{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LX6JF7ZZ3Q46D2O43BGC46FNRX","short_pith_number":"pith:LX6JF7ZZ","schema_version":"1.0","canonical_sha256":"5dfc92ff39dc39e1e9dcd84c2e78ad8ddd475dc715e131a89e23c9019ff32d1d","source":{"kind":"arxiv","id":"2310.17247","version":2},"attestation_state":"computed","paper":{"title":"Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles O'Neill, Jack Miller, Thang Bui","submitted_at":"2023-10-26T08:47:42Z","abstract_excerpt":"In some settings neural networks exhibit a phenomenon known as \\textit{grokking}, where they achieve perfect or near-perfect accuracy on the validation set long after the same performance has been achieved on the training set. In this paper, we discover that grokking is not limited to neural networks but occurs in other settings such as Gaussian process (GP) classification, GP regression, linear regression and Bayesian neural networks. We also uncover a mechanism by which to induce grokking on algorithmic datasets via the addition of dimensions containing spurious information. The presence of "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.17247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T08:47:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46c2efd1f5ade5349f1f020503b8fecc4313238f3c6e4f59119b102943d68983","abstract_canon_sha256":"70bddf5df4d6be9497912fc13f3ed192b01214591e353403f11a8178085b6606"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:47.209040Z","signature_b64":"8f8Ov6kf7NnOF+rN6dcR6u4bV3RAC8vcx7P/l0E5kA42dDorEL6NtH0Xx8+f2oK8gNBr/iZ4jfrwdV7J6TiXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dfc92ff39dc39e1e9dcd84c2e78ad8ddd475dc715e131a89e23c9019ff32d1d","last_reissued_at":"2026-07-05T08:02:47.208451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:47.208451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles O'Neill, Jack Miller, Thang Bui","submitted_at":"2023-10-26T08:47:42Z","abstract_excerpt":"In some settings neural networks exhibit a phenomenon known as \\textit{grokking}, where they achieve perfect or near-perfect accuracy on the validation set long after the same performance has been achieved on the training set. In this paper, we discover that grokking is not limited to neural networks but occurs in other settings such as Gaussian process (GP) classification, GP regression, linear regression and Bayesian neural networks. We also uncover a mechanism by which to induce grokking on algorithmic datasets via the addition of dimensions containing spurious information. The presence of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17247","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.17247/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.17247","created_at":"2026-07-05T08:02:47.208520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17247v2","created_at":"2026-07-05T08:02:47.208520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17247","created_at":"2026-07-05T08:02:47.208520+00:00"},{"alias_kind":"pith_short_12","alias_value":"LX6JF7ZZ3Q46","created_at":"2026-07-05T08:02:47.208520+00:00"},{"alias_kind":"pith_short_16","alias_value":"LX6JF7ZZ3Q46D2O4","created_at":"2026-07-05T08:02:47.208520+00:00"},{"alias_kind":"pith_short_8","alias_value":"LX6JF7ZZ","created_at":"2026-07-05T08:02:47.208520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23286","citing_title":"Not All Explanations for Deep Learning Phenomena Are Equally Valuable","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX","json":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX.json","graph_json":"https://pith.science/api/pith-number/LX6JF7ZZ3Q46D2O43BGC46FNRX/graph.json","events_json":"https://pith.science/api/pith-number/LX6JF7ZZ3Q46D2O43BGC46FNRX/events.json","paper":"https://pith.science/paper/LX6JF7ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX","download_json":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX.json","view_paper":"https://pith.science/paper/LX6JF7ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17247&json=true","fetch_graph":"https://pith.science/api/pith-number/LX6JF7ZZ3Q46D2O43BGC46FNRX/graph.json","fetch_events":"https://pith.science/api/pith-number/LX6JF7ZZ3Q46D2O43BGC46FNRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX/action/storage_attestation","attest_author":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX/action/author_attestation","sign_citation":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX/action/citation_signature","submit_replication":"https://pith.science/pith/LX6JF7ZZ3Q46D2O43BGC46FNRX/action/replication_record"}},"created_at":"2026-07-05T08:02:47.208520+00:00","updated_at":"2026-07-05T08:02:47.208520+00:00"}