{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:C4PYYZQ6NPHY2XNIZKDMSQDENI","short_pith_number":"pith:C4PYYZQ6","canonical_record":{"source":{"id":"2201.06336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:49:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"853bfb99e9e54686e6990cedffcc4a849f1142a1c3a5f1d3c033ba5035b5325f","abstract_canon_sha256":"14509192e29fc6da22c089d6e91aacd85644456a036915f117d4413edab7e265"},"schema_version":"1.0"},"canonical_sha256":"171f8c661e6bcf8d5da8ca86c940646a304288b3dbf32ef22f82ce0dd5435f6d","source":{"kind":"arxiv","id":"2201.06336","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06336","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06336v1","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06336","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"C4PYYZQ6NPHY","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"C4PYYZQ6NPHY2XNI","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"C4PYYZQ6","created_at":"2026-07-05T03:48:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:C4PYYZQ6NPHY2XNIZKDMSQDENI","target":"record","payload":{"canonical_record":{"source":{"id":"2201.06336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:49:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"853bfb99e9e54686e6990cedffcc4a849f1142a1c3a5f1d3c033ba5035b5325f","abstract_canon_sha256":"14509192e29fc6da22c089d6e91aacd85644456a036915f117d4413edab7e265"},"schema_version":"1.0"},"canonical_sha256":"171f8c661e6bcf8d5da8ca86c940646a304288b3dbf32ef22f82ce0dd5435f6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:57.226981Z","signature_b64":"1go8HskMBqTW7fbl87el6p9gThvorBJnvKGpsvS4NCZUuWwCHVBjYuUaoo/KPN3UMvec6y0wXf26IcEn3KEDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"171f8c661e6bcf8d5da8ca86c940646a304288b3dbf32ef22f82ce0dd5435f6d","last_reissued_at":"2026-07-05T03:48:57.226554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:57.226554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.06336","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":"7erlgUT7TG58rWwba9veS2mHs2/OvE7yJB8RtuQgloSw5JlKU/0E5/TSbh4QBcQ5DQITRl+ORCU9Fl0syZTqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:02.688589Z"},"content_sha256":"24b6219b972cf1214b4b06cff3911a2481bde36a8bb700fe140ec2f6c4b5ab86","schema_version":"1.0","event_id":"sha256:24b6219b972cf1214b4b06cff3911a2481bde36a8bb700fe140ec2f6c4b5ab86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:C4PYYZQ6NPHY2XNIZKDMSQDENI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fair Group-Shared Representations with Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Stefan Kramer","submitted_at":"2022-01-17T10:49:49Z","abstract_excerpt":"The issue of fairness in machine learning stems from the fact that historical data often displays biases against specific groups of people which have been underprivileged in the recent past, or still are. In this context, one of the possible approaches is to employ fair representation learning algorithms which are able to remove biases from data, making groups statistically indistinguishable. In this paper, we instead develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. This is made possible by training a pair of Nor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06336","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/2201.06336/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":"iRFgZEGXxZ0p/exXfYpInp7BtHeoFcPahih2p6a482J0pRNjPv2C3JE0LNbiG7RvZnCcpBbDqtHi6j66FM3YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:02.688955Z"},"content_sha256":"1e8a3ff5a60b65a70254fe91ba141c4207809596ea4c9839f37f63e0bd569523","schema_version":"1.0","event_id":"sha256:1e8a3ff5a60b65a70254fe91ba141c4207809596ea4c9839f37f63e0bd569523"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/bundle.json","state_url":"https://pith.science/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/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":"2026-07-07T08:09:02Z","links":{"resolver":"https://pith.science/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI","bundle":"https://pith.science/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/bundle.json","state":"https://pith.science/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4PYYZQ6NPHY2XNIZKDMSQDENI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:C4PYYZQ6NPHY2XNIZKDMSQDENI","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":"14509192e29fc6da22c089d6e91aacd85644456a036915f117d4413edab7e265","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:49:49Z","title_canon_sha256":"853bfb99e9e54686e6990cedffcc4a849f1142a1c3a5f1d3c033ba5035b5325f"},"schema_version":"1.0","source":{"id":"2201.06336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06336","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06336v1","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06336","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"C4PYYZQ6NPHY","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"C4PYYZQ6NPHY2XNI","created_at":"2026-07-05T03:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"C4PYYZQ6","created_at":"2026-07-05T03:48:57Z"}],"graph_snapshots":[{"event_id":"sha256:1e8a3ff5a60b65a70254fe91ba141c4207809596ea4c9839f37f63e0bd569523","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/2201.06336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The issue of fairness in machine learning stems from the fact that historical data often displays biases against specific groups of people which have been underprivileged in the recent past, or still are. In this context, one of the possible approaches is to employ fair representation learning algorithms which are able to remove biases from data, making groups statistically indistinguishable. In this paper, we instead develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. This is made possible by training a pair of Nor","authors_text":"Alexander Segner, Marius K\\\"oppel, Mattia Cerrato, Stefan Kramer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:49:49Z","title":"Fair Group-Shared Representations with Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06336","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":"sha256:24b6219b972cf1214b4b06cff3911a2481bde36a8bb700fe140ec2f6c4b5ab86","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":"14509192e29fc6da22c089d6e91aacd85644456a036915f117d4413edab7e265","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T10:49:49Z","title_canon_sha256":"853bfb99e9e54686e6990cedffcc4a849f1142a1c3a5f1d3c033ba5035b5325f"},"schema_version":"1.0","source":{"id":"2201.06336","kind":"arxiv","version":1}},"canonical_sha256":"171f8c661e6bcf8d5da8ca86c940646a304288b3dbf32ef22f82ce0dd5435f6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"171f8c661e6bcf8d5da8ca86c940646a304288b3dbf32ef22f82ce0dd5435f6d","first_computed_at":"2026-07-05T03:48:57.226554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:57.226554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1go8HskMBqTW7fbl87el6p9gThvorBJnvKGpsvS4NCZUuWwCHVBjYuUaoo/KPN3UMvec6y0wXf26IcEn3KEDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:57.226981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24b6219b972cf1214b4b06cff3911a2481bde36a8bb700fe140ec2f6c4b5ab86","sha256:1e8a3ff5a60b65a70254fe91ba141c4207809596ea4c9839f37f63e0bd569523"],"state_sha256":"0c0a889744841244f2fb1038ef39b073fc9ed45c008d3beee4210227e40a5e3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76Q0wcoXckFxehAybBDbrbwkEy1LHyslknFUNT/WCOkYSSEpkvgILYWeYFkCCRSRxm2gnlVMNUeJpvI5UtCdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:09:02.690863Z","bundle_sha256":"9079cf0972c51c7a9b4343983f8f4a530d0d09f71400e39c0827d3098ecbf77f"}}