{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WFGCOT5UO2RD6YYJMWEYSPODZJ","short_pith_number":"pith:WFGCOT5U","schema_version":"1.0","canonical_sha256":"b14c274fb476a23f63096589893dc3ca6f0fc0138cca5f9c1e0b409f9a48aee3","source":{"kind":"arxiv","id":"1904.10632","version":2},"attestation_state":"computed","paper":{"title":"Maximum Entropy Based Significance of Itemsets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nikolaj Tatti","submitted_at":"2019-04-24T03:46:23Z","abstract_excerpt":"We consider the problem of defining the significance of an itemset. We say that the itemset is significant if we are surprised by its frequency when compared to the frequencies of its sub-itemsets. In other words, we estimate the frequency of the itemset from the frequencies of its sub-itemsets and compute the deviation between the real value and the estimate. For the estimation we use Maximum Entropy and for measuring the deviation we use Kullback-Leibler divergence.\n  A major advantage compared to the previous methods is that we are able to use richer models whereas the previous approaches o"},"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":"1904.10632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T03:46:23Z","cross_cats_sorted":["cs.DB","stat.ML"],"title_canon_sha256":"c43acfcebb947c7ce30bc4c1e9d2775fe0848ad341da7be83e47ef4b6b259909","abstract_canon_sha256":"b87dd5e816c85426db1a3a64365c9018971434534027b4a337584cdb605c0d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:39.162524Z","signature_b64":"r6Pica4MdHPjRgZ5XetTsuS7yirq5tXaQbiZC82CcuYPrb+weFEhjtAygnWHGiOJWuARqWbupXJVbrYg4loUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b14c274fb476a23f63096589893dc3ca6f0fc0138cca5f9c1e0b409f9a48aee3","last_reissued_at":"2026-05-17T23:47:39.161961Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:39.161961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy Based Significance of Itemsets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nikolaj Tatti","submitted_at":"2019-04-24T03:46:23Z","abstract_excerpt":"We consider the problem of defining the significance of an itemset. We say that the itemset is significant if we are surprised by its frequency when compared to the frequencies of its sub-itemsets. In other words, we estimate the frequency of the itemset from the frequencies of its sub-itemsets and compute the deviation between the real value and the estimate. For the estimation we use Maximum Entropy and for measuring the deviation we use Kullback-Leibler divergence.\n  A major advantage compared to the previous methods is that we are able to use richer models whereas the previous approaches o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10632","kind":"arxiv","version":2},"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":"1904.10632","created_at":"2026-05-17T23:47:39.162038+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.10632v2","created_at":"2026-05-17T23:47:39.162038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10632","created_at":"2026-05-17T23:47:39.162038+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFGCOT5UO2RD","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFGCOT5UO2RD6YYJ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFGCOT5U","created_at":"2026-05-18T12:33:30.264802+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/WFGCOT5UO2RD6YYJMWEYSPODZJ","json":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ.json","graph_json":"https://pith.science/api/pith-number/WFGCOT5UO2RD6YYJMWEYSPODZJ/graph.json","events_json":"https://pith.science/api/pith-number/WFGCOT5UO2RD6YYJMWEYSPODZJ/events.json","paper":"https://pith.science/paper/WFGCOT5U"},"agent_actions":{"view_html":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ","download_json":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ.json","view_paper":"https://pith.science/paper/WFGCOT5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.10632&json=true","fetch_graph":"https://pith.science/api/pith-number/WFGCOT5UO2RD6YYJMWEYSPODZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WFGCOT5UO2RD6YYJMWEYSPODZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ/action/storage_attestation","attest_author":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ/action/author_attestation","sign_citation":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ/action/citation_signature","submit_replication":"https://pith.science/pith/WFGCOT5UO2RD6YYJMWEYSPODZJ/action/replication_record"}},"created_at":"2026-05-17T23:47:39.162038+00:00","updated_at":"2026-05-17T23:47:39.162038+00:00"}