{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HS2EWNUAWAP23YZN4FGYHTX7LP","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":"38c90f56e9dd104cff7e7b99ed039c3c870f24ccb6f6bd316a7f510778c5dfa6","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T07:39:26Z","title_canon_sha256":"4919d7db164a89d7c483abd06c19e3480b6bbb6e7e61f161861f3a5f89b084f1"},"schema_version":"1.0","source":{"id":"2201.11358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11358","created_at":"2026-07-05T07:37:09Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11358v2","created_at":"2026-07-05T07:37:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11358","created_at":"2026-07-05T07:37:09Z"},{"alias_kind":"pith_short_12","alias_value":"HS2EWNUAWAP2","created_at":"2026-07-05T07:37:09Z"},{"alias_kind":"pith_short_16","alias_value":"HS2EWNUAWAP23YZN","created_at":"2026-07-05T07:37:09Z"},{"alias_kind":"pith_short_8","alias_value":"HS2EWNUA","created_at":"2026-07-05T07:37:09Z"}],"graph_snapshots":[{"event_id":"sha256:5210790c9ab31222bfb0fc66f95869bb4dd01f412f0b09d90400bbd832cefb95","target":"graph","created_at":"2026-07-05T07:37:09Z","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/2201.11358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, however, cannot directly process categorical attributes, such as country of birth or ethnicity. Because protected attributes frequently are categorical, they must be encoded as features that can be input to a chosen machine learning algorithm, e.g.\\ support vector machines, gradient boosting decision trees or linear models. Thereby, encoding methods influence how and what the machine learning algorithm will learn, affectin","authors_text":"Carlos Mougan, Jose M. Alvarez, Salvatore Ruggieri, Steffen Staab","cross_cats":["cs.CY","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T07:39:26Z","title":"Fairness Implications of Encoding Protected Categorical Attributes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11358","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":"sha256:35aa56bed1b5fff86906a5ec05323e032b4f6339f0adb1fc930c18fbd0a09a0f","target":"record","created_at":"2026-07-05T07:37:09Z","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":"38c90f56e9dd104cff7e7b99ed039c3c870f24ccb6f6bd316a7f510778c5dfa6","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T07:39:26Z","title_canon_sha256":"4919d7db164a89d7c483abd06c19e3480b6bbb6e7e61f161861f3a5f89b084f1"},"schema_version":"1.0","source":{"id":"2201.11358","kind":"arxiv","version":2}},"canonical_sha256":"3cb44b3680b01fade32de14d83ceff5bfa75d26245491761f4376d108d1ecdb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cb44b3680b01fade32de14d83ceff5bfa75d26245491761f4376d108d1ecdb1","first_computed_at":"2026-07-05T07:37:09.840089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:09.840089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lPLj/iZ/ftHHSEbG1s+PHEtPs7ANLMzOi3KlsvTFhyT5pcJKV4hDQCsnVegS92AdxvqnwI8wTsya+DhGElWuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:09.840623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.11358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35aa56bed1b5fff86906a5ec05323e032b4f6339f0adb1fc930c18fbd0a09a0f","sha256:5210790c9ab31222bfb0fc66f95869bb4dd01f412f0b09d90400bbd832cefb95"],"state_sha256":"c374f054edcb017d8e3cb9bb2debc62612630dfa2bd0775644e357099fc91f85"}