{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MUU4NQZGKWCL5YGM2R5LOM5BPX","short_pith_number":"pith:MUU4NQZG","canonical_record":{"source":{"id":"1809.02169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T18:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"b0c3df50a42d5389471bf15a2444ec196ef3cd5976ed981408a0aed902349648","abstract_canon_sha256":"95f6831223e329f3da3da00163c92d371886eb3cef3d9cc6bfd47f241e26d4d3"},"schema_version":"1.0"},"canonical_sha256":"6529c6c3265584bee0ccd47ab733a17df5917829eed83792bfb796d47ef57c32","source":{"kind":"arxiv","id":"1809.02169","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02169","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02169v2","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02169","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"MUU4NQZGKWCL","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MUU4NQZGKWCL5YGM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MUU4NQZG","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MUU4NQZGKWCL5YGM2R5LOM5BPX","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T18:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"b0c3df50a42d5389471bf15a2444ec196ef3cd5976ed981408a0aed902349648","abstract_canon_sha256":"95f6831223e329f3da3da00163c92d371886eb3cef3d9cc6bfd47f241e26d4d3"},"schema_version":"1.0"},"canonical_sha256":"6529c6c3265584bee0ccd47ab733a17df5917829eed83792bfb796d47ef57c32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:39.107831Z","signature_b64":"thhmklDjLqd9PddN397L/ZU5RME5SVfMer/6BWRKfIqkBzoVPQ3JCfwVXU8IkcrBiAkUeT1raVZ+bNvG54N6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6529c6c3265584bee0ccd47ab733a17df5917829eed83792bfb796d47ef57c32","last_reissued_at":"2026-05-18T00:04:39.107280Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:39.107280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02169","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":"2026-05-18T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EP+GiFu8AsbbKfEPKdKpZ1I2fV2PCMoZvyvoEnzqzsHEIt7bWDfMc26S5PSO4CRq/tzZel+iS7Ba4v5UdNewAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:58:48.798926Z"},"content_sha256":"62950de469ec00112862b6ce3e98c537ba686e944c1023bb06bc9b4973cec5a8","schema_version":"1.0","event_id":"sha256:62950de469ec00112862b6ce3e98c537ba686e944c1023bb06bc9b4973cec5a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MUU4NQZGKWCL5YGM2R5LOM5BPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Christoffer Nellaker, Mohsan Alvi","submitted_at":"2018-09-06T18:44:56Z","abstract_excerpt":"Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not balanced for gender can lead to gender biased predicitons (e.g. wrongly predicting that males are older if only elderly males are in the training set). We present two distinct contributions: 1) An algorithm that can remove multiple sources of variation from the feature representation of a network. We demonstrate that this algorithm can be used to remove biases "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02169","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":""},"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":"2026-05-18T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zJAYmQncbAQ6/JwcTy5v1B0k0KMegk30EvPyaXHFq0FHzufUMjAjEG4kL7VvrpFw3xAYlGh5Ij1UeioC327UAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:58:48.799499Z"},"content_sha256":"c042d3918dcb47b4605d6a4d65857be2c4d0fc8b23fd7bd43531127c9052a4ee","schema_version":"1.0","event_id":"sha256:c042d3918dcb47b4605d6a4d65857be2c4d0fc8b23fd7bd43531127c9052a4ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/bundle.json","state_url":"https://pith.science/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/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":"2026-06-01T03:58:48Z","links":{"resolver":"https://pith.science/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX","bundle":"https://pith.science/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/bundle.json","state":"https://pith.science/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MUU4NQZGKWCL5YGM2R5LOM5BPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MUU4NQZGKWCL5YGM2R5LOM5BPX","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":"95f6831223e329f3da3da00163c92d371886eb3cef3d9cc6bfd47f241e26d4d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T18:44:56Z","title_canon_sha256":"b0c3df50a42d5389471bf15a2444ec196ef3cd5976ed981408a0aed902349648"},"schema_version":"1.0","source":{"id":"1809.02169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02169","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02169v2","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02169","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"MUU4NQZGKWCL","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MUU4NQZGKWCL5YGM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MUU4NQZG","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:c042d3918dcb47b4605d6a4d65857be2c4d0fc8b23fd7bd43531127c9052a4ee","target":"graph","created_at":"2026-05-18T00:04:39Z","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"},"paper":{"abstract_excerpt":"Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not balanced for gender can lead to gender biased predicitons (e.g. wrongly predicting that males are older if only elderly males are in the training set). We present two distinct contributions: 1) An algorithm that can remove multiple sources of variation from the feature representation of a network. We demonstrate that this algorithm can be used to remove biases ","authors_text":"Andrew Zisserman, Christoffer Nellaker, Mohsan Alvi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T18:44:56Z","title":"Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02169","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":"sha256:62950de469ec00112862b6ce3e98c537ba686e944c1023bb06bc9b4973cec5a8","target":"record","created_at":"2026-05-18T00:04:39Z","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":"95f6831223e329f3da3da00163c92d371886eb3cef3d9cc6bfd47f241e26d4d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T18:44:56Z","title_canon_sha256":"b0c3df50a42d5389471bf15a2444ec196ef3cd5976ed981408a0aed902349648"},"schema_version":"1.0","source":{"id":"1809.02169","kind":"arxiv","version":2}},"canonical_sha256":"6529c6c3265584bee0ccd47ab733a17df5917829eed83792bfb796d47ef57c32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6529c6c3265584bee0ccd47ab733a17df5917829eed83792bfb796d47ef57c32","first_computed_at":"2026-05-18T00:04:39.107280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:39.107280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thhmklDjLqd9PddN397L/ZU5RME5SVfMer/6BWRKfIqkBzoVPQ3JCfwVXU8IkcrBiAkUeT1raVZ+bNvG54N6Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:39.107831Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62950de469ec00112862b6ce3e98c537ba686e944c1023bb06bc9b4973cec5a8","sha256:c042d3918dcb47b4605d6a4d65857be2c4d0fc8b23fd7bd43531127c9052a4ee"],"state_sha256":"3a3cdaab14634391891683da30014aeaea0a5398bb9747cc9391575328869cd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lr3Cag0RaaLcoVBAKKwpJpM9sNW9LmLV3iwBmtX6ZW7hXlxbVQCKbGCPHuEjDqREzoTUvdjkP50HRs3aLSXSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:58:48.802377Z","bundle_sha256":"d857c58e9962184d688226050e050aeedb974f499bb6d75c5e5d5a73aedb030d"}}