{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APWY3XO675ZRPR24A6MWBQ25ZR","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":"52c478084dca5140a0b0cf72542291c6125a9fb43e307d1a4cf0bb2e3c5d7422","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-30T17:55:28Z","title_canon_sha256":"80551ca997cfddc7fd7a8293d034c812009498d059456be16e35719ce8a5823d"},"schema_version":"1.0","source":{"id":"2310.19793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19793","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19793v2","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19793","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"APWY3XO675ZR","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"APWY3XO675ZRPR24","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"APWY3XO6","created_at":"2026-07-05T07:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:0dc571234b36d824216383ad869cca37324d8dce5fda37c7eaafbbb4310e190f","target":"graph","created_at":"2026-07-05T07:08:13Z","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/2310.19793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study gradient flow on the multi-index regression problem for high-dimensional Gaussian data. Multi-index functions consist of a composition of an unknown low-rank linear projection and an arbitrary unknown, low-dimensional link function. As such, they constitute a natural template for feature learning in neural networks.\n  We consider a two-timescale algorithm, whereby the low-dimensional link function is learnt with a non-parametric model infinitely faster than the subspace parametrizing the low-rank projection. By appropriately exploiting the matrix semigroup structure arising over the s","authors_text":"Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-30T17:55:28Z","title":"On Learning Gaussian Multi-index Models with Gradient Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19793","kind":"arxiv","version":2},"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:efd731fd25258b14542bb029afdfcdc1bfea179199d238184e1f8a2e753b6f58","target":"record","created_at":"2026-07-05T07:08:13Z","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":"52c478084dca5140a0b0cf72542291c6125a9fb43e307d1a4cf0bb2e3c5d7422","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-30T17:55:28Z","title_canon_sha256":"80551ca997cfddc7fd7a8293d034c812009498d059456be16e35719ce8a5823d"},"schema_version":"1.0","source":{"id":"2310.19793","kind":"arxiv","version":2}},"canonical_sha256":"03ed8ddddeff7317c75c079960c35dcc42ecd47c673a844fde99059f856d0773","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03ed8ddddeff7317c75c079960c35dcc42ecd47c673a844fde99059f856d0773","first_computed_at":"2026-07-05T07:08:13.853377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:13.853377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0be3kKQbMHmqd/X2NMW0U5FHhnrLsWbKDSeSNAHKK9S+qAWn18ygNeqOEK7WDOeNfNjLeNgkwEpNVM7pypIRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:13.853884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efd731fd25258b14542bb029afdfcdc1bfea179199d238184e1f8a2e753b6f58","sha256:0dc571234b36d824216383ad869cca37324d8dce5fda37c7eaafbbb4310e190f"],"state_sha256":"36e3d3abf530968f12c182a6ed33045ab3e166acc2cfd08cd437fba55291a652"}