{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NMVUXD2NFXW2GDNYL5VHVZOWDN","short_pith_number":"pith:NMVUXD2N","schema_version":"1.0","canonical_sha256":"6b2b4b8f4d2deda30db85f6a7ae5d61b7fb0357ec2dca0f30f1aa1bf3be6a311","source":{"kind":"arxiv","id":"1708.07178","version":1},"attestation_state":"computed","paper":{"title":"Massively-Parallel Feature Selection for Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Giorgos Borboudakis, Ioannis Tsamardinos, Pavlos Katsogridakis, Polyvios Pratikakis, Vassilis Christophides","submitted_at":"2017-08-23T20:23:36Z","abstract_excerpt":"We present the Parallel, Forward-Backward with Pruning (PFBP) algorithm for feature selection (FS) in Big Data settings (high dimensionality and/or sample size). To tackle the challenges of Big Data FS PFBP partitions the data matrix both in terms of rows (samples, training examples) as well as columns (features). By employing the concepts of $p$-values of conditional independence tests and meta-analysis techniques PFBP manages to rely only on computations local to a partition while minimizing communication costs. Then, it employs powerful and safe (asymptotically sound) heuristics to make ear"},"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":"1708.07178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-23T20:23:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7334e35a3053ef2e9a6b972ebc9685f5463b79fc5737b0e43ff6804aa7c987fa","abstract_canon_sha256":"121667a7e2819de530a5bedd51411c545d9df3d85bad1ac59f62a3258adc3f0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:47.015340Z","signature_b64":"0g8iW0SUFUqTtM0t/nRrvgYe3QX/aPmTxB3ZwoL5/1QM/JH4DQBjuHik+hKplSuOhc0xn/z0zVzAhj8TBwTKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b2b4b8f4d2deda30db85f6a7ae5d61b7fb0357ec2dca0f30f1aa1bf3be6a311","last_reissued_at":"2026-05-18T00:36:47.014758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:47.014758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively-Parallel Feature Selection for Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Giorgos Borboudakis, Ioannis Tsamardinos, Pavlos Katsogridakis, Polyvios Pratikakis, Vassilis Christophides","submitted_at":"2017-08-23T20:23:36Z","abstract_excerpt":"We present the Parallel, Forward-Backward with Pruning (PFBP) algorithm for feature selection (FS) in Big Data settings (high dimensionality and/or sample size). To tackle the challenges of Big Data FS PFBP partitions the data matrix both in terms of rows (samples, training examples) as well as columns (features). By employing the concepts of $p$-values of conditional independence tests and meta-analysis techniques PFBP manages to rely only on computations local to a partition while minimizing communication costs. Then, it employs powerful and safe (asymptotically sound) heuristics to make ear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07178","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":"1708.07178","created_at":"2026-05-18T00:36:47.014844+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.07178v1","created_at":"2026-05-18T00:36:47.014844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07178","created_at":"2026-05-18T00:36:47.014844+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMVUXD2NFXW2","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMVUXD2NFXW2GDNY","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMVUXD2N","created_at":"2026-05-18T12:31:34.259226+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/NMVUXD2NFXW2GDNYL5VHVZOWDN","json":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN.json","graph_json":"https://pith.science/api/pith-number/NMVUXD2NFXW2GDNYL5VHVZOWDN/graph.json","events_json":"https://pith.science/api/pith-number/NMVUXD2NFXW2GDNYL5VHVZOWDN/events.json","paper":"https://pith.science/paper/NMVUXD2N"},"agent_actions":{"view_html":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN","download_json":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN.json","view_paper":"https://pith.science/paper/NMVUXD2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.07178&json=true","fetch_graph":"https://pith.science/api/pith-number/NMVUXD2NFXW2GDNYL5VHVZOWDN/graph.json","fetch_events":"https://pith.science/api/pith-number/NMVUXD2NFXW2GDNYL5VHVZOWDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN/action/storage_attestation","attest_author":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN/action/author_attestation","sign_citation":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN/action/citation_signature","submit_replication":"https://pith.science/pith/NMVUXD2NFXW2GDNYL5VHVZOWDN/action/replication_record"}},"created_at":"2026-05-18T00:36:47.014844+00:00","updated_at":"2026-05-18T00:36:47.014844+00:00"}