{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H2TGB7D4XQJ7OB7RJYSDO6CY4E","short_pith_number":"pith:H2TGB7D4","canonical_record":{"source":{"id":"2301.01720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T17:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"614c2a4dfc80a9b1317a81435bfa5680c4552ebf7e33607b94a5f52795ff2433","abstract_canon_sha256":"4f4fae7f37f75046335fe029814ce1db801513cdaa815d008392fdc0dab94e09"},"schema_version":"1.0"},"canonical_sha256":"3ea660fc7cbc13f707f14e24377858e13eb6b8ac2b7e55cdfcbe661d3cf7437b","source":{"kind":"arxiv","id":"2301.01720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01720","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01720v1","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01720","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"H2TGB7D4XQJ7","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"H2TGB7D4XQJ7OB7R","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"H2TGB7D4","created_at":"2026-07-05T05:30:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H2TGB7D4XQJ7OB7RJYSDO6CY4E","target":"record","payload":{"canonical_record":{"source":{"id":"2301.01720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T17:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"614c2a4dfc80a9b1317a81435bfa5680c4552ebf7e33607b94a5f52795ff2433","abstract_canon_sha256":"4f4fae7f37f75046335fe029814ce1db801513cdaa815d008392fdc0dab94e09"},"schema_version":"1.0"},"canonical_sha256":"3ea660fc7cbc13f707f14e24377858e13eb6b8ac2b7e55cdfcbe661d3cf7437b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:40.047093Z","signature_b64":"YHzNk9iFQbDaKOB+aztVJE4c8bJrhxt4R5MFDdnxjSlqlGIN23Rymz+VkffGW1V9v85tVRfLfvGV92WYSk/ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea660fc7cbc13f707f14e24377858e13eb6b8ac2b7e55cdfcbe661d3cf7437b","last_reissued_at":"2026-07-05T05:30:40.046639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:40.046639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.01720","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":"2026-07-05T05:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QH+A4W7BzE3+YlCXt5nGYilYe1wg8eAtEpM6dZNV6zQwPXyS4ineuDyTlOlCX+/PrIjKzZNPjsdWEY7MMwj8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:44:07.133174Z"},"content_sha256":"96a5f0db2939c15f4822e177a37749a5c4144a1c9513ee8a49d492061ffcacce","schema_version":"1.0","event_id":"sha256:96a5f0db2939c15f4822e177a37749a5c4144a1c9513ee8a49d492061ffcacce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H2TGB7D4XQJ7OB7RJYSDO6CY4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting data-driven models for energy systems through feature engineering: A Python framework for feature engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sandra Wilfling","submitted_at":"2023-01-04T17:37:15Z","abstract_excerpt":"Data-driven modeling is an approach in energy systems modeling that has been gaining popularity. In data-driven modeling, machine learning methods such as linear regression, neural networks or decision-tree based methods are being applied. While these methods do not require domain knowledge, they are sensitive to data quality. Therefore, improving data quality in a dataset is beneficial for creating machine learning-based models. The improvement of data quality can be implemented through preprocessing methods. A selected type of preprocessing is feature engineering, which focuses on evaluating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01720","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/2301.01720/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":"2026-07-05T05:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"061F2qI9wh62fto2IlygeqAoA9KWr0LC5NrGcohLfFxA3Znprsp6GrgNYeccKd59APDCOBU9N29xiLbD/J+DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:44:07.133576Z"},"content_sha256":"70925b5d33eba766055202ad5fb9251545834068bdefb9dec87a48c88361548f","schema_version":"1.0","event_id":"sha256:70925b5d33eba766055202ad5fb9251545834068bdefb9dec87a48c88361548f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/bundle.json","state_url":"https://pith.science/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/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":"2026-08-13T20:44:07Z","links":{"resolver":"https://pith.science/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E","bundle":"https://pith.science/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/bundle.json","state":"https://pith.science/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2TGB7D4XQJ7OB7RJYSDO6CY4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2TGB7D4XQJ7OB7RJYSDO6CY4E","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":"4f4fae7f37f75046335fe029814ce1db801513cdaa815d008392fdc0dab94e09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T17:37:15Z","title_canon_sha256":"614c2a4dfc80a9b1317a81435bfa5680c4552ebf7e33607b94a5f52795ff2433"},"schema_version":"1.0","source":{"id":"2301.01720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01720","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01720v1","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01720","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"H2TGB7D4XQJ7","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"H2TGB7D4XQJ7OB7R","created_at":"2026-07-05T05:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"H2TGB7D4","created_at":"2026-07-05T05:30:40Z"}],"graph_snapshots":[{"event_id":"sha256:70925b5d33eba766055202ad5fb9251545834068bdefb9dec87a48c88361548f","target":"graph","created_at":"2026-07-05T05:30:40Z","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/2301.01720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven modeling is an approach in energy systems modeling that has been gaining popularity. In data-driven modeling, machine learning methods such as linear regression, neural networks or decision-tree based methods are being applied. While these methods do not require domain knowledge, they are sensitive to data quality. Therefore, improving data quality in a dataset is beneficial for creating machine learning-based models. The improvement of data quality can be implemented through preprocessing methods. A selected type of preprocessing is feature engineering, which focuses on evaluating","authors_text":"Sandra Wilfling","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T17:37:15Z","title":"Augmenting data-driven models for energy systems through feature engineering: A Python framework for feature engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01720","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":"sha256:96a5f0db2939c15f4822e177a37749a5c4144a1c9513ee8a49d492061ffcacce","target":"record","created_at":"2026-07-05T05:30:40Z","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":"4f4fae7f37f75046335fe029814ce1db801513cdaa815d008392fdc0dab94e09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T17:37:15Z","title_canon_sha256":"614c2a4dfc80a9b1317a81435bfa5680c4552ebf7e33607b94a5f52795ff2433"},"schema_version":"1.0","source":{"id":"2301.01720","kind":"arxiv","version":1}},"canonical_sha256":"3ea660fc7cbc13f707f14e24377858e13eb6b8ac2b7e55cdfcbe661d3cf7437b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ea660fc7cbc13f707f14e24377858e13eb6b8ac2b7e55cdfcbe661d3cf7437b","first_computed_at":"2026-07-05T05:30:40.046639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:40.046639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHzNk9iFQbDaKOB+aztVJE4c8bJrhxt4R5MFDdnxjSlqlGIN23Rymz+VkffGW1V9v85tVRfLfvGV92WYSk/ICA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:40.047093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.01720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96a5f0db2939c15f4822e177a37749a5c4144a1c9513ee8a49d492061ffcacce","sha256:70925b5d33eba766055202ad5fb9251545834068bdefb9dec87a48c88361548f"],"state_sha256":"a925a1abf6d26b310db4b5888b093d499f9272d4da4036bcd7ca4edd54243181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+cWtxnqnJYNU4OO8IbOCDDOSAJzfSyn30umB/3+dlkU2eV2XEeN1OH8bKGqIJDU0P0HqTyrhg0g1crZbE5YAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:44:07.138665Z","bundle_sha256":"dee245fda79a7538a52ac295f2c5f272d904d46898baa9e11351a09a1d9feabe"}}