{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IDWREW7A6BKDJGFY6CLMDD3U3I","short_pith_number":"pith:IDWREW7A","schema_version":"1.0","canonical_sha256":"40ed125be0f0543498b8f096c18f74da25fc8d65ba3ae5cf6c2ff08811874a25","source":{"kind":"arxiv","id":"1706.00327","version":1},"attestation_state":"computed","paper":{"title":"One button machine for automating feature engineering in relational databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Bei Chen, Hoang Thanh Lam, Johann-Michael Thiebaut, Mathieu Sinn, Oznur Alkan, Tiep Mai","submitted_at":"2017-06-01T14:44:34Z","abstract_excerpt":"Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in wh"},"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":"1706.00327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-06-01T14:44:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bee7757c5b1bde2d3a8d55962d1c09c0aba7bed1c2743b52b31489b7a114e726","abstract_canon_sha256":"f9d4c4c67bbf20b054d2cebfd1627409e11c472fe9472ef454c295acc39be30b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:14.344111Z","signature_b64":"oqRP6hownEIjL4JzhVgp3eV3yElkSkkhKC41LRUURlCLawVzmYt3xQjKi+obRFiqRantqVGji6QCAbSxW14RCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40ed125be0f0543498b8f096c18f74da25fc8d65ba3ae5cf6c2ff08811874a25","last_reissued_at":"2026-05-18T00:43:14.343599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:14.343599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One button machine for automating feature engineering in relational databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Bei Chen, Hoang Thanh Lam, Johann-Michael Thiebaut, Mathieu Sinn, Oznur Alkan, Tiep Mai","submitted_at":"2017-06-01T14:44:34Z","abstract_excerpt":"Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00327","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":"1706.00327","created_at":"2026-05-18T00:43:14.343686+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00327v1","created_at":"2026-05-18T00:43:14.343686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00327","created_at":"2026-05-18T00:43:14.343686+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDWREW7A6BKD","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDWREW7A6BKDJGFY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDWREW7A","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14464","citing_title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I","json":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I.json","graph_json":"https://pith.science/api/pith-number/IDWREW7A6BKDJGFY6CLMDD3U3I/graph.json","events_json":"https://pith.science/api/pith-number/IDWREW7A6BKDJGFY6CLMDD3U3I/events.json","paper":"https://pith.science/paper/IDWREW7A"},"agent_actions":{"view_html":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I","download_json":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I.json","view_paper":"https://pith.science/paper/IDWREW7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00327&json=true","fetch_graph":"https://pith.science/api/pith-number/IDWREW7A6BKDJGFY6CLMDD3U3I/graph.json","fetch_events":"https://pith.science/api/pith-number/IDWREW7A6BKDJGFY6CLMDD3U3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I/action/storage_attestation","attest_author":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I/action/author_attestation","sign_citation":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I/action/citation_signature","submit_replication":"https://pith.science/pith/IDWREW7A6BKDJGFY6CLMDD3U3I/action/replication_record"}},"created_at":"2026-05-18T00:43:14.343686+00:00","updated_at":"2026-05-18T00:43:14.343686+00:00"}