{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q4RR4HSLDSD4KK727UGOD6WFIN","short_pith_number":"pith:Q4RR4HSL","canonical_record":{"source":{"id":"2502.10648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T02:55:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"142b86bc93dd1ab7a180a7bd3c620dcd06698a91672c39fb892cd93aa62b705d","abstract_canon_sha256":"c86affa51ac0ad17f1ee9f310bcaa7e1efeb26fed142403be1694fa7418b4865"},"schema_version":"1.0"},"canonical_sha256":"87231e1e4b1c87c52bfafd0ce1fac5437141f326a1cdbcc4efe9e928ccfefbb0","source":{"kind":"arxiv","id":"2502.10648","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10648","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10648v3","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10648","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q4RR4HSLDSD4","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"Q4RR4HSLDSD4KK72","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"Q4RR4HSL","created_at":"2026-07-05T11:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q4RR4HSLDSD4KK727UGOD6WFIN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T02:55:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"142b86bc93dd1ab7a180a7bd3c620dcd06698a91672c39fb892cd93aa62b705d","abstract_canon_sha256":"c86affa51ac0ad17f1ee9f310bcaa7e1efeb26fed142403be1694fa7418b4865"},"schema_version":"1.0"},"canonical_sha256":"87231e1e4b1c87c52bfafd0ce1fac5437141f326a1cdbcc4efe9e928ccfefbb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:17.824043Z","signature_b64":"MockUSrbd4XRZ2D1sxinBJsxOEQpUe48Ru8MbrOwXFlFHT0qB71dMoNWjKbbBr0OBEDiRMiiv/8Q1+wrYprHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87231e1e4b1c87c52bfafd0ce1fac5437141f326a1cdbcc4efe9e928ccfefbb0","last_reissued_at":"2026-07-05T11:52:17.823533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:17.823533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10648","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRcHZXMjqQPxweELkWSWy8v5HotfdqW4gRLjQMKkW8Sb2rZeLc2AtGKD17TpXQ8LGutAl041vzK187u8vRgZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:02:31.410792Z"},"content_sha256":"52b335bc7840aeb03356798dcd34577137fc84f70f29e9122dd637403f94114c","schema_version":"1.0","event_id":"sha256:52b335bc7840aeb03356798dcd34577137fc84f70f29e9122dd637403f94114c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q4RR4HSLDSD4KK727UGOD6WFIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ash Alizadeh, Erica Zhang, Jose Blanchet, Jurik Mutter, Kangwook Lee, Mert Pilanci, Naomi Sagan, Nick Phillips, Robert Tibshirani, Ryunosuke Goto","submitted_at":"2025-02-15T02:55:22Z","abstract_excerpt":"We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates domain-specific knowledge extracted from natural language, enhanced through a retrieval-augmented generation (RAG) pipeline, to seamlessly integrate data-driven modeling with contextual insights. Specifically, the LLM generates penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10648","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/2502.10648/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLrbmZB2mV0sa9lnbtDmy/yfQKnPD/rDFW4rLUL8fu6tHwvEA+Br1vrrOxLohKShZnF6FxoMdau91bbEx79NDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:02:31.411924Z"},"content_sha256":"1b077b58ef422998b5ed853450184f4d3648d69cf28036e91a7f734066995d87","schema_version":"1.0","event_id":"sha256:1b077b58ef422998b5ed853450184f4d3648d69cf28036e91a7f734066995d87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/bundle.json","state_url":"https://pith.science/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:02:31Z","links":{"resolver":"https://pith.science/pith/Q4RR4HSLDSD4KK727UGOD6WFIN","bundle":"https://pith.science/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/bundle.json","state":"https://pith.science/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4RR4HSLDSD4KK727UGOD6WFIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q4RR4HSLDSD4KK727UGOD6WFIN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c86affa51ac0ad17f1ee9f310bcaa7e1efeb26fed142403be1694fa7418b4865","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T02:55:22Z","title_canon_sha256":"142b86bc93dd1ab7a180a7bd3c620dcd06698a91672c39fb892cd93aa62b705d"},"schema_version":"1.0","source":{"id":"2502.10648","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10648","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10648v3","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10648","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q4RR4HSLDSD4","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"Q4RR4HSLDSD4KK72","created_at":"2026-07-05T11:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"Q4RR4HSL","created_at":"2026-07-05T11:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:1b077b58ef422998b5ed853450184f4d3648d69cf28036e91a7f734066995d87","target":"graph","created_at":"2026-07-05T11:52:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.10648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates domain-specific knowledge extracted from natural language, enhanced through a retrieval-augmented generation (RAG) pipeline, to seamlessly integrate data-driven modeling with contextual insights. Specifically, the LLM generates penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as ","authors_text":"Ash Alizadeh, Erica Zhang, Jose Blanchet, Jurik Mutter, Kangwook Lee, Mert Pilanci, Naomi Sagan, Nick Phillips, Robert Tibshirani, Ryunosuke Goto","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T02:55:22Z","title":"LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10648","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:52b335bc7840aeb03356798dcd34577137fc84f70f29e9122dd637403f94114c","target":"record","created_at":"2026-07-05T11:52:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c86affa51ac0ad17f1ee9f310bcaa7e1efeb26fed142403be1694fa7418b4865","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T02:55:22Z","title_canon_sha256":"142b86bc93dd1ab7a180a7bd3c620dcd06698a91672c39fb892cd93aa62b705d"},"schema_version":"1.0","source":{"id":"2502.10648","kind":"arxiv","version":3}},"canonical_sha256":"87231e1e4b1c87c52bfafd0ce1fac5437141f326a1cdbcc4efe9e928ccfefbb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87231e1e4b1c87c52bfafd0ce1fac5437141f326a1cdbcc4efe9e928ccfefbb0","first_computed_at":"2026-07-05T11:52:17.823533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:17.823533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MockUSrbd4XRZ2D1sxinBJsxOEQpUe48Ru8MbrOwXFlFHT0qB71dMoNWjKbbBr0OBEDiRMiiv/8Q1+wrYprHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:17.824043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10648","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52b335bc7840aeb03356798dcd34577137fc84f70f29e9122dd637403f94114c","sha256:1b077b58ef422998b5ed853450184f4d3648d69cf28036e91a7f734066995d87"],"state_sha256":"2f3689894455f31d977579bd39b8178670b8b8e3682aa7d63316681fae15d231"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wNqmgj1SALUi4jQc0PWEvUe4sQctgHH7qW8P+5J0dTvnwi7EAVlOI+t2SLIsW4OGja/Ly0iIPiBJkbzktKW1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:02:31.417019Z","bundle_sha256":"ae72ac56bb7f49c0a984caf8836aa595f07597476e4f712e87c8b39de8251e64"}}