{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:354XLDJ747JQCSLPDTCCIPJZUY","short_pith_number":"pith:354XLDJ7","canonical_record":{"source":{"id":"2201.06343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:59:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d576b1f8a4a27620c1cb8ba974f50542898d3c685b47ab1a1eba820124784f34","abstract_canon_sha256":"c137577d29befff7073cd7c2bc61aa8fc50e438531ae043eb670ae54c9d67ee6"},"schema_version":"1.0"},"canonical_sha256":"df79758d3fe7d301496f1cc4243d39a60cea22e8dc1ca5730344df99ec5f16ad","source":{"kind":"arxiv","id":"2201.06343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06343","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06343v1","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06343","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"354XLDJ747JQ","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"354XLDJ747JQCSLP","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"354XLDJ7","created_at":"2026-07-05T03:48:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:354XLDJ747JQCSLPDTCCIPJZUY","target":"record","payload":{"canonical_record":{"source":{"id":"2201.06343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:59:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d576b1f8a4a27620c1cb8ba974f50542898d3c685b47ab1a1eba820124784f34","abstract_canon_sha256":"c137577d29befff7073cd7c2bc61aa8fc50e438531ae043eb670ae54c9d67ee6"},"schema_version":"1.0"},"canonical_sha256":"df79758d3fe7d301496f1cc4243d39a60cea22e8dc1ca5730344df99ec5f16ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:57.341381Z","signature_b64":"3ClUmghg3kq96es5i/vkuf+IrPq5big0l+KUybIEpOXYaB51IdBfPCkhyw4Ah4rBJbbXl7JEZjmzNGs0m7EjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df79758d3fe7d301496f1cc4243d39a60cea22e8dc1ca5730344df99ec5f16ad","last_reissued_at":"2026-07-05T03:48:57.340821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:57.340821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.06343","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":"2026-07-05T03:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdfqhZ7Rxk2c4CgsFz6hjaVBn0CLSYRn/aPNZGVaOvYV7+UroZbQQz/nuUHJfBxHFEmB2e/UUVw0w+RoZl/sDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:40.626918Z"},"content_sha256":"9cc62762d396497257fbb3be2d69b1d242fc68e4dcb2f48c3782b7fa2dd20d24","schema_version":"1.0","event_id":"sha256:9cc62762d396497257fbb3be2d69b1d242fc68e4dcb2f48c3782b7fa2dd20d24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:354XLDJ747JQCSLPDTCCIPJZUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fair Interpretable Learning via Correction Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Stefan Kramer","submitted_at":"2022-01-17T10:59:33Z","abstract_excerpt":"Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various \"representation debiasing\" techniques have been proposed in the literature. However, as neural networks are inherently opaque, these methods are hard to comprehend, which limits their usefulness. We propose a new framework for fair representation learning which is centered around the learning of \"correction vectors\", which have the same dimensionality as the given d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06343","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/2201.06343/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":"2026-07-05T03:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWA3UyzZqz6iwL60P26t4+RK4JuTgfBsvf7GYBOLfWM2KZ0EwE7haAR7ezHLa/lxNsfSW0y0lj0HFpgnUr5JCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:40.627290Z"},"content_sha256":"b75394ba025e15f9317c8ee75db05948155aa1be439a73baa5519b5b83a5f82c","schema_version":"1.0","event_id":"sha256:b75394ba025e15f9317c8ee75db05948155aa1be439a73baa5519b5b83a5f82c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/354XLDJ747JQCSLPDTCCIPJZUY/bundle.json","state_url":"https://pith.science/pith/354XLDJ747JQCSLPDTCCIPJZUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/354XLDJ747JQCSLPDTCCIPJZUY/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":"2026-07-06T11:10:40Z","links":{"resolver":"https://pith.science/pith/354XLDJ747JQCSLPDTCCIPJZUY","bundle":"https://pith.science/pith/354XLDJ747JQCSLPDTCCIPJZUY/bundle.json","state":"https://pith.science/pith/354XLDJ747JQCSLPDTCCIPJZUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/354XLDJ747JQCSLPDTCCIPJZUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:354XLDJ747JQCSLPDTCCIPJZUY","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":"c137577d29befff7073cd7c2bc61aa8fc50e438531ae043eb670ae54c9d67ee6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:59:33Z","title_canon_sha256":"d576b1f8a4a27620c1cb8ba974f50542898d3c685b47ab1a1eba820124784f34"},"schema_version":"1.0","source":{"id":"2201.06343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06343","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06343v1","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06343","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"354XLDJ747JQ","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"354XLDJ747JQCSLP","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"354XLDJ7","created_at":"2026-07-05T03:48:57Z"}],"graph_snapshots":[{"event_id":"sha256:b75394ba025e15f9317c8ee75db05948155aa1be439a73baa5519b5b83a5f82c","target":"graph","created_at":"2026-07-05T03:48:57Z","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/2201.06343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various \"representation debiasing\" techniques have been proposed in the literature. However, as neural networks are inherently opaque, these methods are hard to comprehend, which limits their usefulness. We propose a new framework for fair representation learning which is centered around the learning of \"correction vectors\", which have the same dimensionality as the given d","authors_text":"Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Stefan Kramer","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:59:33Z","title":"Fair Interpretable Learning via Correction Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06343","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":"sha256:9cc62762d396497257fbb3be2d69b1d242fc68e4dcb2f48c3782b7fa2dd20d24","target":"record","created_at":"2026-07-05T03:48:57Z","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":"c137577d29befff7073cd7c2bc61aa8fc50e438531ae043eb670ae54c9d67ee6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:59:33Z","title_canon_sha256":"d576b1f8a4a27620c1cb8ba974f50542898d3c685b47ab1a1eba820124784f34"},"schema_version":"1.0","source":{"id":"2201.06343","kind":"arxiv","version":1}},"canonical_sha256":"df79758d3fe7d301496f1cc4243d39a60cea22e8dc1ca5730344df99ec5f16ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df79758d3fe7d301496f1cc4243d39a60cea22e8dc1ca5730344df99ec5f16ad","first_computed_at":"2026-07-05T03:48:57.340821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:57.340821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ClUmghg3kq96es5i/vkuf+IrPq5big0l+KUybIEpOXYaB51IdBfPCkhyw4Ah4rBJbbXl7JEZjmzNGs0m7EjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:57.341381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cc62762d396497257fbb3be2d69b1d242fc68e4dcb2f48c3782b7fa2dd20d24","sha256:b75394ba025e15f9317c8ee75db05948155aa1be439a73baa5519b5b83a5f82c"],"state_sha256":"7698f6ed96d5915073c1e194bb253cdee86f9a9a8660938f9397c2dbb23011fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+L+QbdCmoFKB8lNm72gA9vs5gf1vw2Osfmego4J41aONKjyuCqZNhcZkjFsfjFabt39maQnq9v0INVg8/MkDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:10:40.629257Z","bundle_sha256":"e1c86af326381892528ddcc3e19bc9776c7feb5657edd85c79f35b369f672890"}}