{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5OUVIWAFWF4NQRCOBG2BNHRZEU","short_pith_number":"pith:5OUVIWAF","schema_version":"1.0","canonical_sha256":"eba9545805b178d8444e09b4169e392539617c6aecbe5b66eecfd9d917b39032","source":{"kind":"arxiv","id":"1612.07448","version":6},"attestation_state":"computed","paper":{"title":"Towards Linear Algebra over Normalized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arun Kumar, Jeffrey Naughton, Jignesh M. Patel, Lingjiao Chen","submitted_at":"2016-12-22T05:41:27Z","abstract_excerpt":"Providing machine learning (ML) over relational data is a mainstream requirement for data analytics systems. While almost all the ML tools require the input data to be presented as a single table, many datasets are multi-table, which forces data scientists to join those tables first, leading to data redundancy and runtime waste. Recent works on \"factorized\" ML mitigate this issue for a few specific ML algorithms by pushing ML through joins. But their approaches require a manual rewrite of ML implementations. Such piecemeal methods create a massive development overhead when extending such ideas"},"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":"1612.07448","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-12-22T05:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd125dc581814fac1efc6d0f8115ff8ed397f2a06d2db81f04b8a6c3a5f890ea","abstract_canon_sha256":"dc01560fab2ff06065e38dcc68ec25fee8eea19fbad81e2bbc3c9ee120c3b181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:37.904525Z","signature_b64":"aAkAXvpGioj/o7gu1ObggtxLN0JdCwiLUjhXdCcW1QX9Se0jF50wy7qHl/TqFMwoijl6j6z3tUZWgTS/UYORDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba9545805b178d8444e09b4169e392539617c6aecbe5b66eecfd9d917b39032","last_reissued_at":"2026-05-18T00:41:37.903870Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:37.903870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Linear Algebra over Normalized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arun Kumar, Jeffrey Naughton, Jignesh M. Patel, Lingjiao Chen","submitted_at":"2016-12-22T05:41:27Z","abstract_excerpt":"Providing machine learning (ML) over relational data is a mainstream requirement for data analytics systems. While almost all the ML tools require the input data to be presented as a single table, many datasets are multi-table, which forces data scientists to join those tables first, leading to data redundancy and runtime waste. Recent works on \"factorized\" ML mitigate this issue for a few specific ML algorithms by pushing ML through joins. But their approaches require a manual rewrite of ML implementations. Such piecemeal methods create a massive development overhead when extending such ideas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07448","kind":"arxiv","version":6},"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":"1612.07448","created_at":"2026-05-18T00:41:37.903980+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.07448v6","created_at":"2026-05-18T00:41:37.903980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07448","created_at":"2026-05-18T00:41:37.903980+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OUVIWAFWF4N","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OUVIWAFWF4NQRCO","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OUVIWAF","created_at":"2026-05-18T12:30:01.593930+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/5OUVIWAFWF4NQRCOBG2BNHRZEU","json":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU.json","graph_json":"https://pith.science/api/pith-number/5OUVIWAFWF4NQRCOBG2BNHRZEU/graph.json","events_json":"https://pith.science/api/pith-number/5OUVIWAFWF4NQRCOBG2BNHRZEU/events.json","paper":"https://pith.science/paper/5OUVIWAF"},"agent_actions":{"view_html":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU","download_json":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU.json","view_paper":"https://pith.science/paper/5OUVIWAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.07448&json=true","fetch_graph":"https://pith.science/api/pith-number/5OUVIWAFWF4NQRCOBG2BNHRZEU/graph.json","fetch_events":"https://pith.science/api/pith-number/5OUVIWAFWF4NQRCOBG2BNHRZEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU/action/storage_attestation","attest_author":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU/action/author_attestation","sign_citation":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU/action/citation_signature","submit_replication":"https://pith.science/pith/5OUVIWAFWF4NQRCOBG2BNHRZEU/action/replication_record"}},"created_at":"2026-05-18T00:41:37.903980+00:00","updated_at":"2026-05-18T00:41:37.903980+00:00"}