{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WE6SLDGGXFIGYCFNDQC7N77NLM","short_pith_number":"pith:WE6SLDGG","canonical_record":{"source":{"id":"1911.11834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T21:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"bad8e043fecf96147c1c3a77031922a66eba25cbf27a2d99419140a323bb59c7","abstract_canon_sha256":"95d9e92d3b0907fbc308abdb5570b2b5ad395e82081f4a8fc1787085d5c66920"},"schema_version":"1.0"},"canonical_sha256":"b13d258cc6b9506c08ad1c05f6ffed5b3188bf6d2a6e69328cc522c401c31b79","source":{"kind":"arxiv","id":"1911.11834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11834","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11834v2","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11834","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"WE6SLDGGXFIG","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"WE6SLDGGXFIGYCFN","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"WE6SLDGG","created_at":"2026-07-05T00:52:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WE6SLDGGXFIGYCFNDQC7N77NLM","target":"record","payload":{"canonical_record":{"source":{"id":"1911.11834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T21:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"bad8e043fecf96147c1c3a77031922a66eba25cbf27a2d99419140a323bb59c7","abstract_canon_sha256":"95d9e92d3b0907fbc308abdb5570b2b5ad395e82081f4a8fc1787085d5c66920"},"schema_version":"1.0"},"canonical_sha256":"b13d258cc6b9506c08ad1c05f6ffed5b3188bf6d2a6e69328cc522c401c31b79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:16.799191Z","signature_b64":"UhOIL0ZR1AtkMil6BRCGaOrVbXxUjvet5Bh7V8KfHvGgG2K7Q18F5IGmgXXT6bjEjaO/qCx2/mixpHzTrBJGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13d258cc6b9506c08ad1c05f6ffed5b3188bf6d2a6e69328cc522c401c31b79","last_reissued_at":"2026-07-05T00:52:16.798773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:16.798773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.11834","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":"2026-07-05T00:52:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5vdTxwmnAN0K1gZ+I/AHuWOxl8JU54dGxb+8FAwAPvGDfmTjLbM7qY7odGjpqbKqZQ3/rHiW/gf0jJYXM9eDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:45:26.484599Z"},"content_sha256":"458c902509306afbda6e145fcd83d1c04e85a585d166574d7030255eca3b61f2","schema_version":"1.0","event_id":"sha256:458c902509306afbda6e145fcd83d1c04e85a585d166574d7030255eca3b61f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WE6SLDGGXFIGYCFNDQC7N77NLM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioannis Christos Karakozis, Kenji Hata, Klint Qinami, Kyle Genova, Olga Russakovsky, Prem Nair, Zeyu Wang","submitted_at":"2019-11-26T21:02:30Z","abstract_excerpt":"Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity recognition or image captioning. Various mitigation techniques have been presented to prevent models from utilizing or learning such biases. However, there has been little systematic comparison between these techniques. We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation. Using this benchmark, we provide a tho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11834","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/1911.11834/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":"2026-07-05T00:52:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnJm7xlSRQNW3OpMhqXISJSfAvV/KFWB75eQb/uVEvyJfsya/giqIhUN7OI3s8TIWmj1+/V6OH+MqayR0a5EAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:45:26.485558Z"},"content_sha256":"79a88065aadd117b13fe611b28e25ff99ec5d9db7369e43352cfca33476a54a4","schema_version":"1.0","event_id":"sha256:79a88065aadd117b13fe611b28e25ff99ec5d9db7369e43352cfca33476a54a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/bundle.json","state_url":"https://pith.science/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/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":"2026-07-05T15:45:26Z","links":{"resolver":"https://pith.science/pith/WE6SLDGGXFIGYCFNDQC7N77NLM","bundle":"https://pith.science/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/bundle.json","state":"https://pith.science/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WE6SLDGGXFIGYCFNDQC7N77NLM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WE6SLDGGXFIGYCFNDQC7N77NLM","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":"95d9e92d3b0907fbc308abdb5570b2b5ad395e82081f4a8fc1787085d5c66920","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T21:02:30Z","title_canon_sha256":"bad8e043fecf96147c1c3a77031922a66eba25cbf27a2d99419140a323bb59c7"},"schema_version":"1.0","source":{"id":"1911.11834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11834","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11834v2","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11834","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"WE6SLDGGXFIG","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"WE6SLDGGXFIGYCFN","created_at":"2026-07-05T00:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"WE6SLDGG","created_at":"2026-07-05T00:52:16Z"}],"graph_snapshots":[{"event_id":"sha256:79a88065aadd117b13fe611b28e25ff99ec5d9db7369e43352cfca33476a54a4","target":"graph","created_at":"2026-07-05T00:52:16Z","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/1911.11834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity recognition or image captioning. Various mitigation techniques have been presented to prevent models from utilizing or learning such biases. However, there has been little systematic comparison between these techniques. We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation. Using this benchmark, we provide a tho","authors_text":"Ioannis Christos Karakozis, Kenji Hata, Klint Qinami, Kyle Genova, Olga Russakovsky, Prem Nair, Zeyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T21:02:30Z","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11834","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":"sha256:458c902509306afbda6e145fcd83d1c04e85a585d166574d7030255eca3b61f2","target":"record","created_at":"2026-07-05T00:52:16Z","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":"95d9e92d3b0907fbc308abdb5570b2b5ad395e82081f4a8fc1787085d5c66920","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T21:02:30Z","title_canon_sha256":"bad8e043fecf96147c1c3a77031922a66eba25cbf27a2d99419140a323bb59c7"},"schema_version":"1.0","source":{"id":"1911.11834","kind":"arxiv","version":2}},"canonical_sha256":"b13d258cc6b9506c08ad1c05f6ffed5b3188bf6d2a6e69328cc522c401c31b79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b13d258cc6b9506c08ad1c05f6ffed5b3188bf6d2a6e69328cc522c401c31b79","first_computed_at":"2026-07-05T00:52:16.798773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:16.798773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UhOIL0ZR1AtkMil6BRCGaOrVbXxUjvet5Bh7V8KfHvGgG2K7Q18F5IGmgXXT6bjEjaO/qCx2/mixpHzTrBJGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:16.799191Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.11834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:458c902509306afbda6e145fcd83d1c04e85a585d166574d7030255eca3b61f2","sha256:79a88065aadd117b13fe611b28e25ff99ec5d9db7369e43352cfca33476a54a4"],"state_sha256":"821924582404cdde9b37aba2674bdc1b920a9cf4ee39ac4ff99c2348b93c6626"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09wjfLIHkIkfaWWyLcebTXoxObIxJ5CTqt6pKU72kaYEWnMA86oiHTDUCHdmUMlTcR/dmZS6MuuplmixWrREBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:45:26.489647Z","bundle_sha256":"22acd52bc7169225c6a66fa9901d0d5a4bf4bb53bfc7a9e775ac436841c58da3"}}