{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6FCHHSZMSS4TAKQSY45QF6LG52","short_pith_number":"pith:6FCHHSZM","canonical_record":{"source":{"id":"1901.11286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:36:04Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"863b0627f789bb8e471336169332cde269e3956111f029c6407ffbf5234300a2","abstract_canon_sha256":"75e58a84ec4e368de15d0aad3776180062583f8a1d3c9fb869d5f69988ae8d16"},"schema_version":"1.0"},"canonical_sha256":"f14473cb2c94b9302a12c73b02f966ee927be880338ae8fa86f15dc67b4e79b3","source":{"kind":"arxiv","id":"1901.11286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11286","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11286v1","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11286","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"6FCHHSZMSS4T","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6FCHHSZMSS4TAKQS","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6FCHHSZM","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6FCHHSZMSS4TAKQSY45QF6LG52","target":"record","payload":{"canonical_record":{"source":{"id":"1901.11286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:36:04Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"863b0627f789bb8e471336169332cde269e3956111f029c6407ffbf5234300a2","abstract_canon_sha256":"75e58a84ec4e368de15d0aad3776180062583f8a1d3c9fb869d5f69988ae8d16"},"schema_version":"1.0"},"canonical_sha256":"f14473cb2c94b9302a12c73b02f966ee927be880338ae8fa86f15dc67b4e79b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:02.271280Z","signature_b64":"NH54Yd1FEmSr9lZz49v8lRjQhHSuSlsWBamEGaH8zSHbib11BfZHeR29wLES4wm5sDhu7QtKSpiTvRVcv8HVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f14473cb2c94b9302a12c73b02f966ee927be880338ae8fa86f15dc67b4e79b3","last_reissued_at":"2026-05-17T23:55:02.270814Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:02.270814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.11286","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":"2026-05-17T23:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+UctJEXpH7+X+55L2oM+PvrWLQMGE1yMgCc9nxZIFcbQ3NyrFsakZBnRxdohd0fPG8Zq1xy/S1+MSGOjfzNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T19:40:17.623452Z"},"content_sha256":"a98f3de13fc5ec21e875146a3a05f21b790ab3e78f16c84e906b38ff29fa599d","schema_version":"1.0","event_id":"sha256:a98f3de13fc5ec21e875146a3a05f21b790ab3e78f16c84e906b38ff29fa599d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6FCHHSZMSS4TAKQSY45QF6LG52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Correlation-Based Feature Selection in Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amparo Alonso-Betanzos, Daniel Rodriguez, Luis de-Marcos, Raul-Jose Palma-Mendoza","submitted_at":"2019-01-31T09:36:04Z","abstract_excerpt":"CFS (Correlation-Based Feature Selection) is an FS algorithm that has been successfully applied to classification problems in many domains. We describe Distributed CFS (DiCFS) as a completely redesigned, scalable, parallel and distributed version of the CFS algorithm, capable of dealing with the large volumes of data typical of big data applications. Two versions of the algorithm were implemented and compared using the Apache Spark cluster computing model, currently gaining popularity due to its much faster processing times than Hadoop's MapReduce model. We tested our algorithms on four public"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11286","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":"2026-05-17T23:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Beo6GjqS+a/BiDvCxNCixx4IAEihfcE+dnI9ItSDaeJzI2+c00p/7DB+eOByfwm2LT4k7DekSTfaF3tNjKx6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T19:40:17.624181Z"},"content_sha256":"0ba9920caf0065845a57ae49129e8debfba7f4af80c78688588e9212b1a3ec0d","schema_version":"1.0","event_id":"sha256:0ba9920caf0065845a57ae49129e8debfba7f4af80c78688588e9212b1a3ec0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FCHHSZMSS4TAKQSY45QF6LG52/bundle.json","state_url":"https://pith.science/pith/6FCHHSZMSS4TAKQSY45QF6LG52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FCHHSZMSS4TAKQSY45QF6LG52/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":"2026-06-11T19:40:17Z","links":{"resolver":"https://pith.science/pith/6FCHHSZMSS4TAKQSY45QF6LG52","bundle":"https://pith.science/pith/6FCHHSZMSS4TAKQSY45QF6LG52/bundle.json","state":"https://pith.science/pith/6FCHHSZMSS4TAKQSY45QF6LG52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FCHHSZMSS4TAKQSY45QF6LG52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6FCHHSZMSS4TAKQSY45QF6LG52","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":"75e58a84ec4e368de15d0aad3776180062583f8a1d3c9fb869d5f69988ae8d16","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:36:04Z","title_canon_sha256":"863b0627f789bb8e471336169332cde269e3956111f029c6407ffbf5234300a2"},"schema_version":"1.0","source":{"id":"1901.11286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11286","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11286v1","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11286","created_at":"2026-05-17T23:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"6FCHHSZMSS4T","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6FCHHSZMSS4TAKQS","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6FCHHSZM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:0ba9920caf0065845a57ae49129e8debfba7f4af80c78688588e9212b1a3ec0d","target":"graph","created_at":"2026-05-17T23:55:02Z","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":"CFS (Correlation-Based Feature Selection) is an FS algorithm that has been successfully applied to classification problems in many domains. We describe Distributed CFS (DiCFS) as a completely redesigned, scalable, parallel and distributed version of the CFS algorithm, capable of dealing with the large volumes of data typical of big data applications. Two versions of the algorithm were implemented and compared using the Apache Spark cluster computing model, currently gaining popularity due to its much faster processing times than Hadoop's MapReduce model. We tested our algorithms on four public","authors_text":"Amparo Alonso-Betanzos, Daniel Rodriguez, Luis de-Marcos, Raul-Jose Palma-Mendoza","cross_cats":["cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:36:04Z","title":"Distributed Correlation-Based Feature Selection in Spark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11286","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:a98f3de13fc5ec21e875146a3a05f21b790ab3e78f16c84e906b38ff29fa599d","target":"record","created_at":"2026-05-17T23:55:02Z","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":"75e58a84ec4e368de15d0aad3776180062583f8a1d3c9fb869d5f69988ae8d16","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T09:36:04Z","title_canon_sha256":"863b0627f789bb8e471336169332cde269e3956111f029c6407ffbf5234300a2"},"schema_version":"1.0","source":{"id":"1901.11286","kind":"arxiv","version":1}},"canonical_sha256":"f14473cb2c94b9302a12c73b02f966ee927be880338ae8fa86f15dc67b4e79b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f14473cb2c94b9302a12c73b02f966ee927be880338ae8fa86f15dc67b4e79b3","first_computed_at":"2026-05-17T23:55:02.270814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:02.270814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NH54Yd1FEmSr9lZz49v8lRjQhHSuSlsWBamEGaH8zSHbib11BfZHeR29wLES4wm5sDhu7QtKSpiTvRVcv8HVBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:02.271280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a98f3de13fc5ec21e875146a3a05f21b790ab3e78f16c84e906b38ff29fa599d","sha256:0ba9920caf0065845a57ae49129e8debfba7f4af80c78688588e9212b1a3ec0d"],"state_sha256":"9494f6bcdb1e176c7214b71a8f2fff4b055d646e83c036fbf32c2d1ac1b0cc5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjVoEjMDUo2unyGeAcg5aW+JFwYa+7nm6Ouet4L35yAMkRH+4HZebnxOggWfRtMIEIr487ROxyedW7A7lD1NCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T19:40:17.628165Z","bundle_sha256":"4eafbd92ae74c455f756f72a98d4d275a689f1f596245814a20a0259e22add61"}}