{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R2FLGBEWCSWVRAOGWZKMMSZDND","short_pith_number":"pith:R2FLGBEW","schema_version":"1.0","canonical_sha256":"8e8ab3049614ad5881c6b654c64b2368d991c85a821f6f90368d5350fc1cfae6","source":{"kind":"arxiv","id":"2408.10340","version":1},"attestation_state":"computed","paper":{"title":"Can an unsupervised clustering algorithm reproduce a categorization system?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.ST","stat.AP"],"primary_cat":"stat.ML","authors_text":"Dhagash Mehta, Dhruv Desai, Nathalia Castellanos, Sebastian Frank, Stefano Pasquali","submitted_at":"2024-08-19T18:27:14Z","abstract_excerpt":"Peer analysis is a critical component of investment management, often relying on expert-provided categorization systems. These systems' consistency is questioned when they do not align with cohorts from unsupervised clustering algorithms optimized for various metrics. We investigate whether unsupervised clustering can reproduce ground truth classes in a labeled dataset, showing that success depends on feature selection and the chosen distance metric. Using toy datasets and fund categorization as real-world examples we demonstrate that accurately reproducing ground truth classes is challenging."},"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":"2408.10340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T18:27:14Z","cross_cats_sorted":["cs.LG","q-fin.ST","stat.AP"],"title_canon_sha256":"aafd9baa811dca9f248b51c9ce2aaaa9e47d895fd2f89ef23d863d07438d1ea5","abstract_canon_sha256":"87149ee4a8d9108919d80c057124a993405aeacd3842afd0fa685671fa562653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:09.929879Z","signature_b64":"8DrJYGEWUOkQN2FVrQNn/K2vDtNVmCktXsYCLGhC3wL8uCnS5h7rUY89EWS9HEgPMwwjLR78hkuORUWyZIhDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e8ab3049614ad5881c6b654c64b2368d991c85a821f6f90368d5350fc1cfae6","last_reissued_at":"2026-07-05T08:57:09.929404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:09.929404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can an unsupervised clustering algorithm reproduce a categorization system?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.ST","stat.AP"],"primary_cat":"stat.ML","authors_text":"Dhagash Mehta, Dhruv Desai, Nathalia Castellanos, Sebastian Frank, Stefano Pasquali","submitted_at":"2024-08-19T18:27:14Z","abstract_excerpt":"Peer analysis is a critical component of investment management, often relying on expert-provided categorization systems. These systems' consistency is questioned when they do not align with cohorts from unsupervised clustering algorithms optimized for various metrics. We investigate whether unsupervised clustering can reproduce ground truth classes in a labeled dataset, showing that success depends on feature selection and the chosen distance metric. Using toy datasets and fund categorization as real-world examples we demonstrate that accurately reproducing ground truth classes is challenging."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10340","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/2408.10340/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":"2408.10340","created_at":"2026-07-05T08:57:09.929465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10340v1","created_at":"2026-07-05T08:57:09.929465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10340","created_at":"2026-07-05T08:57:09.929465+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2FLGBEWCSWV","created_at":"2026-07-05T08:57:09.929465+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2FLGBEWCSWVRAOG","created_at":"2026-07-05T08:57:09.929465+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2FLGBEW","created_at":"2026-07-05T08:57:09.929465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01495","citing_title":"Supervised Similarity for High-Yield Corporate Bonds with Quantum Cognition Machine Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND","json":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND.json","graph_json":"https://pith.science/api/pith-number/R2FLGBEWCSWVRAOGWZKMMSZDND/graph.json","events_json":"https://pith.science/api/pith-number/R2FLGBEWCSWVRAOGWZKMMSZDND/events.json","paper":"https://pith.science/paper/R2FLGBEW"},"agent_actions":{"view_html":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND","download_json":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND.json","view_paper":"https://pith.science/paper/R2FLGBEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10340&json=true","fetch_graph":"https://pith.science/api/pith-number/R2FLGBEWCSWVRAOGWZKMMSZDND/graph.json","fetch_events":"https://pith.science/api/pith-number/R2FLGBEWCSWVRAOGWZKMMSZDND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND/action/storage_attestation","attest_author":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND/action/author_attestation","sign_citation":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND/action/citation_signature","submit_replication":"https://pith.science/pith/R2FLGBEWCSWVRAOGWZKMMSZDND/action/replication_record"}},"created_at":"2026-07-05T08:57:09.929465+00:00","updated_at":"2026-07-05T08:57:09.929465+00:00"}