{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3N44X6ZTCI2QHZBXFHLJJ2GNTD","short_pith_number":"pith:3N44X6ZT","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"},"canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","source":{"kind":"arxiv","id":"1805.03887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03887","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03887v1","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03887","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"3N44X6ZTCI2Q","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3N44X6ZTCI2QHZBX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3N44X6ZT","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3N44X6ZTCI2QHZBXFHLJJ2GNTD","target":"record","payload":{"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"},"canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","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"},"source_kind":"arxiv","source_id":"1805.03887","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":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCXQpMTvQU7xN2ClHa4xbLCf7geNsTHI6ucPv9LJtfjHSY6ZqzaDC+MRUkrOfJOjrWY/NnsgIFzYynf8UB4PDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:22:52.957683Z"},"content_sha256":"0e3b9ba4579d78288c0e9112669e66cb02456193f13ee71e00a6126f9d0cb6d6","schema_version":"1.0","event_id":"sha256:0e3b9ba4579d78288c0e9112669e66cb02456193f13ee71e00a6126f9d0cb6d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3N44X6ZTCI2QHZBXFHLJJ2GNTD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xr4MZETX5p/MeM3UsW6glTrA3WkNCOOSXp9DVJwx0pAVGnE303TPe7rHt847rByYaHlMZwNrbIiCtI+wv0QUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:22:52.958085Z"},"content_sha256":"1d8975551a9a354a10cfa21674329ce43ee165eff2385c135e36f9ee69bd0de5","schema_version":"1.0","event_id":"sha256:1d8975551a9a354a10cfa21674329ce43ee165eff2385c135e36f9ee69bd0de5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/bundle.json","state_url":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/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":"2026-05-27T01:22:52Z","links":{"resolver":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD","bundle":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/bundle.json","state":"https://pith.science/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3N44X6ZTCI2QHZBXFHLJJ2GNTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3N44X6ZTCI2QHZBXFHLJJ2GNTD","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":"e90f7012d735bd18b4def6b7e417c8e021f7012ff9410fadf0bba5777da6df88","cross_cats_sorted":["cs.AI","cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-10T08:41:55Z","title_canon_sha256":"0fb2debb22a2b1e692e6ff568e60876f4862ff9f3ae4e9ee8e75094b368300c2"},"schema_version":"1.0","source":{"id":"1805.03887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03887","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03887v1","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03887","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"3N44X6ZTCI2Q","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3N44X6ZTCI2QHZBX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3N44X6ZT","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:1d8975551a9a354a10cfa21674329ce43ee165eff2385c135e36f9ee69bd0de5","target":"graph","created_at":"2026-05-18T00:16:16Z","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":"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","authors_text":"Elena Baralis, Luca Venturini, Paolo Garza","cross_cats":["cs.AI","cs.DC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-10T08:41:55Z","title":"Scaling associative classification for very large datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03887","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":"sha256:0e3b9ba4579d78288c0e9112669e66cb02456193f13ee71e00a6126f9d0cb6d6","target":"record","created_at":"2026-05-18T00:16:16Z","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":"e90f7012d735bd18b4def6b7e417c8e021f7012ff9410fadf0bba5777da6df88","cross_cats_sorted":["cs.AI","cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-05-10T08:41:55Z","title_canon_sha256":"0fb2debb22a2b1e692e6ff568e60876f4862ff9f3ae4e9ee8e75094b368300c2"},"schema_version":"1.0","source":{"id":"1805.03887","kind":"arxiv","version":1}},"canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db79cbfb33123503e43729d694e8cd98cafe5f1bf59d945fb54bf164b4ea3ff2","first_computed_at":"2026-05-18T00:16:16.465973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:16.465973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P6buF9vuMEpJcJ2WobXuKpUcB2Rzvk1GUV67q+PVuu+j6tEHtKizG9nI6OWKLa5XtZVo2btn5TJ6sNRKwD80Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:16.466658Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e3b9ba4579d78288c0e9112669e66cb02456193f13ee71e00a6126f9d0cb6d6","sha256:1d8975551a9a354a10cfa21674329ce43ee165eff2385c135e36f9ee69bd0de5"],"state_sha256":"c37b66b35fd675e0778d023c6af7b0842cc545e88a3ea9eec2021793d16c34a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0DV05F6OneoeY+JJYCGdKnojVUUNnzDicww4pxxq2d/xiTJoNJTXHs24xuNuXSwXDAJ96Xv7PckWkwAnbjKDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:22:52.960531Z","bundle_sha256":"151e09af5e11b3e13a25df04a73cbbbb521fc8124bd8851020d76c02735973a6"}}