{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:2LQTIIZJR4N353TRY5D2EPRMWM","short_pith_number":"pith:2LQTIIZJ","schema_version":"1.0","canonical_sha256":"d2e13423298f1bbeee71c747a23e2cb312bc244264415ac26ca37adfae918eaf","source":{"kind":"arxiv","id":"1301.3884","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Models for Query Approximation with Large Sparse Binary Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Dmitry Y. Pavlov, Heikki Mannila, Padhraic Smyth","submitted_at":"2013-01-16T15:52:06Z","abstract_excerpt":"Large sparse sets of binary transaction data with millions of records and thousands of attributes occur in various domains: customers purchasing products, users visiting web pages, and documents containing words are just three typical examples. Real-time query selectivity estimation (the problem of estimating the number of rows in the data satisfying a given predicate) is an important practical problem for such databases.\n We investigate the application of probabilistic models to this problem. In particular, we study a Markov random field (MRF) approach based on frequent sets and maximum entro"},"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":"1301.3884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:52:06Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"1e0c255943aadda241ae78666e8a2ba2113a236686d9728ced6485f5829256b8","abstract_canon_sha256":"96aeec63adb1f593be5bdaa249061e91a778c495a784cbc2e85bade8a312aebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:15.068853Z","signature_b64":"YOLUcNOYwCTpXHmwHCJooadZs9y/6qUWKIe7Rp+Fl0jnwUfrRALJeUdzYEi5tG1sAPi4bVPL6knbnZ7yqEi1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e13423298f1bbeee71c747a23e2cb312bc244264415ac26ca37adfae918eaf","last_reissued_at":"2026-05-18T03:36:15.068313Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:15.068313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Models for Query Approximation with Large Sparse Binary Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Dmitry Y. Pavlov, Heikki Mannila, Padhraic Smyth","submitted_at":"2013-01-16T15:52:06Z","abstract_excerpt":"Large sparse sets of binary transaction data with millions of records and thousands of attributes occur in various domains: customers purchasing products, users visiting web pages, and documents containing words are just three typical examples. Real-time query selectivity estimation (the problem of estimating the number of rows in the data satisfying a given predicate) is an important practical problem for such databases.\n We investigate the application of probabilistic models to this problem. In particular, we study a Markov random field (MRF) approach based on frequent sets and maximum entro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3884","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":"1301.3884","created_at":"2026-05-18T03:36:15.068411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3884v1","created_at":"2026-05-18T03:36:15.068411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3884","created_at":"2026-05-18T03:36:15.068411+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LQTIIZJR4N3","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LQTIIZJR4N353TR","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LQTIIZJ","created_at":"2026-05-18T12:27:30.460161+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/2LQTIIZJR4N353TRY5D2EPRMWM","json":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM.json","graph_json":"https://pith.science/api/pith-number/2LQTIIZJR4N353TRY5D2EPRMWM/graph.json","events_json":"https://pith.science/api/pith-number/2LQTIIZJR4N353TRY5D2EPRMWM/events.json","paper":"https://pith.science/paper/2LQTIIZJ"},"agent_actions":{"view_html":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM","download_json":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM.json","view_paper":"https://pith.science/paper/2LQTIIZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3884&json=true","fetch_graph":"https://pith.science/api/pith-number/2LQTIIZJR4N353TRY5D2EPRMWM/graph.json","fetch_events":"https://pith.science/api/pith-number/2LQTIIZJR4N353TRY5D2EPRMWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM/action/storage_attestation","attest_author":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM/action/author_attestation","sign_citation":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM/action/citation_signature","submit_replication":"https://pith.science/pith/2LQTIIZJR4N353TRY5D2EPRMWM/action/replication_record"}},"created_at":"2026-05-18T03:36:15.068411+00:00","updated_at":"2026-05-18T03:36:15.068411+00:00"}