01T01:18:02.965017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR","json":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR.json","graph_json":"https://pith.science/api/pith-number/HK27RIZUBCXFEQWH7KAZYRH3AR/graph.json","events_json":"https://pith.science/api/pith-number/HK27RIZUBCXFEQWH7KAZYRH3AR/events.json","paper":"https://pith.science/paper/HK27RIZU"},"agent_actions":{"view_html":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR","download_json":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR.json","view_paper":"https://pith.science/paper/HK27RIZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31429&json=true","fetch_graph":"https://pith.science/api/pith-number/HK27RIZUBCXFEQWH7KAZYRH3AR/graph.json","fetch_events":"https://pith.science/api/pith-number/HK27RIZUBCXFEQWH7KAZYRH3AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/action/storage_attestation","attest_author":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/action/author_attestation","sign_citation":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/action/citation_signature","submit_replication":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/action/replication_record"}},"created_at":"2026-07-01T01:18:02.965017+00:00","updated_at":"2026-07-01T01:18:02.965017+00:00"}