{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WXDY6METDSIF2HLDIYUQHTTDZ","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":"bd3f286e3c11d5898e820be62ab2aaf792a3e086e0b618b2ede58b016d8fee80","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T06:15:30Z","title_canon_sha256":"ce53d89f308c52112a6e76df45ca91ff08f7f8602a486853339720d6d8c33ded"},"schema_version":"1.0","source":{"id":"2407.12332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12332","created_at":"2026-07-05T08:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12332v1","created_at":"2026-07-05T08:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12332","created_at":"2026-07-05T08:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"7WXDY6METDSI","created_at":"2026-07-05T08:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"7WXDY6METDSIF2HL","created_at":"2026-07-05T08:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"7WXDY6ME","created_at":"2026-07-05T08:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:72dce2e2a13e0db8ae233d24edd0abcf0b75031ac300bd4c31bd9e9d7326fc9d","target":"graph","created_at":"2026-07-05T08:45:03Z","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/2407.12332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a theoretical explanation of the ``grokking'' phenomenon, where a model generalizes long after overfitting,for the originally-studied problem of modular addition. First, we show that early in gradient descent, when the ``kernel regime'' approximately holds, no permutation-equivariant model can achieve small population error on modular addition unless it sees at least a constant fraction of all possible data points. Eventually, however, models escape the kernel regime. We show that two-layer quadratic networks that achieve zero training loss with bounded $\\ell_{\\infty}$ norm generali","authors_text":"Danica J. Sutherland, Lei Wu, Mohamad Amin Mohamadi, Zhiyuan Li","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T06:15:30Z","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12332","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":"sha256:3922facdbad868fcfb6a8a4da5a3aeffe3304197b1b06dc806d6924952cc2778","target":"record","created_at":"2026-07-05T08:45:03Z","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":"bd3f286e3c11d5898e820be62ab2aaf792a3e086e0b618b2ede58b016d8fee80","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T06:15:30Z","title_canon_sha256":"ce53d89f308c52112a6e76df45ca91ff08f7f8602a486853339720d6d8c33ded"},"schema_version":"1.0","source":{"id":"2407.12332","kind":"arxiv","version":1}},"canonical_sha256":"fdae3c798498e482e8eb1a31481e731e583839d4587d060dbadf8ee3e4d31f78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdae3c798498e482e8eb1a31481e731e583839d4587d060dbadf8ee3e4d31f78","first_computed_at":"2026-07-05T08:45:03.020215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:03.020215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2mDYspa+AXgQ+E1m3ogGJN8xVKzlX0d0G20bRlkdsKSvkhjTZEKmxWq6Q5YmNBhLWT8CYNRqphp01buvhzImCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:03.020698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3922facdbad868fcfb6a8a4da5a3aeffe3304197b1b06dc806d6924952cc2778","sha256:72dce2e2a13e0db8ae233d24edd0abcf0b75031ac300bd4c31bd9e9d7326fc9d"],"state_sha256":"80608e00974031c7f44f93fd09d5dc24528627954e85d280d96a6f7847d21b69"}