{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CGMN6KNOWXOKDCY53CMWD753LW","short_pith_number":"pith:CGMN6KNO","canonical_record":{"source":{"id":"2106.05937","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T17:35:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49b5b6c212d075451e9d1bd90723de5a42016a1f7175f21cf07fe3bf9642ab05","abstract_canon_sha256":"eaef6bb261bc37498c14737e00249c4c3e8320dcebcb67efa05f004c077fcc9f"},"schema_version":"1.0"},"canonical_sha256":"1198df29aeb5dca18b1dd89961ffbb5d8a1f7b95d799742af04a12f798ad5bf5","source":{"kind":"arxiv","id":"2106.05937","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05937","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05937v2","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05937","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"CGMN6KNOWXOK","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"CGMN6KNOWXOKDCY5","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"CGMN6KNO","created_at":"2026-07-05T04:06:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CGMN6KNOWXOKDCY53CMWD753LW","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05937","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T17:35:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49b5b6c212d075451e9d1bd90723de5a42016a1f7175f21cf07fe3bf9642ab05","abstract_canon_sha256":"eaef6bb261bc37498c14737e00249c4c3e8320dcebcb67efa05f004c077fcc9f"},"schema_version":"1.0"},"canonical_sha256":"1198df29aeb5dca18b1dd89961ffbb5d8a1f7b95d799742af04a12f798ad5bf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:15.236392Z","signature_b64":"fjLCsXd0Rn2mya/+GCrjASAV8yWS8JXwCto1v8zCYdVu1gzk0KQYSOLv1q+5lQLJvrAfmpgWVVIufdaWiq1ACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1198df29aeb5dca18b1dd89961ffbb5d8a1f7b95d799742af04a12f798ad5bf5","last_reissued_at":"2026-07-05T04:06:15.235843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:15.235843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05937","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QRAua9EKIX9tpr6UvKlm1RhI7upOQ6PzNoWzu6IhFKG/1Fzez+gnvTUkyOD7kTaQ7zuJ6aff7l8ZcuY02snmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:23:16.835790Z"},"content_sha256":"358579b8fb7d3963905145082f06ffc168bc73a677b0c74d852eb690d32f0e13","schema_version":"1.0","event_id":"sha256:358579b8fb7d3963905145082f06ffc168bc73a677b0c74d852eb690d32f0e13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CGMN6KNOWXOKDCY53CMWD753LW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fair Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anian Ruoss, Martin Vechev, Mislav Balunovi\\'c","submitted_at":"2021-06-10T17:35:59Z","abstract_excerpt":"Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data. Unfortunately, recent work has shown that strong adversarial predictors can still exhibit unfairness by recovering sensitive attributes from these representations. In this work, we present Fair Normalizing Flows (FNF), a new approach offering more rigorous fairness guarantees for learned representations. Specifically, we consider a practical setting where we can estimate the probability density for sensitive groups. The key idea is to model the encoder as a normali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05937","kind":"arxiv","version":2},"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/2106.05937/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":"2026-07-05T04:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/vW48xlhJkmPx6BULUzy0APnp+aKUcZ/D7bPHOWvJjGr1+mGF52sl7unziU4oIqevfN71bPXEFXW696IzyfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:23:16.836701Z"},"content_sha256":"1505e9ab39848781a8d14ce08f73c864e94b8aa49c87cdbcd5ce8fbbc38af03b","schema_version":"1.0","event_id":"sha256:1505e9ab39848781a8d14ce08f73c864e94b8aa49c87cdbcd5ce8fbbc38af03b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGMN6KNOWXOKDCY53CMWD753LW/bundle.json","state_url":"https://pith.science/pith/CGMN6KNOWXOKDCY53CMWD753LW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGMN6KNOWXOKDCY53CMWD753LW/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":"2026-08-10T11:23:16Z","links":{"resolver":"https://pith.science/pith/CGMN6KNOWXOKDCY53CMWD753LW","bundle":"https://pith.science/pith/CGMN6KNOWXOKDCY53CMWD753LW/bundle.json","state":"https://pith.science/pith/CGMN6KNOWXOKDCY53CMWD753LW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGMN6KNOWXOKDCY53CMWD753LW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CGMN6KNOWXOKDCY53CMWD753LW","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":"eaef6bb261bc37498c14737e00249c4c3e8320dcebcb67efa05f004c077fcc9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T17:35:59Z","title_canon_sha256":"49b5b6c212d075451e9d1bd90723de5a42016a1f7175f21cf07fe3bf9642ab05"},"schema_version":"1.0","source":{"id":"2106.05937","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05937","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05937v2","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05937","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"CGMN6KNOWXOK","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"CGMN6KNOWXOKDCY5","created_at":"2026-07-05T04:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"CGMN6KNO","created_at":"2026-07-05T04:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:1505e9ab39848781a8d14ce08f73c864e94b8aa49c87cdbcd5ce8fbbc38af03b","target":"graph","created_at":"2026-07-05T04:06:15Z","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/2106.05937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data. Unfortunately, recent work has shown that strong adversarial predictors can still exhibit unfairness by recovering sensitive attributes from these representations. In this work, we present Fair Normalizing Flows (FNF), a new approach offering more rigorous fairness guarantees for learned representations. Specifically, we consider a practical setting where we can estimate the probability density for sensitive groups. The key idea is to model the encoder as a normali","authors_text":"Anian Ruoss, Martin Vechev, Mislav Balunovi\\'c","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T17:35:59Z","title":"Fair Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05937","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":"sha256:358579b8fb7d3963905145082f06ffc168bc73a677b0c74d852eb690d32f0e13","target":"record","created_at":"2026-07-05T04:06:15Z","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":"eaef6bb261bc37498c14737e00249c4c3e8320dcebcb67efa05f004c077fcc9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T17:35:59Z","title_canon_sha256":"49b5b6c212d075451e9d1bd90723de5a42016a1f7175f21cf07fe3bf9642ab05"},"schema_version":"1.0","source":{"id":"2106.05937","kind":"arxiv","version":2}},"canonical_sha256":"1198df29aeb5dca18b1dd89961ffbb5d8a1f7b95d799742af04a12f798ad5bf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1198df29aeb5dca18b1dd89961ffbb5d8a1f7b95d799742af04a12f798ad5bf5","first_computed_at":"2026-07-05T04:06:15.235843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:15.235843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fjLCsXd0Rn2mya/+GCrjASAV8yWS8JXwCto1v8zCYdVu1gzk0KQYSOLv1q+5lQLJvrAfmpgWVVIufdaWiq1ACA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:15.236392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05937","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:358579b8fb7d3963905145082f06ffc168bc73a677b0c74d852eb690d32f0e13","sha256:1505e9ab39848781a8d14ce08f73c864e94b8aa49c87cdbcd5ce8fbbc38af03b"],"state_sha256":"4276e395c117a8974448a5cbf11ecb2d2b3f24af0c1986cae0bb60861e013653"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgohwq/25tt7RpjWgy+k4PTl8QHQnRfJdp/EtxY2VrQMSbrwm1c1FN61OlV32mz+k0AwcSZZSEpJzt7qV2NDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:23:16.842942Z","bundle_sha256":"25bd266caf805918c2fafa6055e8c7ccdb68ea68dbc100aaf984ddb2280df22c"}}