{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HH2OXD5XWTYSMEB7TY2ZR5APXZ","short_pith_number":"pith:HH2OXD5X","schema_version":"1.0","canonical_sha256":"39f4eb8fb7b4f126103f9e3598f40fbe5841bf5556f0fe1d82b68b1e79b0ea2b","source":{"kind":"arxiv","id":"2607.21866","version":1},"attestation_state":"computed","paper":{"title":"Scaling Laws for Classical Machine Learning on Tabular Data: A Benchmark Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaihua Ding","submitted_at":"2026-07-23T23:45:09Z","abstract_excerpt":"Prior classical-ML learning-curve work fits power laws to tree, linear, and kernel models on tabular data, but at small scale: typically one curve, one team, a handful of cells. We present a distributed classroom-scale replication: 127 students each ran a fixed protocol on 3 assigned datasets, drawn from 18 tabular classification and regression datasets and 6 model families (Boosting, Random Forest, SVM, Linear/Logistic, Ridge, Lasso), yielding 11,536 training runs and 1,648 fitted power-law curves of the form error(N) = a N^(-b) + c. Three findings. (1) Power laws fit: R^2 > 0.8 on 77.7% of c"},"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":"2607.21866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T23:45:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1c2aea9672584d36e3a6cfba5c7ca0dbf01473e388315487dab26092e6b042a0","abstract_canon_sha256":"6c7c9f9a47476069256701260e38ef3b0b1e3f7d8c5f36ad9e253427177ce0a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:25.050256Z","signature_b64":"S4jfwqXs0OxU19DBPCM6hAPUgUsTqr+MnRjk5AyCu6I3eBM6L7rYo7AcD8AeoY7T2aBEukHAKei3eh1lXX9LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f4eb8fb7b4f126103f9e3598f40fbe5841bf5556f0fe1d82b68b1e79b0ea2b","last_reissued_at":"2026-07-27T00:20:25.049434Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:25.049434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws for Classical Machine Learning on Tabular Data: A Benchmark Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaihua Ding","submitted_at":"2026-07-23T23:45:09Z","abstract_excerpt":"Prior classical-ML learning-curve work fits power laws to tree, linear, and kernel models on tabular data, but at small scale: typically one curve, one team, a handful of cells. We present a distributed classroom-scale replication: 127 students each ran a fixed protocol on 3 assigned datasets, drawn from 18 tabular classification and regression datasets and 6 model families (Boosting, Random Forest, SVM, Linear/Logistic, Ridge, Lasso), yielding 11,536 training runs and 1,648 fitted power-law curves of the form error(N) = a N^(-b) + c. Three findings. (1) Power laws fit: R^2 > 0.8 on 77.7% of c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21866","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.21866/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":"2607.21866","created_at":"2026-07-27T00:20:25.049856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21866v1","created_at":"2026-07-27T00:20:25.049856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21866","created_at":"2026-07-27T00:20:25.049856+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH2OXD5XWTYS","created_at":"2026-07-27T00:20:25.049856+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH2OXD5XWTYSMEB7","created_at":"2026-07-27T00:20:25.049856+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH2OXD5X","created_at":"2026-07-27T00:20:25.049856+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/HH2OXD5XWTYSMEB7TY2ZR5APXZ","json":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ.json","graph_json":"https://pith.science/api/pith-number/HH2OXD5XWTYSMEB7TY2ZR5APXZ/graph.json","events_json":"https://pith.science/api/pith-number/HH2OXD5XWTYSMEB7TY2ZR5APXZ/events.json","paper":"https://pith.science/paper/HH2OXD5X"},"agent_actions":{"view_html":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ","download_json":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ.json","view_paper":"https://pith.science/paper/HH2OXD5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21866&json=true","fetch_graph":"https://pith.science/api/pith-number/HH2OXD5XWTYSMEB7TY2ZR5APXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HH2OXD5XWTYSMEB7TY2ZR5APXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ/action/storage_attestation","attest_author":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ/action/author_attestation","sign_citation":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ/action/citation_signature","submit_replication":"https://pith.science/pith/HH2OXD5XWTYSMEB7TY2ZR5APXZ/action/replication_record"}},"created_at":"2026-07-27T00:20:25.049856+00:00","updated_at":"2026-07-27T00:20:25.049856+00:00"}