{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EYNFW7UGONJM4IKEVU6L5N5MPB","short_pith_number":"pith:EYNFW7UG","schema_version":"1.0","canonical_sha256":"261a5b7e867352ce2144ad3cbeb7ac787c7975fb118db82fb16f40c44c347251","source":{"kind":"arxiv","id":"2505.24622","version":3},"attestation_state":"computed","paper":{"title":"Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aaron Ontoyin Yin, Ben Griffin, Diego Vidaurre, Fuat Alican, Joseph Ternasky, Ugur Koyluoglu, Yigit Ihlamur","submitted_at":"2025-05-30T14:13:21Z","abstract_excerpt":"Many high-stakes screening tasks require predicting rare outcomes from unstructured text, where errors are costly and decisions must be auditable. We introduce Random Rule Forest (RRF), an interpretable ensemble that uses a large language model (LLM) not as an end-to-end predictor but as a generator of simple YES/NO questions. Each question acts as a weak learner, and their responses are combined by a plain unit-weight vote into an auditable ``green-flags'' scorecard: enough independent positive signals indicate a higher chance of success. We argue this deliberate simplicity is a robust defaul"},"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":"2505.24622","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T14:13:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27bb3974fdf32700eebfcc992248c32b6585afdc0c628a58b410e517daaad57f","abstract_canon_sha256":"b66a1fe6a70fb5dfe164168013e1dd6809e2a167175d4a0f4ea0543b2956c8f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:57.355425Z","signature_b64":"1ETK/E0q5Zr/5KMrDboasOWi5L8NIBYwhnsJbdfG9MNBJZk5gFRMY0VQ4CGnRtyxWJyvTasu2Lu/u+1hCaPICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261a5b7e867352ce2144ad3cbeb7ac787c7975fb118db82fb16f40c44c347251","last_reissued_at":"2026-06-24T01:14:57.354961Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:57.354961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aaron Ontoyin Yin, Ben Griffin, Diego Vidaurre, Fuat Alican, Joseph Ternasky, Ugur Koyluoglu, Yigit Ihlamur","submitted_at":"2025-05-30T14:13:21Z","abstract_excerpt":"Many high-stakes screening tasks require predicting rare outcomes from unstructured text, where errors are costly and decisions must be auditable. We introduce Random Rule Forest (RRF), an interpretable ensemble that uses a large language model (LLM) not as an end-to-end predictor but as a generator of simple YES/NO questions. Each question acts as a weak learner, and their responses are combined by a plain unit-weight vote into an auditable ``green-flags'' scorecard: enough independent positive signals indicate a higher chance of success. We argue this deliberate simplicity is a robust defaul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24622","kind":"arxiv","version":3},"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/2505.24622/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":"2505.24622","created_at":"2026-06-24T01:14:57.355020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24622v3","created_at":"2026-06-24T01:14:57.355020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24622","created_at":"2026-06-24T01:14:57.355020+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYNFW7UGONJM","created_at":"2026-06-24T01:14:57.355020+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYNFW7UGONJM4IKE","created_at":"2026-06-24T01:14:57.355020+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYNFW7UG","created_at":"2026-06-24T01:14:57.355020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.14448","citing_title":"VCBench: Benchmarking LLMs in Venture Capital","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB","json":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB.json","graph_json":"https://pith.science/api/pith-number/EYNFW7UGONJM4IKEVU6L5N5MPB/graph.json","events_json":"https://pith.science/api/pith-number/EYNFW7UGONJM4IKEVU6L5N5MPB/events.json","paper":"https://pith.science/paper/EYNFW7UG"},"agent_actions":{"view_html":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB","download_json":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB.json","view_paper":"https://pith.science/paper/EYNFW7UG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24622&json=true","fetch_graph":"https://pith.science/api/pith-number/EYNFW7UGONJM4IKEVU6L5N5MPB/graph.json","fetch_events":"https://pith.science/api/pith-number/EYNFW7UGONJM4IKEVU6L5N5MPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB/action/storage_attestation","attest_author":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB/action/author_attestation","sign_citation":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB/action/citation_signature","submit_replication":"https://pith.science/pith/EYNFW7UGONJM4IKEVU6L5N5MPB/action/replication_record"}},"created_at":"2026-06-24T01:14:57.355020+00:00","updated_at":"2026-06-24T01:14:57.355020+00:00"}