{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:EPZNLRMDRAD3HNPAIDWV5CS64U","short_pith_number":"pith:EPZNLRMD","schema_version":"1.0","canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","source":{"kind":"arxiv","id":"1501.00604","version":1},"attestation_state":"computed","paper":{"title":"A Taxonomy of Big Data for Optimal Predictive Machine Learning and Data Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ernest Fokoue","submitted_at":"2015-01-03T20:44:01Z","abstract_excerpt":"Big data comes in various ways, types, shapes, forms and sizes. Indeed, almost all areas of science, technology, medicine, public health, economics, business, linguistics and social science are bombarded by ever increasing flows of data begging to analyzed efficiently and effectively. In this paper, we propose a rough idea of a possible taxonomy of big data, along with some of the most commonly used tools for handling each particular category of bigness. The dimensionality p of the input space and the sample size n are usually the main ingredients in the characterization of data bigness. The s"},"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":"1501.00604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-03T20:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"1813868e1ba4bf4073649af4fe2ce2486bb9694dc0497ca97fbd775827db4a91","abstract_canon_sha256":"5e0a4a2329949e681f8e3936b2691c02b5f3bc99a062495dca8fc7062c497a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:02.178185Z","signature_b64":"lwvuo1CCZAaEyeOAkoAg4I+oQ5aomBnYE44iIOvtUO/8V5g6ChJnG02lczraF1QRXFB2hmG2jtkVaAeRDBbuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","last_reissued_at":"2026-05-18T02:30:02.177803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:02.177803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Taxonomy of Big Data for Optimal Predictive Machine Learning and Data Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ernest Fokoue","submitted_at":"2015-01-03T20:44:01Z","abstract_excerpt":"Big data comes in various ways, types, shapes, forms and sizes. Indeed, almost all areas of science, technology, medicine, public health, economics, business, linguistics and social science are bombarded by ever increasing flows of data begging to analyzed efficiently and effectively. In this paper, we propose a rough idea of a possible taxonomy of big data, along with some of the most commonly used tools for handling each particular category of bigness. The dimensionality p of the input space and the sample size n are usually the main ingredients in the characterization of data bigness. The s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.00604","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":"1501.00604","created_at":"2026-05-18T02:30:02.177859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.00604v1","created_at":"2026-05-18T02:30:02.177859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.00604","created_at":"2026-05-18T02:30:02.177859+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPZNLRMDRAD3","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPZNLRMDRAD3HNPA","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPZNLRMD","created_at":"2026-05-18T12:29:19.899920+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/EPZNLRMDRAD3HNPAIDWV5CS64U","json":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U.json","graph_json":"https://pith.science/api/pith-number/EPZNLRMDRAD3HNPAIDWV5CS64U/graph.json","events_json":"https://pith.science/api/pith-number/EPZNLRMDRAD3HNPAIDWV5CS64U/events.json","paper":"https://pith.science/paper/EPZNLRMD"},"agent_actions":{"view_html":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U","download_json":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U.json","view_paper":"https://pith.science/paper/EPZNLRMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.00604&json=true","fetch_graph":"https://pith.science/api/pith-number/EPZNLRMDRAD3HNPAIDWV5CS64U/graph.json","fetch_events":"https://pith.science/api/pith-number/EPZNLRMDRAD3HNPAIDWV5CS64U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/action/storage_attestation","attest_author":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/action/author_attestation","sign_citation":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/action/citation_signature","submit_replication":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/action/replication_record"}},"created_at":"2026-05-18T02:30:02.177859+00:00","updated_at":"2026-05-18T02:30:02.177859+00:00"}