{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V7GVDYOC5IWBH42Q7LOSPHHMSO","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":"1aa32da03452656e8146a3c254ee6e0c5471f12c4b3f755561833ad0ab373bc5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T02:30:51Z","title_canon_sha256":"48f4140ba4fc1718735a140be23ca8cdbcb1ec19619abcdadc0e08be6d292db6"},"schema_version":"1.0","source":{"id":"2301.11500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11500","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11500v1","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11500","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"V7GVDYOC5IWB","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"V7GVDYOC5IWBH42Q","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"V7GVDYOC","created_at":"2026-07-05T05:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:d69da2bf417e1aec4b1393cd9fd7db442504e8061fa76c49dcf6eaa56a81409b","target":"graph","created_at":"2026-07-05T05:36:22Z","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/2301.11500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal is to recover a low-rank ground-truth matrix from near-isotropic linear measurements. It is shown that GD with small initialization behaves similarly to the greedy low-rank learning heuristics (Li et al., 2020) and follows an incremental learning procedure (Gissin et al., 2019): GD sequentially learns solutions with increasing ranks until it recovers the gr","authors_text":"Jason D. Lee, Jikai Jin, Kaifeng Lyu, Simon S. Du, Zhiyuan Li","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T02:30:51Z","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11500","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":"sha256:439a8bb3671696b463c0a00d6c08a587434cbdf11d61e549b9cd9feb82a5fb65","target":"record","created_at":"2026-07-05T05:36:22Z","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":"1aa32da03452656e8146a3c254ee6e0c5471f12c4b3f755561833ad0ab373bc5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T02:30:51Z","title_canon_sha256":"48f4140ba4fc1718735a140be23ca8cdbcb1ec19619abcdadc0e08be6d292db6"},"schema_version":"1.0","source":{"id":"2301.11500","kind":"arxiv","version":1}},"canonical_sha256":"afcd51e1c2ea2c13f350fadd279cec93849ef19230bf42048b6b14fb1d65aa9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afcd51e1c2ea2c13f350fadd279cec93849ef19230bf42048b6b14fb1d65aa9c","first_computed_at":"2026-07-05T05:36:22.866637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:22.866637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8DQTUTOzBOcfkFugXlV1bsF6BnY3TlBv/X7jkkC+plWifmlzbX/nxdpbFuXDZrCcbWOrKAvLTMCMye5rLpiQAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:22.867067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:439a8bb3671696b463c0a00d6c08a587434cbdf11d61e549b9cd9feb82a5fb65","sha256:d69da2bf417e1aec4b1393cd9fd7db442504e8061fa76c49dcf6eaa56a81409b"],"state_sha256":"dd5ad5361a3bada82cc8f4a8ffaef3fef3c1517d99676cd11671cad48c7b6c69"}