{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VX4YFMXBCLXCKOKQIUXPHZ25IL","short_pith_number":"pith:VX4YFMXB","schema_version":"1.0","canonical_sha256":"adf982b2e112ee253950452ef3e75d42f855e592df03cfed033dce0d3bef05eb","source":{"kind":"arxiv","id":"2410.21520","version":4},"attestation_state":"computed","paper":{"title":"LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Curtiss B. Cook, Jiaru Zou, Jingrui He, Tianxin Wei, Xinrui He, Yikun Ban","submitted_at":"2024-10-28T20:42:46Z","abstract_excerpt":"Missing data imputation is a critical challenge in various domains, such as healthcare and finance, where data completeness is vital for accurate analysis. Large language models (LLMs), trained on vast corpora, have shown strong potential in data generation, making them a promising tool for data imputation. However, challenges persist in designing effective prompts for a finetuning-free process and in mitigating biases and uncertainty in LLM outputs. To address these issues, we propose a novel framework, LLM-Forest, which introduces a \"forest\" of few-shot prompt learning LLM \"trees\" with their"},"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":"2410.21520","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T20:42:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"69a564882375fcc19d8508ac2106f6c3957e5687ebc3121fcf0b30bab12f665e","abstract_canon_sha256":"5ef12d7b44089b9f1264fdfb9628c1854e97f6a74e762f4cb24e70401bedd603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:21.392955Z","signature_b64":"KVZde8uMPLJheu4mBZK8palcREVAkpD+lzyfOk+rxglnmBooTZCwDlb4pLMx0LKW70BQ5CcHsw/rxg4QCRSUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adf982b2e112ee253950452ef3e75d42f855e592df03cfed033dce0d3bef05eb","last_reissued_at":"2026-07-05T11:58:21.392518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:21.392518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Curtiss B. Cook, Jiaru Zou, Jingrui He, Tianxin Wei, Xinrui He, Yikun Ban","submitted_at":"2024-10-28T20:42:46Z","abstract_excerpt":"Missing data imputation is a critical challenge in various domains, such as healthcare and finance, where data completeness is vital for accurate analysis. Large language models (LLMs), trained on vast corpora, have shown strong potential in data generation, making them a promising tool for data imputation. However, challenges persist in designing effective prompts for a finetuning-free process and in mitigating biases and uncertainty in LLM outputs. To address these issues, we propose a novel framework, LLM-Forest, which introduces a \"forest\" of few-shot prompt learning LLM \"trees\" with their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21520","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/2410.21520/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":"2410.21520","created_at":"2026-07-05T11:58:21.392575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21520v4","created_at":"2026-07-05T11:58:21.392575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21520","created_at":"2026-07-05T11:58:21.392575+00:00"},{"alias_kind":"pith_short_12","alias_value":"VX4YFMXBCLXC","created_at":"2026-07-05T11:58:21.392575+00:00"},{"alias_kind":"pith_short_16","alias_value":"VX4YFMXBCLXCKOKQ","created_at":"2026-07-05T11:58:21.392575+00:00"},{"alias_kind":"pith_short_8","alias_value":"VX4YFMXB","created_at":"2026-07-05T11:58:21.392575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17336","citing_title":"APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL","json":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL.json","graph_json":"https://pith.science/api/pith-number/VX4YFMXBCLXCKOKQIUXPHZ25IL/graph.json","events_json":"https://pith.science/api/pith-number/VX4YFMXBCLXCKOKQIUXPHZ25IL/events.json","paper":"https://pith.science/paper/VX4YFMXB"},"agent_actions":{"view_html":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL","download_json":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL.json","view_paper":"https://pith.science/paper/VX4YFMXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21520&json=true","fetch_graph":"https://pith.science/api/pith-number/VX4YFMXBCLXCKOKQIUXPHZ25IL/graph.json","fetch_events":"https://pith.science/api/pith-number/VX4YFMXBCLXCKOKQIUXPHZ25IL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL/action/storage_attestation","attest_author":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL/action/author_attestation","sign_citation":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL/action/citation_signature","submit_replication":"https://pith.science/pith/VX4YFMXBCLXCKOKQIUXPHZ25IL/action/replication_record"}},"created_at":"2026-07-05T11:58:21.392575+00:00","updated_at":"2026-07-05T11:58:21.392575+00:00"}