{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J4HBP2QMLLEJU5BV2V47GYPJ6U","short_pith_number":"pith:J4HBP2QM","schema_version":"1.0","canonical_sha256":"4f0e17ea0c5ac89a7435d579f361e9f5281b02e9586b96d030de0b492334602f","source":{"kind":"arxiv","id":"2506.04553","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andersen Chang, Genevera I. Allen, Tarek M. Zikry, Tiffany M. Tang","submitted_at":"2025-06-05T01:58:45Z","abstract_excerpt":"Unsupervised machine learning is widely used to mine large, unlabeled datasets to make data-driven discoveries in critical domains such as climate science, biomedicine, astronomy, chemistry, and more. However, despite its widespread utilization, there is a lack of standardization in unsupervised learning workflows for making reliable and reproducible scientific discoveries. In this paper, we present a structured workflow for using unsupervised learning techniques in science. We highlight and discuss best practices starting with formulating validatable scientific questions, conducting robust 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":"2506.04553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T01:58:45Z","cross_cats_sorted":["stat.AP","stat.CO","stat.ML"],"title_canon_sha256":"68d77645492ff4cc1399805a81923d1c4c025e6cca5c3cde62efb42f102bc8b3","abstract_canon_sha256":"6160d3d11bf3b53147ddb7626e2d45b039268f42372adaabbe7047b6b7e1c771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:16.552709Z","signature_b64":"F40x56YqfVTCmFXLulxnmCWklcfl93jFOlfV6cwzsgEEyB/ePEPCxrxzIJVUH34nYxF0aw+OEVsSWJbIyi+BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f0e17ea0c5ac89a7435d579f361e9f5281b02e9586b96d030de0b492334602f","last_reissued_at":"2026-07-05T11:16:16.552182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:16.552182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andersen Chang, Genevera I. Allen, Tarek M. Zikry, Tiffany M. Tang","submitted_at":"2025-06-05T01:58:45Z","abstract_excerpt":"Unsupervised machine learning is widely used to mine large, unlabeled datasets to make data-driven discoveries in critical domains such as climate science, biomedicine, astronomy, chemistry, and more. However, despite its widespread utilization, there is a lack of standardization in unsupervised learning workflows for making reliable and reproducible scientific discoveries. In this paper, we present a structured workflow for using unsupervised learning techniques in science. We highlight and discuss best practices starting with formulating validatable scientific questions, conducting robust da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04553","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.04553/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":"2506.04553","created_at":"2026-07-05T11:16:16.552225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04553v1","created_at":"2026-07-05T11:16:16.552225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04553","created_at":"2026-07-05T11:16:16.552225+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4HBP2QMLLEJ","created_at":"2026-07-05T11:16:16.552225+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4HBP2QMLLEJU5BV","created_at":"2026-07-05T11:16:16.552225+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4HBP2QM","created_at":"2026-07-05T11:16:16.552225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24244","citing_title":"MEDAL: Manifold Embedding Distillation via Autoencoder Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03488","citing_title":"Inference for Clustering: Conformal Sets for Cluster Labels","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U","json":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U.json","graph_json":"https://pith.science/api/pith-number/J4HBP2QMLLEJU5BV2V47GYPJ6U/graph.json","events_json":"https://pith.science/api/pith-number/J4HBP2QMLLEJU5BV2V47GYPJ6U/events.json","paper":"https://pith.science/paper/J4HBP2QM"},"agent_actions":{"view_html":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U","download_json":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U.json","view_paper":"https://pith.science/paper/J4HBP2QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04553&json=true","fetch_graph":"https://pith.science/api/pith-number/J4HBP2QMLLEJU5BV2V47GYPJ6U/graph.json","fetch_events":"https://pith.science/api/pith-number/J4HBP2QMLLEJU5BV2V47GYPJ6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U/action/storage_attestation","attest_author":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U/action/author_attestation","sign_citation":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U/action/citation_signature","submit_replication":"https://pith.science/pith/J4HBP2QMLLEJU5BV2V47GYPJ6U/action/replication_record"}},"created_at":"2026-07-05T11:16:16.552225+00:00","updated_at":"2026-07-05T11:16:16.552225+00:00"}