{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YQLKRTN572K3E6ZIZYRRJUGCZ2","short_pith_number":"pith:YQLKRTN5","schema_version":"1.0","canonical_sha256":"c416a8cdbdfe95b27b28ce2314d0c2ce8e072d709830978fe14691ceb57d6660","source":{"kind":"arxiv","id":"2507.22665","version":1},"attestation_state":"computed","paper":{"title":"Cluster-Based Random Forest Visualization and Interpretation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Christofer Meinecke, Dennis Collaris, Max Sondag, Stef van den Elzen, Tatiana von Landesberger","submitted_at":"2025-07-30T13:22:28Z","abstract_excerpt":"Random forests are a machine learning method used to automatically classify datasets and consist of a multitude of decision trees. While these random forests often have higher performance and generalize better than a single decision tree, they are also harder to interpret. This paper presents a visualization method and system to increase interpretability of random forests. We cluster similar trees which enables users to interpret how the model performs in general without needing to analyze each individual decision tree in detail, or interpret an oversimplified summary of the full forest. To me"},"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":"2507.22665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T13:22:28Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"7e221660a6abc7ef1b59f113fcf3e6d911c206339b2835063bfd842357b6c4cb","abstract_canon_sha256":"a3a7d212909878162da99dabc5063b09e3bb6f13ba137846308c89c728d2a4b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:46.544735Z","signature_b64":"9jB63nVlwOw40m1ELTtjxbPzsG2+WW6WoPKCV2qH5HW7CDBB0T8jYV+jPGWWfzItI3BvajQmo8tpe3cX92S0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c416a8cdbdfe95b27b28ce2314d0c2ce8e072d709830978fe14691ceb57d6660","last_reissued_at":"2026-07-05T11:45:46.544223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:46.544223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cluster-Based Random Forest Visualization and Interpretation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Christofer Meinecke, Dennis Collaris, Max Sondag, Stef van den Elzen, Tatiana von Landesberger","submitted_at":"2025-07-30T13:22:28Z","abstract_excerpt":"Random forests are a machine learning method used to automatically classify datasets and consist of a multitude of decision trees. While these random forests often have higher performance and generalize better than a single decision tree, they are also harder to interpret. This paper presents a visualization method and system to increase interpretability of random forests. We cluster similar trees which enables users to interpret how the model performs in general without needing to analyze each individual decision tree in detail, or interpret an oversimplified summary of the full forest. To me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22665","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/2507.22665/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":"2507.22665","created_at":"2026-07-05T11:45:46.544283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22665v1","created_at":"2026-07-05T11:45:46.544283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22665","created_at":"2026-07-05T11:45:46.544283+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQLKRTN572K3","created_at":"2026-07-05T11:45:46.544283+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQLKRTN572K3E6ZI","created_at":"2026-07-05T11:45:46.544283+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQLKRTN5","created_at":"2026-07-05T11:45:46.544283+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/YQLKRTN572K3E6ZIZYRRJUGCZ2","json":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2.json","graph_json":"https://pith.science/api/pith-number/YQLKRTN572K3E6ZIZYRRJUGCZ2/graph.json","events_json":"https://pith.science/api/pith-number/YQLKRTN572K3E6ZIZYRRJUGCZ2/events.json","paper":"https://pith.science/paper/YQLKRTN5"},"agent_actions":{"view_html":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2","download_json":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2.json","view_paper":"https://pith.science/paper/YQLKRTN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22665&json=true","fetch_graph":"https://pith.science/api/pith-number/YQLKRTN572K3E6ZIZYRRJUGCZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/YQLKRTN572K3E6ZIZYRRJUGCZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2/action/storage_attestation","attest_author":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2/action/author_attestation","sign_citation":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2/action/citation_signature","submit_replication":"https://pith.science/pith/YQLKRTN572K3E6ZIZYRRJUGCZ2/action/replication_record"}},"created_at":"2026-07-05T11:45:46.544283+00:00","updated_at":"2026-07-05T11:45:46.544283+00:00"}