{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:EPZNLRMDRAD3HNPAIDWV5CS64U","short_pith_number":"pith:EPZNLRMD","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"},"canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","source":{"kind":"arxiv","id":"1501.00604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.00604","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"arxiv_version","alias_value":"1501.00604v1","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.00604","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"pith_short_12","alias_value":"EPZNLRMDRAD3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EPZNLRMDRAD3HNPA","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EPZNLRMD","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:EPZNLRMDRAD3HNPAIDWV5CS64U","target":"record","payload":{"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"},"canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","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"},"source_kind":"arxiv","source_id":"1501.00604","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:30:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yy8GU4ERZ5RkzfCpPh/4RHBq9uDL3+mEdQGAcwFs+Ryj/9DDmwikSVkskZMgJEhYQnvkpZusAW9y6+7zIpiEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:57:48.494176Z"},"content_sha256":"a8f45a6a5cfcaf6f93f17f66d07bb9d4c0a6a02a815295d7eb926db33f9f07dd","schema_version":"1.0","event_id":"sha256:a8f45a6a5cfcaf6f93f17f66d07bb9d4c0a6a02a815295d7eb926db33f9f07dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:EPZNLRMDRAD3HNPAIDWV5CS64U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:30:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohLzoPFGEPsfdctNqX8sHo0CquJgBQsDCc8HAASjqVPzREhKw+8Df5GSVO8nva9iKXqZU6vEXkvvKXskwj6SBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:57:48.494531Z"},"content_sha256":"aadc1dd27c3d6be9ae2428edbae0042c55c6ccce606cf3a73fbfefc24c435b3a","schema_version":"1.0","event_id":"sha256:aadc1dd27c3d6be9ae2428edbae0042c55c6ccce606cf3a73fbfefc24c435b3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/bundle.json","state_url":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T18:57:48Z","links":{"resolver":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U","bundle":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/bundle.json","state":"https://pith.science/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPZNLRMDRAD3HNPAIDWV5CS64U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:EPZNLRMDRAD3HNPAIDWV5CS64U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5e0a4a2329949e681f8e3936b2691c02b5f3bc99a062495dca8fc7062c497a3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-03T20:44:01Z","title_canon_sha256":"1813868e1ba4bf4073649af4fe2ce2486bb9694dc0497ca97fbd775827db4a91"},"schema_version":"1.0","source":{"id":"1501.00604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.00604","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"arxiv_version","alias_value":"1501.00604v1","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.00604","created_at":"2026-05-18T02:30:02Z"},{"alias_kind":"pith_short_12","alias_value":"EPZNLRMDRAD3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EPZNLRMDRAD3HNPA","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EPZNLRMD","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:aadc1dd27c3d6be9ae2428edbae0042c55c6ccce606cf3a73fbfefc24c435b3a","target":"graph","created_at":"2026-05-18T02:30:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ernest Fokoue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-03T20:44:01Z","title":"A Taxonomy of Big Data for Optimal Predictive Machine Learning and Data Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.00604","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a8f45a6a5cfcaf6f93f17f66d07bb9d4c0a6a02a815295d7eb926db33f9f07dd","target":"record","created_at":"2026-05-18T02:30:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5e0a4a2329949e681f8e3936b2691c02b5f3bc99a062495dca8fc7062c497a3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-03T20:44:01Z","title_canon_sha256":"1813868e1ba4bf4073649af4fe2ce2486bb9694dc0497ca97fbd775827db4a91"},"schema_version":"1.0","source":{"id":"1501.00604","kind":"arxiv","version":1}},"canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23f2d5c5838807b3b5e040ed5e8a5ee51851b255de5534b401540f79da950758","first_computed_at":"2026-05-18T02:30:02.177803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:30:02.177803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lwvuo1CCZAaEyeOAkoAg4I+oQ5aomBnYE44iIOvtUO/8V5g6ChJnG02lczraF1QRXFB2hmG2jtkVaAeRDBbuAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:30:02.178185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1501.00604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f45a6a5cfcaf6f93f17f66d07bb9d4c0a6a02a815295d7eb926db33f9f07dd","sha256:aadc1dd27c3d6be9ae2428edbae0042c55c6ccce606cf3a73fbfefc24c435b3a"],"state_sha256":"3956482eab569d644c7ccbc8e6568e9bfc1f9f20c7802df3b459338cc078f661"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQpvSUnt0WzXvrHuwH+nUK/f0Zb+VS5fCrIlmKtZCyD/NGNzkjIW5TUD2LCugEDGOz84Zv+msNksgTTKmojZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:57:48.496437Z","bundle_sha256":"1ac421fd7fa36ff180f132d7ad14467232b9cff954a44b4be21292bc8f45456d"}}