{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3LJA53CZZSXVWWZJ6E3YVX6HIN","short_pith_number":"pith:3LJA53CZ","canonical_record":{"source":{"id":"2404.09491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T06:26:08Z","cross_cats_sorted":[],"title_canon_sha256":"a9c5b532f7d6fe1936839faea046b9d10387e25c23890614d5f2e0a3b44ab679","abstract_canon_sha256":"6240413c57ade8bbcc5cfbc36ccc8261b60806da680ca1de4910df673c52db24"},"schema_version":"1.0"},"canonical_sha256":"dad20eec59ccaf5b5b29f1378adfc7437f0848305e35c2ade715834a4fa08ff7","source":{"kind":"arxiv","id":"2404.09491","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09491","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09491v2","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09491","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"3LJA53CZZSXV","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"3LJA53CZZSXVWWZJ","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"3LJA53CZ","created_at":"2026-07-05T08:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3LJA53CZZSXVWWZJ6E3YVX6HIN","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T06:26:08Z","cross_cats_sorted":[],"title_canon_sha256":"a9c5b532f7d6fe1936839faea046b9d10387e25c23890614d5f2e0a3b44ab679","abstract_canon_sha256":"6240413c57ade8bbcc5cfbc36ccc8261b60806da680ca1de4910df673c52db24"},"schema_version":"1.0"},"canonical_sha256":"dad20eec59ccaf5b5b29f1378adfc7437f0848305e35c2ade715834a4fa08ff7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:47.745593Z","signature_b64":"lZ+xkOXWi6B37L+ZCUR3kH36N6Efxo1cC7pXBMuN/Y+Bc6ZAfiLh49geEByjaK2qGVNrkDZPzxf66WlK/WwDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad20eec59ccaf5b5b29f1378adfc7437f0848305e35c2ade715834a4fa08ff7","last_reissued_at":"2026-07-05T08:15:47.744893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:47.744893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09491","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tXenuH7dKoRq17p2i0EagZYc2YI0I8M3LsxST9s0l6KLSEeD2AlzEu0nG7f0ZT3Mi434zkPkz26HkMR4eYRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:13:31.456259Z"},"content_sha256":"8fa16ad36b49cebc8099e2875ea63743b0952aff55d5f4957dd87eef8641cd8f","schema_version":"1.0","event_id":"sha256:8fa16ad36b49cebc8099e2875ea63743b0952aff55d5f4957dd87eef8641cd8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3LJA53CZZSXVWWZJ6E3YVX6HIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinsung Yoon, Sercan O Arik, Sungwon Han, Tomas Pfister","submitted_at":"2024-04-15T06:26:08Z","abstract_excerpt":"Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel in-context learning framework, FeatLLM, which employs LLMs as feature engineers to produce an input data set that is optimally suited for tabular predictions. The generated features are used to infer class likelihood with a simple downstream machine learning model, such as linear regression and yields high performance few-shot learning. The proposed FeatLLM "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09491","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/2404.09491/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":"2026-07-05T08:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KiEsfZSQWau/3jINQOWzEP9CIm2i3rtb2iGRAQO9faFKZy3Lv+0YHAcCRIDFi7ebaH3qPwQxkPqQw3AoVy21AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:13:31.456802Z"},"content_sha256":"562be343f2126557002fc0bf562406c788ce2beb8b074b09720975dd1e119b74","schema_version":"1.0","event_id":"sha256:562be343f2126557002fc0bf562406c788ce2beb8b074b09720975dd1e119b74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/bundle.json","state_url":"https://pith.science/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/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":"2026-08-13T04:13:31Z","links":{"resolver":"https://pith.science/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN","bundle":"https://pith.science/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/bundle.json","state":"https://pith.science/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LJA53CZZSXVWWZJ6E3YVX6HIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LJA53CZZSXVWWZJ6E3YVX6HIN","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":"6240413c57ade8bbcc5cfbc36ccc8261b60806da680ca1de4910df673c52db24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T06:26:08Z","title_canon_sha256":"a9c5b532f7d6fe1936839faea046b9d10387e25c23890614d5f2e0a3b44ab679"},"schema_version":"1.0","source":{"id":"2404.09491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09491","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09491v2","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09491","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"3LJA53CZZSXV","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"3LJA53CZZSXVWWZJ","created_at":"2026-07-05T08:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"3LJA53CZ","created_at":"2026-07-05T08:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:562be343f2126557002fc0bf562406c788ce2beb8b074b09720975dd1e119b74","target":"graph","created_at":"2026-07-05T08:15:47Z","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/2404.09491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel in-context learning framework, FeatLLM, which employs LLMs as feature engineers to produce an input data set that is optimally suited for tabular predictions. The generated features are used to infer class likelihood with a simple downstream machine learning model, such as linear regression and yields high performance few-shot learning. The proposed FeatLLM ","authors_text":"Jinsung Yoon, Sercan O Arik, Sungwon Han, Tomas Pfister","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T06:26:08Z","title":"Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09491","kind":"arxiv","version":2},"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":"sha256:8fa16ad36b49cebc8099e2875ea63743b0952aff55d5f4957dd87eef8641cd8f","target":"record","created_at":"2026-07-05T08:15:47Z","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":"6240413c57ade8bbcc5cfbc36ccc8261b60806da680ca1de4910df673c52db24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T06:26:08Z","title_canon_sha256":"a9c5b532f7d6fe1936839faea046b9d10387e25c23890614d5f2e0a3b44ab679"},"schema_version":"1.0","source":{"id":"2404.09491","kind":"arxiv","version":2}},"canonical_sha256":"dad20eec59ccaf5b5b29f1378adfc7437f0848305e35c2ade715834a4fa08ff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad20eec59ccaf5b5b29f1378adfc7437f0848305e35c2ade715834a4fa08ff7","first_computed_at":"2026-07-05T08:15:47.744893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:47.744893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZ+xkOXWi6B37L+ZCUR3kH36N6Efxo1cC7pXBMuN/Y+Bc6ZAfiLh49geEByjaK2qGVNrkDZPzxf66WlK/WwDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:47.745593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fa16ad36b49cebc8099e2875ea63743b0952aff55d5f4957dd87eef8641cd8f","sha256:562be343f2126557002fc0bf562406c788ce2beb8b074b09720975dd1e119b74"],"state_sha256":"f5871b3c8e5d9072a316044ef86805fa2c4cf6b35e96968832d080dba5c77fdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqQnHTJCVpqjQLiawX12K8gK9UHAQfgjT08gc3PsCPGqqydUaqGUz+Ig43rsotXpu/SOqaOnp522fhdOgSe4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:13:31.465663Z","bundle_sha256":"786951594faf6c7ea769f869a997ab208a5c2c99bbf6acb7c66f7bbf629cc391"}}