{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GWCTGBXZDLXL6JNUPKDDGG5S75","short_pith_number":"pith:GWCTGBXZ","canonical_record":{"source":{"id":"2503.21155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T04:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"510a744c487f4e795a903befc13c8885ddc0d37ff127414bf865e313f5d63a20","abstract_canon_sha256":"c36f56fe112ca2477f1bd8ef9f9f763c0ec6e314fc41dcf48f8f085e3c154e60"},"schema_version":"1.0"},"canonical_sha256":"35853306f91aeebf25b47a86331bb2ff780e197ec55f3406d8c948bca17a175f","source":{"kind":"arxiv","id":"2503.21155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21155","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21155v1","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21155","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"GWCTGBXZDLXL","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"GWCTGBXZDLXL6JNU","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"GWCTGBXZ","created_at":"2026-07-05T10:40:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GWCTGBXZDLXL6JNUPKDDGG5S75","target":"record","payload":{"canonical_record":{"source":{"id":"2503.21155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T04:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"510a744c487f4e795a903befc13c8885ddc0d37ff127414bf865e313f5d63a20","abstract_canon_sha256":"c36f56fe112ca2477f1bd8ef9f9f763c0ec6e314fc41dcf48f8f085e3c154e60"},"schema_version":"1.0"},"canonical_sha256":"35853306f91aeebf25b47a86331bb2ff780e197ec55f3406d8c948bca17a175f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:20.667458Z","signature_b64":"4E+j2u9VuDLHm18J6opoEudLrxt+mz7IZP0wvgwz0QwtoNlg7vI94AFm7w9dKFkfAjs9cLCGDrXBs9MddvoSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35853306f91aeebf25b47a86331bb2ff780e197ec55f3406d8c948bca17a175f","last_reissued_at":"2026-07-05T10:40:20.666998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:20.666998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.21155","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YyI8UzYg0UaNI18UTgkY4BMSgdCUzQmOQKsXenobw4XESCTHnQ1+VtXx5RmhdYyTL5klxvrlYp4SuepFRj8HDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:43:24.120986Z"},"content_sha256":"cf78bff2e78bb951d78add47ec54c89cc5d9c1338e7d2e15e18ffb24b3647b71","schema_version":"1.0","event_id":"sha256:cf78bff2e78bb951d78add47ec54c89cc5d9c1338e7d2e15e18ffb24b3647b71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GWCTGBXZDLXL6JNUPKDDGG5S75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedding Domain-Specific Knowledge from LLMs into the Feature Engineering Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jo\\~ao Eduardo Batista","submitted_at":"2025-03-27T04:48:58Z","abstract_excerpt":"Feature engineering is mandatory in the machine learning pipeline to obtain robust models. While evolutionary computation is well-known for its great results both in feature selection and feature construction, its methods are computationally expensive due to the large number of evaluations required to induce the final model. Part of the reason why these algorithms require a large number of evaluations is their lack of domain-specific knowledge, resulting in a lot of random guessing during evolution. In this work, we propose using Large Language Models (LLMs) as an initial feature construction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21155","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/2503.21155/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":"2026-07-05T10:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71srUAgwAp+IQZrOsW96G71oqE93BwuGCa3hwswyh5x5Wyi9mrNXDiZO60aCqZtSaoo7aim5iOgPtprmfpNLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:43:24.121488Z"},"content_sha256":"2f6717b3666450b8d43c608213b30582e9d39ba4384e048c2797de5edd98f42b","schema_version":"1.0","event_id":"sha256:2f6717b3666450b8d43c608213b30582e9d39ba4384e048c2797de5edd98f42b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/bundle.json","state_url":"https://pith.science/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/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":"2026-08-18T22:43:24Z","links":{"resolver":"https://pith.science/pith/GWCTGBXZDLXL6JNUPKDDGG5S75","bundle":"https://pith.science/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/bundle.json","state":"https://pith.science/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWCTGBXZDLXL6JNUPKDDGG5S75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GWCTGBXZDLXL6JNUPKDDGG5S75","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":"c36f56fe112ca2477f1bd8ef9f9f763c0ec6e314fc41dcf48f8f085e3c154e60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T04:48:58Z","title_canon_sha256":"510a744c487f4e795a903befc13c8885ddc0d37ff127414bf865e313f5d63a20"},"schema_version":"1.0","source":{"id":"2503.21155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21155","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21155v1","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21155","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"GWCTGBXZDLXL","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"GWCTGBXZDLXL6JNU","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"GWCTGBXZ","created_at":"2026-07-05T10:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:2f6717b3666450b8d43c608213b30582e9d39ba4384e048c2797de5edd98f42b","target":"graph","created_at":"2026-07-05T10:40:20Z","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/2503.21155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Feature engineering is mandatory in the machine learning pipeline to obtain robust models. While evolutionary computation is well-known for its great results both in feature selection and feature construction, its methods are computationally expensive due to the large number of evaluations required to induce the final model. Part of the reason why these algorithms require a large number of evaluations is their lack of domain-specific knowledge, resulting in a lot of random guessing during evolution. In this work, we propose using Large Language Models (LLMs) as an initial feature construction ","authors_text":"Jo\\~ao Eduardo Batista","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T04:48:58Z","title":"Embedding Domain-Specific Knowledge from LLMs into the Feature Engineering Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21155","kind":"arxiv","version":1},"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:cf78bff2e78bb951d78add47ec54c89cc5d9c1338e7d2e15e18ffb24b3647b71","target":"record","created_at":"2026-07-05T10:40:20Z","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":"c36f56fe112ca2477f1bd8ef9f9f763c0ec6e314fc41dcf48f8f085e3c154e60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-27T04:48:58Z","title_canon_sha256":"510a744c487f4e795a903befc13c8885ddc0d37ff127414bf865e313f5d63a20"},"schema_version":"1.0","source":{"id":"2503.21155","kind":"arxiv","version":1}},"canonical_sha256":"35853306f91aeebf25b47a86331bb2ff780e197ec55f3406d8c948bca17a175f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35853306f91aeebf25b47a86331bb2ff780e197ec55f3406d8c948bca17a175f","first_computed_at":"2026-07-05T10:40:20.666998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:20.666998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4E+j2u9VuDLHm18J6opoEudLrxt+mz7IZP0wvgwz0QwtoNlg7vI94AFm7w9dKFkfAjs9cLCGDrXBs9MddvoSCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:20.667458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf78bff2e78bb951d78add47ec54c89cc5d9c1338e7d2e15e18ffb24b3647b71","sha256:2f6717b3666450b8d43c608213b30582e9d39ba4384e048c2797de5edd98f42b"],"state_sha256":"1c2c97e6ce196a117159942e4f2f4f5329345d8c3472f32613b65d9175f732ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFUApomIadC68ctqN0W35xLqnfZUEMOisTkgIpcoDkEYYhEoxCQPYxQcTUc/ZX1xHW0uDQ+XDrt8sQi+IeT3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:43:24.124581Z","bundle_sha256":"64d6783c4192b73c2bd46bf6165197193d4bfb6aca1899a6b4a3e5a4945242dc"}}