{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:INPYIIK4QDKXJA4NL5BN3QKJW6","short_pith_number":"pith:INPYIIK4","schema_version":"1.0","canonical_sha256":"435f84215c80d574838d5f42ddc149b780acec30d9654c037fbbfc784c426c29","source":{"kind":"arxiv","id":"2001.04721","version":4},"attestation_state":"computed","paper":{"title":"Interpretation and Simplification of Deep Forest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Byoung Chul Ko, Mira Jeong, Sangwon Kim","submitted_at":"2020-01-14T11:30:26Z","abstract_excerpt":"This paper proposes a new method for interpreting and simplifying a black box model of a deep random forest (RF) using a proposed rule elimination. In deep RF, a large number of decision trees are connected to multiple layers, thereby making an analysis difficult. It has a high performance similar to that of a deep neural network (DNN), but achieves a better generalizability. Therefore, in this study, we consider quantifying the feature contributions and frequency of the fully trained deep RF in the form of a decision rule set. The feature contributions provide a basis for determining how feat"},"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":"2001.04721","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-14T11:30:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c4f7de34b77d3410aa3bfa3d7f83dc8481df0accad7f9d390498adfe5dc9ea6c","abstract_canon_sha256":"dcb5babcd7395b8b545f8d76da8aed5c874442aea2d7cf2b8198a5b34d217a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:54.432514Z","signature_b64":"DLAtrnZmnrbxbu728QIQacjx3wW+6Gvv1K7giEPHz3jZFpXkzN/QDpXw+mTYVHEm24AkcJX/Ci76vmru9xsGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"435f84215c80d574838d5f42ddc149b780acec30d9654c037fbbfc784c426c29","last_reissued_at":"2026-07-05T01:58:54.432007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:54.432007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretation and Simplification of Deep Forest","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Byoung Chul Ko, Mira Jeong, Sangwon Kim","submitted_at":"2020-01-14T11:30:26Z","abstract_excerpt":"This paper proposes a new method for interpreting and simplifying a black box model of a deep random forest (RF) using a proposed rule elimination. In deep RF, a large number of decision trees are connected to multiple layers, thereby making an analysis difficult. It has a high performance similar to that of a deep neural network (DNN), but achieves a better generalizability. Therefore, in this study, we consider quantifying the feature contributions and frequency of the fully trained deep RF in the form of a decision rule set. The feature contributions provide a basis for determining how feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04721","kind":"arxiv","version":4},"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/2001.04721/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":"2001.04721","created_at":"2026-07-05T01:58:54.432069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04721v4","created_at":"2026-07-05T01:58:54.432069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04721","created_at":"2026-07-05T01:58:54.432069+00:00"},{"alias_kind":"pith_short_12","alias_value":"INPYIIK4QDKX","created_at":"2026-07-05T01:58:54.432069+00:00"},{"alias_kind":"pith_short_16","alias_value":"INPYIIK4QDKXJA4N","created_at":"2026-07-05T01:58:54.432069+00:00"},{"alias_kind":"pith_short_8","alias_value":"INPYIIK4","created_at":"2026-07-05T01:58:54.432069+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/INPYIIK4QDKXJA4NL5BN3QKJW6","json":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6.json","graph_json":"https://pith.science/api/pith-number/INPYIIK4QDKXJA4NL5BN3QKJW6/graph.json","events_json":"https://pith.science/api/pith-number/INPYIIK4QDKXJA4NL5BN3QKJW6/events.json","paper":"https://pith.science/paper/INPYIIK4"},"agent_actions":{"view_html":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6","download_json":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6.json","view_paper":"https://pith.science/paper/INPYIIK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04721&json=true","fetch_graph":"https://pith.science/api/pith-number/INPYIIK4QDKXJA4NL5BN3QKJW6/graph.json","fetch_events":"https://pith.science/api/pith-number/INPYIIK4QDKXJA4NL5BN3QKJW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6/action/storage_attestation","attest_author":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6/action/author_attestation","sign_citation":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6/action/citation_signature","submit_replication":"https://pith.science/pith/INPYIIK4QDKXJA4NL5BN3QKJW6/action/replication_record"}},"created_at":"2026-07-05T01:58:54.432069+00:00","updated_at":"2026-07-05T01:58:54.432069+00:00"}