{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAQ444CJEYWW3RXUSUEJ3NJ2XY","short_pith_number":"pith:DAQ444CJ","canonical_record":{"source":{"id":"2408.11439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T08:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"ef70ee36320f5661c2d514601474671d80391bf7037688888ebe9086f1b759c7","abstract_canon_sha256":"448af7d1effde2b807e8e56fb2a65aa9c709910fcaa897e0f323002f38320f09"},"schema_version":"1.0"},"canonical_sha256":"1821ce7049262d6dc6f495089db53abe381611c585ddb23f08793560d51924e7","source":{"kind":"arxiv","id":"2408.11439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11439","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11439v1","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11439","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"DAQ444CJEYWW","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"DAQ444CJEYWW3RXU","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"DAQ444CJ","created_at":"2026-07-05T08:57:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAQ444CJEYWW3RXUSUEJ3NJ2XY","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T08:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"ef70ee36320f5661c2d514601474671d80391bf7037688888ebe9086f1b759c7","abstract_canon_sha256":"448af7d1effde2b807e8e56fb2a65aa9c709910fcaa897e0f323002f38320f09"},"schema_version":"1.0"},"canonical_sha256":"1821ce7049262d6dc6f495089db53abe381611c585ddb23f08793560d51924e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:44.149854Z","signature_b64":"iGNmVPldTEkk+dRcpPrNuljp8sMZ4yoA2lCYkbRirPEIW/tnxUuBBrVu86XujC0NaBt4I7WImdvfZ4kjt+xPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1821ce7049262d6dc6f495089db53abe381611c585ddb23f08793560d51924e7","last_reissued_at":"2026-07-05T08:57:44.149244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:44.149244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11439","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":"2026-07-05T08:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZENSaHMudPMj6VaoEPc7oazt4zRZFpQk30mtCowdv+kv9wEU7WWbH9arjN9YZjlkxrfOQM8eczOudEf8GO4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:50:54.765207Z"},"content_sha256":"66fdfc7e99338757f97a7e13823e04f00c199f48b66771d996eb3046a3f25973","schema_version":"1.0","event_id":"sha256:66fdfc7e99338757f97a7e13823e04f00c199f48b66771d996eb3046a3f25973"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAQ444CJEYWW3RXUSUEJ3NJ2XY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BAdd: Bias Mitigation through Bias Addition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Diou, Christos Koutlis, Ioannis Sarridis, Symeon Papadopoulos","submitted_at":"2024-08-21T08:50:31Z","abstract_excerpt":"Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but struggle with multi-attribute biases being present in well-established CV datasets. Here, we introduce BAdd, a simple yet effective method that allows for learning fair representations invariant to the attributes introducing bias by incorporating fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11439","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/2408.11439/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":"2026-07-05T08:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8U7ElnmyhMVH/yPNCcD6BA17dsDCCsKmOvpSYzSgcVQiwKFieklXvo1Fpvvq1fmzpg+uZ9DMnaNA4wWl0cZfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:50:54.765736Z"},"content_sha256":"b5371614b571186f9226ef5a111cf9fdab70f84b2ca4b92a11c5b089101bb9e4","schema_version":"1.0","event_id":"sha256:b5371614b571186f9226ef5a111cf9fdab70f84b2ca4b92a11c5b089101bb9e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/bundle.json","state_url":"https://pith.science/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/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":"2026-08-14T15:50:54Z","links":{"resolver":"https://pith.science/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY","bundle":"https://pith.science/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/bundle.json","state":"https://pith.science/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAQ444CJEYWW3RXUSUEJ3NJ2XY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAQ444CJEYWW3RXUSUEJ3NJ2XY","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":"448af7d1effde2b807e8e56fb2a65aa9c709910fcaa897e0f323002f38320f09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T08:50:31Z","title_canon_sha256":"ef70ee36320f5661c2d514601474671d80391bf7037688888ebe9086f1b759c7"},"schema_version":"1.0","source":{"id":"2408.11439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11439","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11439v1","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11439","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"DAQ444CJEYWW","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"DAQ444CJEYWW3RXU","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"DAQ444CJ","created_at":"2026-07-05T08:57:44Z"}],"graph_snapshots":[{"event_id":"sha256:b5371614b571186f9226ef5a111cf9fdab70f84b2ca4b92a11c5b089101bb9e4","target":"graph","created_at":"2026-07-05T08:57:44Z","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/2408.11439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but struggle with multi-attribute biases being present in well-established CV datasets. Here, we introduce BAdd, a simple yet effective method that allows for learning fair representations invariant to the attributes introducing bias by incorporating fe","authors_text":"Christos Diou, Christos Koutlis, Ioannis Sarridis, Symeon Papadopoulos","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T08:50:31Z","title":"BAdd: Bias Mitigation through Bias Addition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11439","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":"sha256:66fdfc7e99338757f97a7e13823e04f00c199f48b66771d996eb3046a3f25973","target":"record","created_at":"2026-07-05T08:57:44Z","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":"448af7d1effde2b807e8e56fb2a65aa9c709910fcaa897e0f323002f38320f09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T08:50:31Z","title_canon_sha256":"ef70ee36320f5661c2d514601474671d80391bf7037688888ebe9086f1b759c7"},"schema_version":"1.0","source":{"id":"2408.11439","kind":"arxiv","version":1}},"canonical_sha256":"1821ce7049262d6dc6f495089db53abe381611c585ddb23f08793560d51924e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1821ce7049262d6dc6f495089db53abe381611c585ddb23f08793560d51924e7","first_computed_at":"2026-07-05T08:57:44.149244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:44.149244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iGNmVPldTEkk+dRcpPrNuljp8sMZ4yoA2lCYkbRirPEIW/tnxUuBBrVu86XujC0NaBt4I7WImdvfZ4kjt+xPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:44.149854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66fdfc7e99338757f97a7e13823e04f00c199f48b66771d996eb3046a3f25973","sha256:b5371614b571186f9226ef5a111cf9fdab70f84b2ca4b92a11c5b089101bb9e4"],"state_sha256":"5ea148154801b2d43efa633c596342db3a743ee4d0314a7b3c5e8e9b5e1975c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cp0HCiXN7X/AC9bszQ8tVDrqLDPttrOpUS+0iSFw9ZsgxFYFhN5/gmVtJIlQ0F4Sb36E9ChphptJllYhASo2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:50:54.772217Z","bundle_sha256":"d28dd1a2565c885ebbf9932b62f7ec13ab892313ff0b6be33958a6018e36b4ac"}}