{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JGLIVI5PPCAG7S4EDX6NK6CZHN","short_pith_number":"pith:JGLIVI5P","schema_version":"1.0","canonical_sha256":"49968aa3af78806fcb841dfcd578593b4a91d560050de1ff35fb49f17e5b867f","source":{"kind":"arxiv","id":"1708.07242","version":1},"attestation_state":"computed","paper":{"title":"GALILEO: A Generalized Low-Entropy Mixture Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Cetin Savkli, Jeffrey Lin, Matthew Kinsey, Philip Graff","submitted_at":"2017-08-24T01:27:34Z","abstract_excerpt":"We present a new method of generating mixture models for data with categorical attributes. The keys to this approach are an entropy-based density metric in categorical space and annealing of high-entropy/low-density components from an initial state with many components. Pruning of low-density components using the entropy-based density allows GALILEO to consistently find high-quality clusters and the same optimal number of clusters. GALILEO has shown promising results on a range of test datasets commonly used for categorical clustering benchmarks. We demonstrate that the scaling of GALILEO is l"},"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":"1708.07242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-24T01:27:34Z","cross_cats_sorted":["cs.DS","cs.LG","math.PR"],"title_canon_sha256":"1d29b35bc982778c5a1073432efdba52f2c078f3cd032a18dd8070bdabf4261d","abstract_canon_sha256":"e39b0529ef7d039c335c295cabd0b546198b2a68aa5f91b3000a9e29f9414aa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:46.787327Z","signature_b64":"2QNz3SHB0RAuwB4RAnR82mc5x7sc1hY1Q5B188z6j/o79CQwAFVjfPuX72SUuV2Fx9kcnAdSanAmb4CmJ0r+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49968aa3af78806fcb841dfcd578593b4a91d560050de1ff35fb49f17e5b867f","last_reissued_at":"2026-05-18T00:36:46.786704Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:46.786704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GALILEO: A Generalized Low-Entropy Mixture Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Cetin Savkli, Jeffrey Lin, Matthew Kinsey, Philip Graff","submitted_at":"2017-08-24T01:27:34Z","abstract_excerpt":"We present a new method of generating mixture models for data with categorical attributes. The keys to this approach are an entropy-based density metric in categorical space and annealing of high-entropy/low-density components from an initial state with many components. Pruning of low-density components using the entropy-based density allows GALILEO to consistently find high-quality clusters and the same optimal number of clusters. GALILEO has shown promising results on a range of test datasets commonly used for categorical clustering benchmarks. We demonstrate that the scaling of GALILEO is l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07242","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":"1708.07242","created_at":"2026-05-18T00:36:46.786808+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.07242v1","created_at":"2026-05-18T00:36:46.786808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07242","created_at":"2026-05-18T00:36:46.786808+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGLIVI5PPCAG","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGLIVI5PPCAG7S4E","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGLIVI5P","created_at":"2026-05-18T12:31:24.725408+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/JGLIVI5PPCAG7S4EDX6NK6CZHN","json":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN.json","graph_json":"https://pith.science/api/pith-number/JGLIVI5PPCAG7S4EDX6NK6CZHN/graph.json","events_json":"https://pith.science/api/pith-number/JGLIVI5PPCAG7S4EDX6NK6CZHN/events.json","paper":"https://pith.science/paper/JGLIVI5P"},"agent_actions":{"view_html":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN","download_json":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN.json","view_paper":"https://pith.science/paper/JGLIVI5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.07242&json=true","fetch_graph":"https://pith.science/api/pith-number/JGLIVI5PPCAG7S4EDX6NK6CZHN/graph.json","fetch_events":"https://pith.science/api/pith-number/JGLIVI5PPCAG7S4EDX6NK6CZHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN/action/storage_attestation","attest_author":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN/action/author_attestation","sign_citation":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN/action/citation_signature","submit_replication":"https://pith.science/pith/JGLIVI5PPCAG7S4EDX6NK6CZHN/action/replication_record"}},"created_at":"2026-05-18T00:36:46.786808+00:00","updated_at":"2026-05-18T00:36:46.786808+00:00"}