{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I2JA2DVTGA5KEGKWUSG7GAWVK5","short_pith_number":"pith:I2JA2DVT","schema_version":"1.0","canonical_sha256":"46920d0eb3303aa21956a48df302d55778d5e6c7eff279e833e6859348f82201","source":{"kind":"arxiv","id":"2408.12025","version":2},"attestation_state":"computed","paper":{"title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dawei Li, Huan Liu, Zhen Tan","submitted_at":"2024-08-21T22:35:19Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In this work, we aim to explore and understand the LLMs-based feature selection methods from a data-centric perspective. We begin by categorizing existing feature selection methods with LLMs into two groups: data-driven feature selection which requires numerical values of samples to do statistical inference and text-based feature selection which utilizes prior knowledge of LLMs to do semantical associations using descript"},"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":"2408.12025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T22:35:19Z","cross_cats_sorted":[],"title_canon_sha256":"1e49be54e728935c3170bbbf898a318bb018ee7d1329de08d41d554ec794c517","abstract_canon_sha256":"eb0575d77557ce3fea67780dd77bbffcdcd8986436ab6918569fb3a85ea7a84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:37.859405Z","signature_b64":"aFj4wHABl9RaGLYWk4v7F0sUxQE0nvm+0QGvf2YWU7a+u7+RSWr/YBBMAzqtwJY2pXFk8MB2UvtQbcXURXFKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46920d0eb3303aa21956a48df302d55778d5e6c7eff279e833e6859348f82201","last_reissued_at":"2026-07-05T09:24:37.858889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:37.858889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dawei Li, Huan Liu, Zhen Tan","submitted_at":"2024-08-21T22:35:19Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In this work, we aim to explore and understand the LLMs-based feature selection methods from a data-centric perspective. We begin by categorizing existing feature selection methods with LLMs into two groups: data-driven feature selection which requires numerical values of samples to do statistical inference and text-based feature selection which utilizes prior knowledge of LLMs to do semantical associations using descript"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12025","kind":"arxiv","version":2},"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/2408.12025/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":"2408.12025","created_at":"2026-07-05T09:24:37.858947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12025v2","created_at":"2026-07-05T09:24:37.858947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12025","created_at":"2026-07-05T09:24:37.858947+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2JA2DVTGA5K","created_at":"2026-07-05T09:24:37.858947+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2JA2DVTGA5KEGKW","created_at":"2026-07-05T09:24:37.858947+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2JA2DVT","created_at":"2026-07-05T09:24:37.858947+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/I2JA2DVTGA5KEGKWUSG7GAWVK5","json":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5.json","graph_json":"https://pith.science/api/pith-number/I2JA2DVTGA5KEGKWUSG7GAWVK5/graph.json","events_json":"https://pith.science/api/pith-number/I2JA2DVTGA5KEGKWUSG7GAWVK5/events.json","paper":"https://pith.science/paper/I2JA2DVT"},"agent_actions":{"view_html":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5","download_json":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5.json","view_paper":"https://pith.science/paper/I2JA2DVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12025&json=true","fetch_graph":"https://pith.science/api/pith-number/I2JA2DVTGA5KEGKWUSG7GAWVK5/graph.json","fetch_events":"https://pith.science/api/pith-number/I2JA2DVTGA5KEGKWUSG7GAWVK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5/action/storage_attestation","attest_author":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5/action/author_attestation","sign_citation":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5/action/citation_signature","submit_replication":"https://pith.science/pith/I2JA2DVTGA5KEGKWUSG7GAWVK5/action/replication_record"}},"created_at":"2026-07-05T09:24:37.858947+00:00","updated_at":"2026-07-05T09:24:37.858947+00:00"}