{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZVUGRCXBVEBAYUZ7KAGCZ6T4DX","short_pith_number":"pith:ZVUGRCXB","canonical_record":{"source":{"id":"2202.03078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T11:19:23Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"10b71db3de651b7faa67dd8002e9140f60a61a6a952344c7c2ad6a02eaaf86d4","abstract_canon_sha256":"9ececde5dfe1492622852d753d2703242f873b1fc4cb770ee9efc13fd519d290"},"schema_version":"1.0"},"canonical_sha256":"cd68688ae1a9020c533f500c2cfa7c1dfceadd2ef71246357e185dc76541718d","source":{"kind":"arxiv","id":"2202.03078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03078","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03078v1","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03078","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZVUGRCXBVEBA","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZVUGRCXBVEBAYUZ7","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZVUGRCXB","created_at":"2026-07-05T03:54:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZVUGRCXBVEBAYUZ7KAGCZ6T4DX","target":"record","payload":{"canonical_record":{"source":{"id":"2202.03078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T11:19:23Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"10b71db3de651b7faa67dd8002e9140f60a61a6a952344c7c2ad6a02eaaf86d4","abstract_canon_sha256":"9ececde5dfe1492622852d753d2703242f873b1fc4cb770ee9efc13fd519d290"},"schema_version":"1.0"},"canonical_sha256":"cd68688ae1a9020c533f500c2cfa7c1dfceadd2ef71246357e185dc76541718d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:35.418551Z","signature_b64":"JNsOhjxKE2A/yecCBbf00Qb8zRFBLg50I/jBuYOhwWMVpbW3wh4tdMEkgM36hlTLsWk+K1joXW0FvwBq/lzwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd68688ae1a9020c533f500c2cfa7c1dfceadd2ef71246357e185dc76541718d","last_reissued_at":"2026-07-05T03:54:35.418197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:35.418197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.03078","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":"2026-07-05T03:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZeYE4AMTqoTIxwnqSWHO8H1+6kbLKKQ1hVxdMbRrBRNMWP+iS40H2rA65z48Shq4/oACABm7yMZ/MEJK4Q5nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:10:52.217207Z"},"content_sha256":"8500221a9c8a9b52890b1d3e5a34e86ee0813ab1e9e0b049790a3f73d7afb715","schema_version":"1.0","event_id":"sha256:8500221a9c8a9b52890b1d3e5a34e86ee0813ab1e9e0b049790a3f73d7afb715"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZVUGRCXBVEBAYUZ7KAGCZ6T4DX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fair Interpretable Representation Learning with Correction Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Alesia Vallenas Coronel, Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Roberto Esposito, Stefan Kramer","submitted_at":"2022-02-07T11:19:23Z","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 that is centered around the learning of \"correction vectors\", which have the same dimensionality as the given data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03078","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/2202.03078/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":"2026-07-05T03:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gg1phnLDvJw5r8MENa4HUWxw038FiBKkLaa/MHUa7e+BEzMXACuK9pRqsjk7IOv+fmrf5tzYEqaLcodxtpQtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:10:52.217583Z"},"content_sha256":"8507358807c425f4b3ef88622e43008a513964f58d01579bbf853b7c2e341de3","schema_version":"1.0","event_id":"sha256:8507358807c425f4b3ef88622e43008a513964f58d01579bbf853b7c2e341de3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/bundle.json","state_url":"https://pith.science/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/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":"2026-07-07T11:10:52Z","links":{"resolver":"https://pith.science/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX","bundle":"https://pith.science/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/bundle.json","state":"https://pith.science/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVUGRCXBVEBAYUZ7KAGCZ6T4DX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZVUGRCXBVEBAYUZ7KAGCZ6T4DX","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":"9ececde5dfe1492622852d753d2703242f873b1fc4cb770ee9efc13fd519d290","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T11:19:23Z","title_canon_sha256":"10b71db3de651b7faa67dd8002e9140f60a61a6a952344c7c2ad6a02eaaf86d4"},"schema_version":"1.0","source":{"id":"2202.03078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03078","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03078v1","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03078","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZVUGRCXBVEBA","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZVUGRCXBVEBAYUZ7","created_at":"2026-07-05T03:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZVUGRCXB","created_at":"2026-07-05T03:54:35Z"}],"graph_snapshots":[{"event_id":"sha256:8507358807c425f4b3ef88622e43008a513964f58d01579bbf853b7c2e341de3","target":"graph","created_at":"2026-07-05T03:54:35Z","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/2202.03078/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 that is centered around the learning of \"correction vectors\", which have the same dimensionality as the given data","authors_text":"Alesia Vallenas Coronel, Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Roberto Esposito, Stefan Kramer","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T11:19:23Z","title":"Fair Interpretable Representation Learning with Correction Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03078","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":"sha256:8500221a9c8a9b52890b1d3e5a34e86ee0813ab1e9e0b049790a3f73d7afb715","target":"record","created_at":"2026-07-05T03:54:35Z","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":"9ececde5dfe1492622852d753d2703242f873b1fc4cb770ee9efc13fd519d290","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T11:19:23Z","title_canon_sha256":"10b71db3de651b7faa67dd8002e9140f60a61a6a952344c7c2ad6a02eaaf86d4"},"schema_version":"1.0","source":{"id":"2202.03078","kind":"arxiv","version":1}},"canonical_sha256":"cd68688ae1a9020c533f500c2cfa7c1dfceadd2ef71246357e185dc76541718d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd68688ae1a9020c533f500c2cfa7c1dfceadd2ef71246357e185dc76541718d","first_computed_at":"2026-07-05T03:54:35.418197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:35.418197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNsOhjxKE2A/yecCBbf00Qb8zRFBLg50I/jBuYOhwWMVpbW3wh4tdMEkgM36hlTLsWk+K1joXW0FvwBq/lzwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:35.418551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8500221a9c8a9b52890b1d3e5a34e86ee0813ab1e9e0b049790a3f73d7afb715","sha256:8507358807c425f4b3ef88622e43008a513964f58d01579bbf853b7c2e341de3"],"state_sha256":"dc9e6069ee34e388da18b4e0a84e1db489ba54a68d183c433d1228fcc1b2082d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNvZKbMVGCugvMVYyXWMUhc2TcbCVVc7UlsQ2rDUBP7UWNF6ElP2APSiI7Dj4kCvZR9IsvTSMb2VScn981ICBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:10:52.219453Z","bundle_sha256":"e5363dbfba688966111b6ffda4a87fc19cac5a1b50605e14d19ea212df57d0db"}}