{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J4HBP2QMLLEJU5BV2V47GYPJ6U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6160d3d11bf3b53147ddb7626e2d45b039268f42372adaabbe7047b6b7e1c771","cross_cats_sorted":["stat.AP","stat.CO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T01:58:45Z","title_canon_sha256":"68d77645492ff4cc1399805a81923d1c4c025e6cca5c3cde62efb42f102bc8b3"},"schema_version":"1.0","source":{"id":"2506.04553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04553","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04553v1","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04553","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"J4HBP2QMLLEJ","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_16","alias_value":"J4HBP2QMLLEJU5BV","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_8","alias_value":"J4HBP2QM","created_at":"2026-07-05T11:16:16Z"}],"graph_snapshots":[{"event_id":"sha256:7142b4a9c0ae58b08bf648ec259d2bbc5d2537046630873e2794748d21054557","target":"graph","created_at":"2026-07-05T11:16:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.04553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andersen Chang, Genevera I. Allen, Tarek M. Zikry, Tiffany M. Tang","cross_cats":["stat.AP","stat.CO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04553","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1722d4216a56ff412269f0a0d02e80d33eb5a4d3dbcad7ad7de272891383646d","target":"record","created_at":"2026-07-05T11:16:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6160d3d11bf3b53147ddb7626e2d45b039268f42372adaabbe7047b6b7e1c771","cross_cats_sorted":["stat.AP","stat.CO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T01:58:45Z","title_canon_sha256":"68d77645492ff4cc1399805a81923d1c4c025e6cca5c3cde62efb42f102bc8b3"},"schema_version":"1.0","source":{"id":"2506.04553","kind":"arxiv","version":1}},"canonical_sha256":"4f0e17ea0c5ac89a7435d579f361e9f5281b02e9586b96d030de0b492334602f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f0e17ea0c5ac89a7435d579f361e9f5281b02e9586b96d030de0b492334602f","first_computed_at":"2026-07-05T11:16:16.552182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:16.552182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F40x56YqfVTCmFXLulxnmCWklcfl93jFOlfV6cwzsgEEyB/ePEPCxrxzIJVUH34nYxF0aw+OEVsSWJbIyi+BBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:16.552709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1722d4216a56ff412269f0a0d02e80d33eb5a4d3dbcad7ad7de272891383646d","sha256:7142b4a9c0ae58b08bf648ec259d2bbc5d2537046630873e2794748d21054557"],"state_sha256":"7b8c8ec232cf870dba8c2cfb6c8eadcfb759bdb88c58b0d5fd59578ff4bb23dd"}