{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:77KEEUB7EWTVP6F7T5G33DLRGR","short_pith_number":"pith:77KEEUB7","schema_version":"1.0","canonical_sha256":"ffd442503f25a757f8bf9f4dbd8d713466946810ee4c92e90fe942cbacb026af","source":{"kind":"arxiv","id":"2605.14659","version":1},"attestation_state":"computed","paper":{"title":"Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert No, Kyelim Lee, Shin So","submitted_at":"2026-05-14T10:12:49Z","abstract_excerpt":"Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, additional data should accelerate validation convergence. We show that this intuition can fail in a controlled structured-output task. In Needleman--Wunsch (NW) matrix generation, small Transformers reach high validation exact-match accuracy fastest at an intermediate dataset size, not at the largest one. Past this dataset-size sweet spot, generalization remains achievable but requires more gradient updates. Conversely, in the regime where partia"},"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":"2605.14659","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T10:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"e2d4884d6ee9aea51325b5ed88b24cd08114050b2739d054d0d4af4db633e81b","abstract_canon_sha256":"8b2d445800e3a69b83d3adff298d3cd2f82358cacfa952cd723c33d769fed3bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:02.212944Z","signature_b64":"wNX3PgN8nlmapK4Pmoi0l7ZCHik+gJM+hml1ouEG6+lU9is1C656ZsMtpNSqajp+W8YB3DuaBHcylwmZFdZMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffd442503f25a757f8bf9f4dbd8d713466946810ee4c92e90fe942cbacb026af","last_reissued_at":"2026-05-17T23:39:02.212235Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:02.212235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert No, Kyelim Lee, Shin So","submitted_at":"2026-05-14T10:12:49Z","abstract_excerpt":"Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, additional data should accelerate validation convergence. We show that this intuition can fail in a controlled structured-output task. In Needleman--Wunsch (NW) matrix generation, small Transformers reach high validation exact-match accuracy fastest at an intermediate dataset size, not at the largest one. Past this dataset-size sweet spot, generalization remains achievable but requires more gradient updates. Conversely, in the regime where partia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14659","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2605.14659","created_at":"2026-05-17T23:39:02.212340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14659v1","created_at":"2026-05-17T23:39:02.212340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14659","created_at":"2026-05-17T23:39:02.212340+00:00"},{"alias_kind":"pith_short_12","alias_value":"77KEEUB7EWTV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"77KEEUB7EWTVP6F7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"77KEEUB7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR","json":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR.json","graph_json":"https://pith.science/api/pith-number/77KEEUB7EWTVP6F7T5G33DLRGR/graph.json","events_json":"https://pith.science/api/pith-number/77KEEUB7EWTVP6F7T5G33DLRGR/events.json","paper":"https://pith.science/paper/77KEEUB7"},"agent_actions":{"view_html":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR","download_json":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR.json","view_paper":"https://pith.science/paper/77KEEUB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14659&json=true","fetch_graph":"https://pith.science/api/pith-number/77KEEUB7EWTVP6F7T5G33DLRGR/graph.json","fetch_events":"https://pith.science/api/pith-number/77KEEUB7EWTVP6F7T5G33DLRGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR/action/storage_attestation","attest_author":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR/action/author_attestation","sign_citation":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR/action/citation_signature","submit_replication":"https://pith.science/pith/77KEEUB7EWTVP6F7T5G33DLRGR/action/replication_record"}},"created_at":"2026-05-17T23:39:02.212340+00:00","updated_at":"2026-05-17T23:39:02.212340+00:00"}