{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3N44X6ZTCI2QHZBXFHLJJ2GNTD","short_pith_number":"pith:3N44X6ZT","schema_version":"1.0","canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","source":{"kind":"arxiv","id":"1805.03887","version":1},"attestation_state":"computed","paper":{"title":"Scaling associative classification for very large datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elena Baralis, Luca Venturini, Paolo Garza","submitted_at":"2018-05-10T08:41:55Z","abstract_excerpt":"Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of large-domain categorical features are a difficult challenge for any classifier. Most off-the-shelf solutions cannot cope with this problem. In this work we introduce DAC, a Distributed Associative Classifier. DAC exploits ensemble learning to distribute the training of an associative classifier among parallel workers and improve the final quality of the model. Furtherm"},"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":"1805.03887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-10T08:41:55Z","cross_cats_sorted":["cs.AI","cs.DC","stat.ML"],"title_canon_sha256":"0fb2debb22a2b1e692e6ff568e60876f4862ff9f3ae4e9ee8e75094b368300c2","abstract_canon_sha256":"e90f7012d735bd18b4def6b7e417c8e021f7012ff9410fadf0bba5777da6df88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:16.466658Z","signature_b64":"P6buF9vuMEpJcJ2WobXuKpUcB2Rzvk1GUV67q+PVuu+j6tEHtKizG9nI6OWKLa5XtZVo2btn5TJ6sNRKwD80Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","last_reissued_at":"2026-05-18T00:16:16.465973Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:16.465973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling associative classification for very large datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elena Baralis, Luca Venturini, Paolo Garza","submitted_at":"2018-05-10T08:41:55Z","abstract_excerpt":"Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of large-domain categorical features are a difficult challenge for any classifier. Most off-the-shelf solutions cannot cope with this problem. In this work we introduce DAC, a Distributed Associative Classifier. DAC exploits ensemble learning to distribute the training of an associative classifier among parallel workers and improve the final quality of the model. Furtherm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03887","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":"1805.03887","created_at":"2026-05-18T00:16:16.466084+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.03887v1","created_at":"2026-05-18T00:16:16.466084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03887","created_at":"2026-05-18T00:16:16.466084+00:00"},{"alias_kind":"pith_short_12","alias_value":"3N44X6ZTCI2Q","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3N44X6ZTCI2QHZBX","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3N44X6ZT","created_at":"2026-05-18T12:32:02.567920+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/3N44X6ZTCI2QHZBXFHLJJ2GNTD","json":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD.json","graph_json":"https://pith.science/api/pith-number/3N44X6ZTCI2QHZBXFHLJJ2GNTD/graph.json","events_json":"https://pith.science/api/pith-number/3N44X6ZTCI2QHZBXFHLJJ2GNTD/events.json","paper":"https://pith.science/paper/3N44X6ZT"},"agent_actions":{"view_html":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD","download_json":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD.json","view_paper":"https://pith.science/paper/3N44X6ZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.03887&json=true","fetch_graph":"https://pith.science/api/pith-number/3N44X6ZTCI2QHZBXFHLJJ2GNTD/graph.json","fetch_events":"https://pith.science/api/pith-number/3N44X6ZTCI2QHZBXFHLJJ2GNTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/action/storage_attestation","attest_author":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/action/author_attestation","sign_citation":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/action/citation_signature","submit_replication":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/action/replication_record"}},"created_at":"2026-05-18T00:16:16.466084+00:00","updated_at":"2026-05-18T00:16:16.466084+00:00"}