{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ZBUL3HALW5EXI6NDCZZ5IF3V7","short_pith_number":"pith:4ZBUL3HA","schema_version":"1.0","canonical_sha256":"e64345ece05dba4ba3cd18b39ea0bbafef2c3a728cea6e49d5aed490980a4e17","source":{"kind":"arxiv","id":"2306.04785","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Deep Clustering for Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonathan Svirsky, Ofir Lindenbaum","submitted_at":"2023-06-07T21:08:09Z","abstract_excerpt":"Clustering is a fundamental learning task widely used as a first step in data analysis. For example, biologists use cluster assignments to analyze genome sequences, medical records, or images. Since downstream analysis is typically performed at the cluster level, practitioners seek reliable and interpretable clustering models. We propose a new deep-learning framework for general domain tabular data that predicts interpretable cluster assignments at the instance and cluster levels. First, we present a self-supervised procedure to identify the subset of the most informative features from each da"},"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":"2306.04785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T21:08:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cfb7f6de22c1f9c9301f1dffff798c7922c7e028fbed9355b2a4bee909d91552","abstract_canon_sha256":"acfa3844ca469f3d057778e22e796c9beacdebd570015d025bd683244eb0bd12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:15.846392Z","signature_b64":"k5gA7Euua6nRmrcJZ+Jy+SUDwb0trpJSqz6NEovXmDsv3I59cEAAPUspTRD2UzfA6N5wWh1Orv0ss8sqnrGjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e64345ece05dba4ba3cd18b39ea0bbafef2c3a728cea6e49d5aed490980a4e17","last_reissued_at":"2026-07-05T08:29:15.845885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:15.845885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Deep Clustering for Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonathan Svirsky, Ofir Lindenbaum","submitted_at":"2023-06-07T21:08:09Z","abstract_excerpt":"Clustering is a fundamental learning task widely used as a first step in data analysis. For example, biologists use cluster assignments to analyze genome sequences, medical records, or images. Since downstream analysis is typically performed at the cluster level, practitioners seek reliable and interpretable clustering models. We propose a new deep-learning framework for general domain tabular data that predicts interpretable cluster assignments at the instance and cluster levels. First, we present a self-supervised procedure to identify the subset of the most informative features from each da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04785","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04785/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2306.04785","created_at":"2026-07-05T08:29:15.845943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04785v2","created_at":"2026-07-05T08:29:15.845943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04785","created_at":"2026-07-05T08:29:15.845943+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZBUL3HALW5E","created_at":"2026-07-05T08:29:15.845943+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZBUL3HALW5EXI6N","created_at":"2026-07-05T08:29:15.845943+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZBUL3HA","created_at":"2026-07-05T08:29:15.845943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05877","citing_title":"Interpretable Clustering Ensemble","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7","json":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7.json","graph_json":"https://pith.science/api/pith-number/4ZBUL3HALW5EXI6NDCZZ5IF3V7/graph.json","events_json":"https://pith.science/api/pith-number/4ZBUL3HALW5EXI6NDCZZ5IF3V7/events.json","paper":"https://pith.science/paper/4ZBUL3HA"},"agent_actions":{"view_html":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7","download_json":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7.json","view_paper":"https://pith.science/paper/4ZBUL3HA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04785&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZBUL3HALW5EXI6NDCZZ5IF3V7/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZBUL3HALW5EXI6NDCZZ5IF3V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7/action/storage_attestation","attest_author":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7/action/author_attestation","sign_citation":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7/action/citation_signature","submit_replication":"https://pith.science/pith/4ZBUL3HALW5EXI6NDCZZ5IF3V7/action/replication_record"}},"created_at":"2026-07-05T08:29:15.845943+00:00","updated_at":"2026-07-05T08:29:15.845943+00:00"}