{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3ZGR5NM77OIENCVNXTTFZ6TY47","short_pith_number":"pith:3ZGR5NM7","schema_version":"1.0","canonical_sha256":"de4d1eb59ffb90468aadbce65cfa78e7d34da143e882fb8dbc8207b711bbe5b2","source":{"kind":"arxiv","id":"1907.00325","version":7},"attestation_state":"computed","paper":{"title":"Random Forests for Adaptive Nearest Neighbor Estimation of Information-Theoretic Quantities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cencheng Shen, Eva Yezerets, Hayden Helm, Jes\\'us Arroyo, Joshua T. Vogelstein, Mike Powell, Richard Guo, Ronak Mehta, Ronan Perry","submitted_at":"2019-06-30T05:59:50Z","abstract_excerpt":"Information-theoretic quantities, such as conditional entropy and mutual information, are critical data summaries for quantifying uncertainty. Current widely used approaches for computing such quantities rely on nearest neighbor methods and exhibit both strong performance and theoretical guarantees in certain simple scenarios. However, existing approaches fail in high-dimensional settings and when different features are measured on different scales.We propose decision forest-based adaptive nearest neighbor estimators and show that they are able to effectively estimate posterior probabilities, "},"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":"1907.00325","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T05:59:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5bf7691b31a4f32b2b8f71e47dee8d9ae599d4bf678e5b7ab179c6cd80f93b67","abstract_canon_sha256":"5085e0360b2370d15200cbe66f7395baee31e0ac38e66d5f4847c201f5f33361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:14.269524Z","signature_b64":"+UfYHNpcXFWyd80oatCa/WSPrr0e3vPuJ0C+czAhnCSwhNopaNJrNsCqMxI9ZhSUxks4VmfdT/j5NFm6JNFZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4d1eb59ffb90468aadbce65cfa78e7d34da143e882fb8dbc8207b711bbe5b2","last_reissued_at":"2026-07-05T03:20:14.269141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:14.269141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Forests for Adaptive Nearest Neighbor Estimation of Information-Theoretic Quantities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cencheng Shen, Eva Yezerets, Hayden Helm, Jes\\'us Arroyo, Joshua T. Vogelstein, Mike Powell, Richard Guo, Ronak Mehta, Ronan Perry","submitted_at":"2019-06-30T05:59:50Z","abstract_excerpt":"Information-theoretic quantities, such as conditional entropy and mutual information, are critical data summaries for quantifying uncertainty. Current widely used approaches for computing such quantities rely on nearest neighbor methods and exhibit both strong performance and theoretical guarantees in certain simple scenarios. However, existing approaches fail in high-dimensional settings and when different features are measured on different scales.We propose decision forest-based adaptive nearest neighbor estimators and show that they are able to effectively estimate posterior probabilities, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00325","kind":"arxiv","version":7},"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/1907.00325/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":"1907.00325","created_at":"2026-07-05T03:20:14.269198+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00325v7","created_at":"2026-07-05T03:20:14.269198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00325","created_at":"2026-07-05T03:20:14.269198+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZGR5NM77OIE","created_at":"2026-07-05T03:20:14.269198+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZGR5NM77OIENCVN","created_at":"2026-07-05T03:20:14.269198+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZGR5NM7","created_at":"2026-07-05T03:20:14.269198+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/3ZGR5NM77OIENCVNXTTFZ6TY47","json":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47.json","graph_json":"https://pith.science/api/pith-number/3ZGR5NM77OIENCVNXTTFZ6TY47/graph.json","events_json":"https://pith.science/api/pith-number/3ZGR5NM77OIENCVNXTTFZ6TY47/events.json","paper":"https://pith.science/paper/3ZGR5NM7"},"agent_actions":{"view_html":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47","download_json":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47.json","view_paper":"https://pith.science/paper/3ZGR5NM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00325&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZGR5NM77OIENCVNXTTFZ6TY47/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZGR5NM77OIENCVNXTTFZ6TY47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47/action/storage_attestation","attest_author":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47/action/author_attestation","sign_citation":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47/action/citation_signature","submit_replication":"https://pith.science/pith/3ZGR5NM77OIENCVNXTTFZ6TY47/action/replication_record"}},"created_at":"2026-07-05T03:20:14.269198+00:00","updated_at":"2026-07-05T03:20:14.269198+00:00"}