{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XBVPQL5GTT3S5QRGWJQMXXZTVM","short_pith_number":"pith:XBVPQL5G","schema_version":"1.0","canonical_sha256":"b86af82fa69cf72ec226b260cbdf33ab2a76b5e94718b71899f186cb7ccfd3cd","source":{"kind":"arxiv","id":"2507.19455","version":1},"attestation_state":"computed","paper":{"title":"Forest-Guided Clustering -- Shedding Light into the Random Forest Black Box","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dominik Thalmeier, Gregor Miller, Helena Pelin, Lisa Barros de Andrade e Sousa, Marie Piraud, Ronan Le Gleut","submitted_at":"2025-07-25T17:41:39Z","abstract_excerpt":"As machine learning models are increasingly deployed in sensitive application areas, the demand for interpretable and trustworthy decision-making has increased. Random Forests (RF), despite their widespread use and strong performance on tabular data, remain difficult to interpret due to their ensemble nature. We present Forest-Guided Clustering (FGC), a model-specific explainability method that reveals both local and global structure in RFs by grouping instances according to shared decision paths. FGC produces human-interpretable clusters aligned with the model's internal logic and computes cl"},"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":"2507.19455","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:41:39Z","cross_cats_sorted":[],"title_canon_sha256":"32b29ebed96a27e5f5bb1f7b6ea6e44604d9e50476f8cc2272998ead562a9f13","abstract_canon_sha256":"fc13d099194636cff98a39e5a2556ccac546f383dcb57882fa6b1e40c661855d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:25.553606Z","signature_b64":"jER/qUSnB3ITBPWPUiEl3QBUboSZau+NWOvdATRr7NimYp7nfHgGG7uLyqZXEJZGU4Tu3EyzOSFiziKANrqYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86af82fa69cf72ec226b260cbdf33ab2a76b5e94718b71899f186cb7ccfd3cd","last_reissued_at":"2026-07-05T11:43:25.553129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:25.553129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forest-Guided Clustering -- Shedding Light into the Random Forest Black Box","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dominik Thalmeier, Gregor Miller, Helena Pelin, Lisa Barros de Andrade e Sousa, Marie Piraud, Ronan Le Gleut","submitted_at":"2025-07-25T17:41:39Z","abstract_excerpt":"As machine learning models are increasingly deployed in sensitive application areas, the demand for interpretable and trustworthy decision-making has increased. Random Forests (RF), despite their widespread use and strong performance on tabular data, remain difficult to interpret due to their ensemble nature. We present Forest-Guided Clustering (FGC), a model-specific explainability method that reveals both local and global structure in RFs by grouping instances according to shared decision paths. FGC produces human-interpretable clusters aligned with the model's internal logic and computes cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19455","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/2507.19455/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":"2507.19455","created_at":"2026-07-05T11:43:25.553190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19455v1","created_at":"2026-07-05T11:43:25.553190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19455","created_at":"2026-07-05T11:43:25.553190+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBVPQL5GTT3S","created_at":"2026-07-05T11:43:25.553190+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBVPQL5GTT3S5QRG","created_at":"2026-07-05T11:43:25.553190+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBVPQL5G","created_at":"2026-07-05T11:43:25.553190+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/XBVPQL5GTT3S5QRGWJQMXXZTVM","json":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM.json","graph_json":"https://pith.science/api/pith-number/XBVPQL5GTT3S5QRGWJQMXXZTVM/graph.json","events_json":"https://pith.science/api/pith-number/XBVPQL5GTT3S5QRGWJQMXXZTVM/events.json","paper":"https://pith.science/paper/XBVPQL5G"},"agent_actions":{"view_html":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM","download_json":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM.json","view_paper":"https://pith.science/paper/XBVPQL5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19455&json=true","fetch_graph":"https://pith.science/api/pith-number/XBVPQL5GTT3S5QRGWJQMXXZTVM/graph.json","fetch_events":"https://pith.science/api/pith-number/XBVPQL5GTT3S5QRGWJQMXXZTVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM/action/storage_attestation","attest_author":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM/action/author_attestation","sign_citation":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM/action/citation_signature","submit_replication":"https://pith.science/pith/XBVPQL5GTT3S5QRGWJQMXXZTVM/action/replication_record"}},"created_at":"2026-07-05T11:43:25.553190+00:00","updated_at":"2026-07-05T11:43:25.553190+00:00"}