{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R455UFM2EI5JSGCJKXBGXET46P","short_pith_number":"pith:R455UFM2","schema_version":"1.0","canonical_sha256":"8f3bda159a223a99184955c26b927cf3c410dbbd197f4f35dfadd8e5091c4231","source":{"kind":"arxiv","id":"2605.23102","version":1},"attestation_state":"computed","paper":{"title":"LLM Sparsity Prior for Robust Feature Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Caleb Skinner, Meng Li, Yihan Guo","submitted_at":"2026-05-21T23:34:04Z","abstract_excerpt":"Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However, existing methods such as LLM-Lasso are sensitive to weight quality, with performance degrading substantially when LLM-generated weights are inaccurate. To address this challenge, we first introduce a framework for quantifying the quality of LLM-generated weights, enabling rigorous evaluation of LLM-informed methods across varying weight regimes. We then propose the LLM Sparsity Prior (LSP), which integrates LLM-generated weights into the prior in"},"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":"2605.23102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-21T23:34:04Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"f2e35f7437ba4703926777b0654e7463b8f037a937cc5bccb09048295da548d2","abstract_canon_sha256":"4f8d94f72cb7ef19de7382f9aa596fa82b9bcb945e5e2db36dcf615b5ffd6f1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:38.254550Z","signature_b64":"S09f3x+8JMMiE5vdn6ZqTCBGRi0DtNYmNNG2MieOJGUwd/xJxFEeu9t7i1Rh9YRni+t7AC1gugvlYB8MFq9rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3bda159a223a99184955c26b927cf3c410dbbd197f4f35dfadd8e5091c4231","last_reissued_at":"2026-05-25T02:01:38.253939Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:38.253939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Sparsity Prior for Robust Feature Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Caleb Skinner, Meng Li, Yihan Guo","submitted_at":"2026-05-21T23:34:04Z","abstract_excerpt":"Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However, existing methods such as LLM-Lasso are sensitive to weight quality, with performance degrading substantially when LLM-generated weights are inaccurate. To address this challenge, we first introduce a framework for quantifying the quality of LLM-generated weights, enabling rigorous evaluation of LLM-informed methods across varying weight regimes. We then propose the LLM Sparsity Prior (LSP), which integrates LLM-generated weights into the prior in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23102","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/2605.23102/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":"2605.23102","created_at":"2026-05-25T02:01:38.254027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23102v1","created_at":"2026-05-25T02:01:38.254027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23102","created_at":"2026-05-25T02:01:38.254027+00:00"},{"alias_kind":"pith_short_12","alias_value":"R455UFM2EI5J","created_at":"2026-05-25T02:01:38.254027+00:00"},{"alias_kind":"pith_short_16","alias_value":"R455UFM2EI5JSGCJ","created_at":"2026-05-25T02:01:38.254027+00:00"},{"alias_kind":"pith_short_8","alias_value":"R455UFM2","created_at":"2026-05-25T02:01:38.254027+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/R455UFM2EI5JSGCJKXBGXET46P","json":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P.json","graph_json":"https://pith.science/api/pith-number/R455UFM2EI5JSGCJKXBGXET46P/graph.json","events_json":"https://pith.science/api/pith-number/R455UFM2EI5JSGCJKXBGXET46P/events.json","paper":"https://pith.science/paper/R455UFM2"},"agent_actions":{"view_html":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P","download_json":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P.json","view_paper":"https://pith.science/paper/R455UFM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23102&json=true","fetch_graph":"https://pith.science/api/pith-number/R455UFM2EI5JSGCJKXBGXET46P/graph.json","fetch_events":"https://pith.science/api/pith-number/R455UFM2EI5JSGCJKXBGXET46P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P/action/storage_attestation","attest_author":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P/action/author_attestation","sign_citation":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P/action/citation_signature","submit_replication":"https://pith.science/pith/R455UFM2EI5JSGCJKXBGXET46P/action/replication_record"}},"created_at":"2026-05-25T02:01:38.254027+00:00","updated_at":"2026-05-25T02:01:38.254027+00:00"}