{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O5P6KSCEFHFQXSSQTIVHFKGCDN","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":"b532421b8f4378c4dd151d3ef4d6239d310db511bd2eae54e00ff00764df6178","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T19:05:11Z","title_canon_sha256":"4eb954adde346ad63ccc3255864db0eae49a791cb24699547cd4794320753caf"},"schema_version":"1.0","source":{"id":"2405.19454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19454","created_at":"2026-07-05T08:25:23Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19454v1","created_at":"2026-07-05T08:25:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19454","created_at":"2026-07-05T08:25:23Z"},{"alias_kind":"pith_short_12","alias_value":"O5P6KSCEFHFQ","created_at":"2026-07-05T08:25:23Z"},{"alias_kind":"pith_short_16","alias_value":"O5P6KSCEFHFQXSSQ","created_at":"2026-07-05T08:25:23Z"},{"alias_kind":"pith_short_8","alias_value":"O5P6KSCE","created_at":"2026-07-05T08:25:23Z"}],"graph_snapshots":[{"event_id":"sha256:222a01c793c90484a6e11e86feb4a72f940e9618bdee298f91b6b8cda0ba448d","target":"graph","created_at":"2026-07-05T08:25:23Z","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/2405.19454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research on the grokking phenomenon has illuminated the intricacies of neural networks' training dynamics and their generalization behaviors. Grokking refers to a sharp rise of the network's generalization accuracy on the test set, which occurs long after an extended overfitting phase, during which the network perfectly fits the training set. While the existing research primarily focus on shallow networks such as 2-layer MLP and 1-layer Transformer, we explore grokking on deep networks (e.g. 12-layer MLP). We empirically replicate the phenomenon and find that deep neural networks can be","authors_text":"Martin Jaggi, Razvan Pascanu, Simin Fan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T19:05:11Z","title":"Deep Grokking: Would Deep Neural Networks Generalize Better?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19454","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":"sha256:23650306eb91703dd570c2f83e18699074f5ddd14c785887e2395f116255b59f","target":"record","created_at":"2026-07-05T08:25:23Z","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":"b532421b8f4378c4dd151d3ef4d6239d310db511bd2eae54e00ff00764df6178","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T19:05:11Z","title_canon_sha256":"4eb954adde346ad63ccc3255864db0eae49a791cb24699547cd4794320753caf"},"schema_version":"1.0","source":{"id":"2405.19454","kind":"arxiv","version":1}},"canonical_sha256":"775fe5484429cb0bca509a2a72a8c21b58a1528af1e2558b65ea15dd435de067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"775fe5484429cb0bca509a2a72a8c21b58a1528af1e2558b65ea15dd435de067","first_computed_at":"2026-07-05T08:25:23.344290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:23.344290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l6gkWbr0OpPFb5Kmthltchgwo5QN5QP0YFnAe7sM+nhV0Vx+5S3apF0IuUacBzH/KRyDbXB96OJrDu6Xs4hxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:23.344747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23650306eb91703dd570c2f83e18699074f5ddd14c785887e2395f116255b59f","sha256:222a01c793c90484a6e11e86feb4a72f940e9618bdee298f91b6b8cda0ba448d"],"state_sha256":"5534420999c4dc69072de663bf91147da5c477ee5d0849e2f73062f1f4c7b9f5"}