{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OCV424MJ6YKPAX7ZTLRT36RRDV","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":"d2ecaee5ff61e4374b10042df9344eaa0df2bab6134b8122c6a23f7d3b7794b1","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-12T17:01:25Z","title_canon_sha256":"1acb967c2cb31b79649ad1a2f6f14f667e150a58759159be6858c50a21d623bf"},"schema_version":"1.0","source":{"id":"2404.08602","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08602","created_at":"2026-07-05T09:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08602v2","created_at":"2026-07-05T09:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08602","created_at":"2026-07-05T09:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"OCV424MJ6YKP","created_at":"2026-07-05T09:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"OCV424MJ6YKPAX7Z","created_at":"2026-07-05T09:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"OCV424MJ","created_at":"2026-07-05T09:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:d85fe9c996eb64487099c2d9aeb65c06ab84863c52f54c38cbbc97141e7db09d","target":"graph","created_at":"2026-07-05T09:20:42Z","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/2404.08602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks extract features from data using stochastic gradient descent (SGD). In particular, higher-order input cumulants (HOCs) are crucial for their performance. However, extracting information from the $p$th cumulant of $d$-dimensional inputs is computationally hard: the number of samples required to recover a single direction from an order-$p$ tensor (tensor PCA) using online SGD grows as $d^{p-1}$, which is prohibitive for high-dimensional inputs. This result raises the question of how neural networks extract relevant directions from the HOCs of their inputs efficiently. Here, we sh","authors_text":"Lorenzo Bardone, Sebastian Goldt","cross_cats":["cond-mat.stat-mech","cs.LG","math.PR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-12T17:01:25Z","title":"Sliding down the stairs: how correlated latent variables accelerate learning with neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08602","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":"sha256:79643973390fbaa1cf97a5410e87eb84429ee7b5604072cc3a5d261481b9b31c","target":"record","created_at":"2026-07-05T09:20:42Z","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":"d2ecaee5ff61e4374b10042df9344eaa0df2bab6134b8122c6a23f7d3b7794b1","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-12T17:01:25Z","title_canon_sha256":"1acb967c2cb31b79649ad1a2f6f14f667e150a58759159be6858c50a21d623bf"},"schema_version":"1.0","source":{"id":"2404.08602","kind":"arxiv","version":2}},"canonical_sha256":"70abcd7189f614f05ff99ae33dfa311d792fe39b07f083ae2b714d357bb2024a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70abcd7189f614f05ff99ae33dfa311d792fe39b07f083ae2b714d357bb2024a","first_computed_at":"2026-07-05T09:20:42.226736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:42.226736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OoamsvSid1X3JJ9Do/9P1KqDbs+DDLrlpXw54kB9FWZ7wnSY6CR7kYXu2Bdw1yCfm2XeOfoeEF6u+hZFv97UCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:42.227155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08602","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79643973390fbaa1cf97a5410e87eb84429ee7b5604072cc3a5d261481b9b31c","sha256:d85fe9c996eb64487099c2d9aeb65c06ab84863c52f54c38cbbc97141e7db09d"],"state_sha256":"e1acba80ef07b5848c214a926cf4e53f3131a8673f45115fe3422898717f253b"}