{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HNL4SXOSQEFIOUXMCEFOHL6WZM","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":"faa62c54dedd59d9528eaca1d33a86149319046b926d75da7027c8f68a874361","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math-ph","math.MP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-10-25T08:08:44Z","title_canon_sha256":"9889d638e0682d309227d50ff93e61c7504f50feb83c548c315070c4fa4f063d"},"schema_version":"1.0","source":{"id":"2310.16441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16441","created_at":"2026-07-05T07:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16441v1","created_at":"2026-07-05T07:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16441","created_at":"2026-07-05T07:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"HNL4SXOSQEFI","created_at":"2026-07-05T07:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"HNL4SXOSQEFIOUXM","created_at":"2026-07-05T07:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"HNL4SXOS","created_at":"2026-07-05T07:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:2b93197ca0de7e7adbb8db3ab1688b57acb4a8b3a11e84f227f754cacfde1227","target":"graph","created_at":"2026-07-05T07:40:58Z","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/2310.16441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grokking is the intriguing phenomenon where a model learns to generalize long after it has fit the training data. We show both analytically and numerically that grokking can surprisingly occur in linear networks performing linear tasks in a simple teacher-student setup with Gaussian inputs. In this setting, the full training dynamics is derived in terms of the training and generalization data covariance matrix. We present exact predictions on how the grokking time depends on input and output dimensionality, train sample size, regularization, and network initialization. We demonstrate that the ","authors_text":"Alon Beck, Noam Levi, Yohai Bar-Sinai","cross_cats":["cond-mat.dis-nn","cs.LG","math-ph","math.MP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-10-25T08:08:44Z","title":"Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16441","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":"sha256:8dd7fbc9e21d6196b66f76adea9ae15fe2bc1b1e4d561a9ee9e8926d7cd1ab8b","target":"record","created_at":"2026-07-05T07:40:58Z","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":"faa62c54dedd59d9528eaca1d33a86149319046b926d75da7027c8f68a874361","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math-ph","math.MP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-10-25T08:08:44Z","title_canon_sha256":"9889d638e0682d309227d50ff93e61c7504f50feb83c548c315070c4fa4f063d"},"schema_version":"1.0","source":{"id":"2310.16441","kind":"arxiv","version":1}},"canonical_sha256":"3b57c95dd2810a8752ec110ae3afd6cb3911487a12883de69b8751d0d23d8a24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b57c95dd2810a8752ec110ae3afd6cb3911487a12883de69b8751d0d23d8a24","first_computed_at":"2026-07-05T07:40:58.148396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:58.148396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VfxnIoQiGYllwh7lILO1eS9fEszQftjXBgKUa5065Thsj25JcxhpTXonDfD9qeygdAxfuEYpMUocgMNuueFzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:58.148820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dd7fbc9e21d6196b66f76adea9ae15fe2bc1b1e4d561a9ee9e8926d7cd1ab8b","sha256:2b93197ca0de7e7adbb8db3ab1688b57acb4a8b3a11e84f227f754cacfde1227"],"state_sha256":"f1268ef6a8ecd16e484ed319e8a2705d8ebe82e43134cae31c97c09f98549a60"}