{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKQAYE265N62ULQ7YF42CMP3RS","short_pith_number":"pith:OKQAYE26","schema_version":"1.0","canonical_sha256":"72a00c135eeb7daa2e1fc179a131fb8c9023f1cc5dbb01659d0338a1aac3b7e7","source":{"kind":"arxiv","id":"2409.01635","version":1},"attestation_state":"computed","paper":{"title":"PMLBmini: A Tabular Classification Benchmark Suite for Data-Scarce Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Erik Rodner, Marvin Grimm, Ricardo Knauer","submitted_at":"2024-09-03T06:13:03Z","abstract_excerpt":"In practice, we are often faced with small-sized tabular data. However, current tabular benchmarks are not geared towards data-scarce applications, making it very difficult to derive meaningful conclusions from empirical comparisons. We introduce PMLBmini, a tabular benchmark suite of 44 binary classification datasets with sample sizes $\\leq$ 500. We use our suite to thoroughly evaluate current automated machine learning (AutoML) frameworks, off-the-shelf tabular deep neural networks, as well as classical linear models in the low-data regime. Our analysis reveals that state-of-the-art AutoML a"},"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":"2409.01635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T06:13:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4f50ff03f06d33a142c1e5f570a451d5c212d157455673a115e3986d6c7dc9fa","abstract_canon_sha256":"db26acacf27095cdf4249e557e5b8aab3b64bac81e1bc159db5595022a20b7f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:31.854003Z","signature_b64":"XOCFW/dOsDehrTQp/hgkvMAwmy7eiqhhLd5HMwJTl3IFgo+wZeRl6GyweAQE+F2WOGHHQJPIscMzvxtPCH35BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a00c135eeb7daa2e1fc179a131fb8c9023f1cc5dbb01659d0338a1aac3b7e7","last_reissued_at":"2026-07-05T09:02:31.853597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:31.853597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMLBmini: A Tabular Classification Benchmark Suite for Data-Scarce Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Erik Rodner, Marvin Grimm, Ricardo Knauer","submitted_at":"2024-09-03T06:13:03Z","abstract_excerpt":"In practice, we are often faced with small-sized tabular data. However, current tabular benchmarks are not geared towards data-scarce applications, making it very difficult to derive meaningful conclusions from empirical comparisons. We introduce PMLBmini, a tabular benchmark suite of 44 binary classification datasets with sample sizes $\\leq$ 500. We use our suite to thoroughly evaluate current automated machine learning (AutoML) frameworks, off-the-shelf tabular deep neural networks, as well as classical linear models in the low-data regime. Our analysis reveals that state-of-the-art AutoML a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01635","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/2409.01635/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":"2409.01635","created_at":"2026-07-05T09:02:31.853649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01635v1","created_at":"2026-07-05T09:02:31.853649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01635","created_at":"2026-07-05T09:02:31.853649+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKQAYE265N62","created_at":"2026-07-05T09:02:31.853649+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKQAYE265N62ULQ7","created_at":"2026-07-05T09:02:31.853649+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKQAYE26","created_at":"2026-07-05T09:02:31.853649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02003","citing_title":"RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS","json":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS.json","graph_json":"https://pith.science/api/pith-number/OKQAYE265N62ULQ7YF42CMP3RS/graph.json","events_json":"https://pith.science/api/pith-number/OKQAYE265N62ULQ7YF42CMP3RS/events.json","paper":"https://pith.science/paper/OKQAYE26"},"agent_actions":{"view_html":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS","download_json":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS.json","view_paper":"https://pith.science/paper/OKQAYE26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01635&json=true","fetch_graph":"https://pith.science/api/pith-number/OKQAYE265N62ULQ7YF42CMP3RS/graph.json","fetch_events":"https://pith.science/api/pith-number/OKQAYE265N62ULQ7YF42CMP3RS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS/action/storage_attestation","attest_author":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS/action/author_attestation","sign_citation":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS/action/citation_signature","submit_replication":"https://pith.science/pith/OKQAYE265N62ULQ7YF42CMP3RS/action/replication_record"}},"created_at":"2026-07-05T09:02:31.853649+00:00","updated_at":"2026-07-05T09:02:31.853649+00:00"}