{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HK27RIZUBCXFEQWH7KAZYRH3AR","short_pith_number":"pith:HK27RIZU","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"},"canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","source":{"kind":"arxiv","id":"2606.31429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31429","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31429v1","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31429","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"HK27RIZUBCXF","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"HK27RIZUBCXFEQWH","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"HK27RIZU","created_at":"2026-07-01T01:18:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HK27RIZUBCXFEQWH7KAZYRH3AR","target":"record","payload":{"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"},"canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","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"},"source_kind":"arxiv","source_id":"2606.31429","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbu3+TUowHtXOAh6+g2ISN5G1mqnFxK3q0e8xl1yB1Ve17+k7P+zOxwby3Tk/rMKoKUTWZu8IJkEQBJ+IDAdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T22:17:39.501278Z"},"content_sha256":"953cebddc31b0a9739cc8cab8cd205423e5b2d7835be507409cf253eb27337da","schema_version":"1.0","event_id":"sha256:953cebddc31b0a9739cc8cab8cd205423e5b2d7835be507409cf253eb27337da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HK27RIZUBCXFEQWH7KAZYRH3AR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnuemTG4f1mmEHBkEt4QhxlpSaDZEWsFU5huoDhG9zEuXg9Uyr3I914RlbP4sNNeXXEEjQoXzLMDruGZagYNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T22:17:39.501665Z"},"content_sha256":"ca9caba941ba8ee65f3245f2dda647990513f3121ce14fabdc30e699da0bbe6d","schema_version":"1.0","event_id":"sha256:ca9caba941ba8ee65f3245f2dda647990513f3121ce14fabdc30e699da0bbe6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/bundle.json","state_url":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/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":"2026-07-04T22:17:39Z","links":{"resolver":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR","bundle":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/bundle.json","state":"https://pith.science/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HK27RIZUBCXFEQWH7KAZYRH3AR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HK27RIZUBCXFEQWH7KAZYRH3AR","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":"d73d36ffec9928cced4d8f7aa0096fc26e678134d4498ac5d00c3aebbf899461","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-30T09:54:32Z","title_canon_sha256":"6571c5412e6514c62077b8f48f39c755f2518f4c6a0d806430bf3370037cb6ed"},"schema_version":"1.0","source":{"id":"2606.31429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31429","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31429v1","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31429","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"HK27RIZUBCXF","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"HK27RIZUBCXFEQWH","created_at":"2026-07-01T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"HK27RIZU","created_at":"2026-07-01T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:ca9caba941ba8ee65f3245f2dda647990513f3121ce14fabdc30e699da0bbe6d","target":"graph","created_at":"2026-07-01T01:18:02Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.31429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guillaume Lecu\\'e, Taiji Suzuki, Tomoya Wakayama, Zong Shang","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-30T09:54:32Z","title":"The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31429","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:953cebddc31b0a9739cc8cab8cd205423e5b2d7835be507409cf253eb27337da","target":"record","created_at":"2026-07-01T01:18:02Z","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":"d73d36ffec9928cced4d8f7aa0096fc26e678134d4498ac5d00c3aebbf899461","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-30T09:54:32Z","title_canon_sha256":"6571c5412e6514c62077b8f48f39c755f2518f4c6a0d806430bf3370037cb6ed"},"schema_version":"1.0","source":{"id":"2606.31429","kind":"arxiv","version":1}},"canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ab5f8a33408ae5242c7fa819c44fb044f75fec72e13a0642a5499b4021cc621","first_computed_at":"2026-07-01T01:18:02.964952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:02.964952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"edgtT4vNKA3LXRHaC8kqQbaj2ooz8DR9AoKaUkT52DNAQfQeaRFkVBQfGoXcgOTtG+dR5a55zlbbze5MWh8RDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:02.965396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:953cebddc31b0a9739cc8cab8cd205423e5b2d7835be507409cf253eb27337da","sha256:ca9caba941ba8ee65f3245f2dda647990513f3121ce14fabdc30e699da0bbe6d"],"state_sha256":"8fddef97955954149791b7ceea383643fde4d82c153fd44158db42322b6a55fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnNbUA7ko8DiWr/J3K/XeKTYCmWYlF5yqQaAOZ2HwuVu/HVOR/LBS1bWTLuPO0T+g5z/R9dMc7TLbqOvdRi1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T22:17:39.503709Z","bundle_sha256":"08e52009c4e6b16953474e45fc37193739dd73a8c287412806528909e0e7b12a"}}