{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YTXFU5SREBPQNXSGPG4LTKDDTD","short_pith_number":"pith:YTXFU5SR","canonical_record":{"source":{"id":"2305.03403","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-05T09:58:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fcc1addcdf616d4b6875d91646710c5da9f3127b5994175f52e030c2cdba7075","abstract_canon_sha256":"730a0ca17bcd12760dcea7c711716f9b7837469857d4e378ecf8bd6f2a3f7122"},"schema_version":"1.0"},"canonical_sha256":"c4ee5a7651205f06de4679b8b9a86398ea9768cd9d5043f02efbbac1609238be","source":{"kind":"arxiv","id":"2305.03403","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03403","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03403v5","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03403","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_12","alias_value":"YTXFU5SREBPQ","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_16","alias_value":"YTXFU5SREBPQNXSG","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_8","alias_value":"YTXFU5SR","created_at":"2026-07-05T06:55:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YTXFU5SREBPQNXSGPG4LTKDDTD","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03403","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-05T09:58:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fcc1addcdf616d4b6875d91646710c5da9f3127b5994175f52e030c2cdba7075","abstract_canon_sha256":"730a0ca17bcd12760dcea7c711716f9b7837469857d4e378ecf8bd6f2a3f7122"},"schema_version":"1.0"},"canonical_sha256":"c4ee5a7651205f06de4679b8b9a86398ea9768cd9d5043f02efbbac1609238be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:23.351284Z","signature_b64":"mho3o7O29pWL/pyMKh/iWqWxJXHrGtqPg6XGmY/MuSnIgoWr4RpTF5U5mkJikp1W2+h3CLknr7A9pn9kAwXPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4ee5a7651205f06de4679b8b9a86398ea9768cd9d5043f02efbbac1609238be","last_reissued_at":"2026-07-05T06:55:23.350803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:23.350803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03403","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:55:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVYyut3W/SxJrEZ3/CCOundX5blZB1ab93oOU9vbkBZFeHeuH8DbMWDsij92BAwDZq/vNTpA7RYX+wqakZBdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:52:42.898555Z"},"content_sha256":"b791feabe08567031cf38361b4f95b525811548f2944f48a4d65b8129c705f73","schema_version":"1.0","event_id":"sha256:b791feabe08567031cf38361b4f95b525811548f2944f48a4d65b8129c705f73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YTXFU5SREBPQNXSGPG4LTKDDTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Frank Hutter, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2023-05-05T09:58:40Z","abstract_excerpt":"As the field of automated machine learning (AutoML) advances, it becomes increasingly important to incorporate domain knowledge into these systems. We present an approach for doing so by harnessing the power of large language models (LLMs). Specifically, we introduce Context-Aware Automated Feature Engineering (CAAFE), a feature engineering method for tabular datasets that utilizes an LLM to iteratively generate additional semantically meaningful features for tabular datasets based on the description of the dataset. The method produces both Python code for creating new features and explanation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03403","kind":"arxiv","version":5},"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/2305.03403/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":"2026-07-05T06:55:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8EPv0j8YAVBW5ad2M1/lLFP4In0YW7I7hzmi8aAFIFiKJCFXusriuMFru6Qz0i8uNoDFVJUrJngXwiLjvSuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:52:42.900116Z"},"content_sha256":"84a7b665b9351ef04833fb7d4499554901126dad97a761a36c8eaa92fccbd96d","schema_version":"1.0","event_id":"sha256:84a7b665b9351ef04833fb7d4499554901126dad97a761a36c8eaa92fccbd96d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/bundle.json","state_url":"https://pith.science/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/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":"2026-08-22T11:52:42Z","links":{"resolver":"https://pith.science/pith/YTXFU5SREBPQNXSGPG4LTKDDTD","bundle":"https://pith.science/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/bundle.json","state":"https://pith.science/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTXFU5SREBPQNXSGPG4LTKDDTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YTXFU5SREBPQNXSGPG4LTKDDTD","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":"730a0ca17bcd12760dcea7c711716f9b7837469857d4e378ecf8bd6f2a3f7122","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-05T09:58:40Z","title_canon_sha256":"fcc1addcdf616d4b6875d91646710c5da9f3127b5994175f52e030c2cdba7075"},"schema_version":"1.0","source":{"id":"2305.03403","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03403","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03403v5","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03403","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_12","alias_value":"YTXFU5SREBPQ","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_16","alias_value":"YTXFU5SREBPQNXSG","created_at":"2026-07-05T06:55:23Z"},{"alias_kind":"pith_short_8","alias_value":"YTXFU5SR","created_at":"2026-07-05T06:55:23Z"}],"graph_snapshots":[{"event_id":"sha256:84a7b665b9351ef04833fb7d4499554901126dad97a761a36c8eaa92fccbd96d","target":"graph","created_at":"2026-07-05T06:55:23Z","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/2305.03403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the field of automated machine learning (AutoML) advances, it becomes increasingly important to incorporate domain knowledge into these systems. We present an approach for doing so by harnessing the power of large language models (LLMs). Specifically, we introduce Context-Aware Automated Feature Engineering (CAAFE), a feature engineering method for tabular datasets that utilizes an LLM to iteratively generate additional semantically meaningful features for tabular datasets based on the description of the dataset. The method produces both Python code for creating new features and explanation","authors_text":"Frank Hutter, Noah Hollmann, Samuel M\\\"uller","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-05T09:58:40Z","title":"Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03403","kind":"arxiv","version":5},"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:b791feabe08567031cf38361b4f95b525811548f2944f48a4d65b8129c705f73","target":"record","created_at":"2026-07-05T06:55:23Z","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":"730a0ca17bcd12760dcea7c711716f9b7837469857d4e378ecf8bd6f2a3f7122","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-05T09:58:40Z","title_canon_sha256":"fcc1addcdf616d4b6875d91646710c5da9f3127b5994175f52e030c2cdba7075"},"schema_version":"1.0","source":{"id":"2305.03403","kind":"arxiv","version":5}},"canonical_sha256":"c4ee5a7651205f06de4679b8b9a86398ea9768cd9d5043f02efbbac1609238be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4ee5a7651205f06de4679b8b9a86398ea9768cd9d5043f02efbbac1609238be","first_computed_at":"2026-07-05T06:55:23.350803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:23.350803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mho3o7O29pWL/pyMKh/iWqWxJXHrGtqPg6XGmY/MuSnIgoWr4RpTF5U5mkJikp1W2+h3CLknr7A9pn9kAwXPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:23.351284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03403","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b791feabe08567031cf38361b4f95b525811548f2944f48a4d65b8129c705f73","sha256:84a7b665b9351ef04833fb7d4499554901126dad97a761a36c8eaa92fccbd96d"],"state_sha256":"041bfa2a12fd15b5bf8f88fb2eab5f89a881368a00c4c4a3abf12df09b74ad24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERGptXlr2+Cc0DQG0CHmj4lBefMDlKbrOhLzWvXOzJlsuzqB9mZ3mX3a/1aoWmsEcQY793ROylyfjAduovnABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:52:42.903999Z","bundle_sha256":"2353e39363f969af1d5ae7f1e545eee10c08ac54257a472761ecadf7f745d03b"}}