{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IJW66WYFLJHZMKSQ4MP7HDEGNC","short_pith_number":"pith:IJW66WYF","canonical_record":{"source":{"id":"2405.15459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:34:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85aeedcd43e88f427fc5d3f6d8a95f044336e2f44682da55ad8392a239c11ed8","abstract_canon_sha256":"31989f22ef822b3322c0a90b4a979554aff1b44a4cde9f6e0cfda9cfdf79a17b"},"schema_version":"1.0"},"canonical_sha256":"426def5b055a4f962a50e31ff38c8668bed85cb2dc87b35bb0e23d9336d640b5","source":{"kind":"arxiv","id":"2405.15459","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15459","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15459v2","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15459","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"IJW66WYFLJHZ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"IJW66WYFLJHZMKSQ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"IJW66WYF","created_at":"2026-07-05T10:11:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IJW66WYFLJHZMKSQ4MP7HDEGNC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:34:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85aeedcd43e88f427fc5d3f6d8a95f044336e2f44682da55ad8392a239c11ed8","abstract_canon_sha256":"31989f22ef822b3322c0a90b4a979554aff1b44a4cde9f6e0cfda9cfdf79a17b"},"schema_version":"1.0"},"canonical_sha256":"426def5b055a4f962a50e31ff38c8668bed85cb2dc87b35bb0e23d9336d640b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:19.773458Z","signature_b64":"JwNTRWotdKB7fqKSilyxzEh2Vd9MU3YK9N93SXYUtfAHbhWkAYdazppi/GtvXbplbVh6Bp+j86yV9vfCgLIIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426def5b055a4f962a50e31ff38c8668bed85cb2dc87b35bb0e23d9336d640b5","last_reissued_at":"2026-07-05T10:11:19.772923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:19.772923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15459","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHtnGwwpMTZg8usv7VxrSnSNwLxv95fSzteyf54tlizPn4J7ExkJU7lZdc1apeksdHE534n+rXb84NtB++6nAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:38.637249Z"},"content_sha256":"6ea92bea277bdd614852c952bdf05a7a6690018f05198a24551500af73650bfc","schema_version":"1.0","event_id":"sha256:6ea92bea277bdd614852c952bdf05a7a6690018f05198a24551500af73650bfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IJW66WYFLJHZMKSQ4MP7HDEGNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Florent Krzakala, Luca Arnaboldi, Luca Pesce, Ludovic Stephan, Yatin Dandi","submitted_at":"2024-05-24T11:34:31Z","abstract_excerpt":"Neural networks can identify low-dimensional relevant structures within high-dimensional noisy data, yet our mathematical understanding of how they do so remains scarce. Here, we investigate the training dynamics of two-layer shallow neural networks trained with gradient-based algorithms, and discuss how they learn pertinent features in multi-index models, that is target functions with low-dimensional relevant directions. In the high-dimensional regime, where the input dimension $d$ diverges, we show that a simple modification of the idealized single-pass gradient descent training scenario, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15459","kind":"arxiv","version":2},"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/2405.15459/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":"2026-07-05T10:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQUGftaiLmMQXp5JUSnxLeQE0OE1cnBLfvJHZPrN56G6pgTF1Id++hYMIBwPQMQqpa3NRsWgkQQQXXncDF2oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:38.637749Z"},"content_sha256":"c6e05eee8ba7e89bbef0cd6ebf7368a9ffeb4e6787d99522e68c0b87771fe82a","schema_version":"1.0","event_id":"sha256:c6e05eee8ba7e89bbef0cd6ebf7368a9ffeb4e6787d99522e68c0b87771fe82a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/bundle.json","state_url":"https://pith.science/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/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":"2026-08-08T09:38:38Z","links":{"resolver":"https://pith.science/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC","bundle":"https://pith.science/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/bundle.json","state":"https://pith.science/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJW66WYFLJHZMKSQ4MP7HDEGNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IJW66WYFLJHZMKSQ4MP7HDEGNC","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":"31989f22ef822b3322c0a90b4a979554aff1b44a4cde9f6e0cfda9cfdf79a17b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:34:31Z","title_canon_sha256":"85aeedcd43e88f427fc5d3f6d8a95f044336e2f44682da55ad8392a239c11ed8"},"schema_version":"1.0","source":{"id":"2405.15459","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15459","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15459v2","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15459","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"IJW66WYFLJHZ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"IJW66WYFLJHZMKSQ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"IJW66WYF","created_at":"2026-07-05T10:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:c6e05eee8ba7e89bbef0cd6ebf7368a9ffeb4e6787d99522e68c0b87771fe82a","target":"graph","created_at":"2026-07-05T10:11:19Z","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/2405.15459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks can identify low-dimensional relevant structures within high-dimensional noisy data, yet our mathematical understanding of how they do so remains scarce. Here, we investigate the training dynamics of two-layer shallow neural networks trained with gradient-based algorithms, and discuss how they learn pertinent features in multi-index models, that is target functions with low-dimensional relevant directions. In the high-dimensional regime, where the input dimension $d$ diverges, we show that a simple modification of the idealized single-pass gradient descent training scenario, wh","authors_text":"Florent Krzakala, Luca Arnaboldi, Luca Pesce, Ludovic Stephan, Yatin Dandi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:34:31Z","title":"Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15459","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":"sha256:6ea92bea277bdd614852c952bdf05a7a6690018f05198a24551500af73650bfc","target":"record","created_at":"2026-07-05T10:11:19Z","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":"31989f22ef822b3322c0a90b4a979554aff1b44a4cde9f6e0cfda9cfdf79a17b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:34:31Z","title_canon_sha256":"85aeedcd43e88f427fc5d3f6d8a95f044336e2f44682da55ad8392a239c11ed8"},"schema_version":"1.0","source":{"id":"2405.15459","kind":"arxiv","version":2}},"canonical_sha256":"426def5b055a4f962a50e31ff38c8668bed85cb2dc87b35bb0e23d9336d640b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"426def5b055a4f962a50e31ff38c8668bed85cb2dc87b35bb0e23d9336d640b5","first_computed_at":"2026-07-05T10:11:19.772923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:19.772923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JwNTRWotdKB7fqKSilyxzEh2Vd9MU3YK9N93SXYUtfAHbhWkAYdazppi/GtvXbplbVh6Bp+j86yV9vfCgLIIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:19.773458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15459","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ea92bea277bdd614852c952bdf05a7a6690018f05198a24551500af73650bfc","sha256:c6e05eee8ba7e89bbef0cd6ebf7368a9ffeb4e6787d99522e68c0b87771fe82a"],"state_sha256":"f922861358e6d068cf12d6d153bf1c425c8caa7d875d5eb74d36ef5ab5b65a86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZN9flklVO07a3XamO1dYJhrQZlzVp82aOLTcHhvddMwSpASGrH80ArQzcsv3Rv1MPn8T7VTuYsrZ+8/0D2G3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:38:38.641661Z","bundle_sha256":"8337a06e1bef143ecfe343d2a93cd035044b90bf62a29ac42bbb981d9d85cd0f"}}