{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PPTPMKR7XVPIRHG4S4C7OWD2WI","short_pith_number":"pith:PPTPMKR7","schema_version":"1.0","canonical_sha256":"7be6f62a3fbd5e889cdc9705f7587ab2253a75c4fe79c47933ca62053b00b47d","source":{"kind":"arxiv","id":"2509.03616","version":1},"attestation_state":"computed","paper":{"title":"Multi Attribute Bias Mitigation via Representation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankur Kumar, Rajeev Ranjan Dwivedi, Vinod K Kurmi","submitted_at":"2025-09-03T18:08:59Z","abstract_excerpt":"Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the performance of modern vision models, undermining both their robustness and fairness. Addressing these biases individually proves inadequate, as mitigating one bias often permits or intensifies others. We tackle this multi bias problem with Generalized Multi Bias Mitigation (GMBM), a lean two stage framework that needs group labels only while training and minimizes bias at test time. First, Adaptive Bias Integrated Le"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.03616","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-03T18:08:59Z","cross_cats_sorted":[],"title_canon_sha256":"18b4f5346606d2d38e77162fb0123171ee87d271bcccb55c603ba0e577a33299","abstract_canon_sha256":"342cb88da5f08f06b8eea515eda30404ffeac07f461f62f19b2df37b39c2c18e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:43.198971Z","signature_b64":"0hA5jhweTPGDvXXfx1d0GlRkYOF455ALoRJ0lgD+fH/ROn5yKchDH4YC27LYIZzVJgRJgqFmw/DgSdEYzp4ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be6f62a3fbd5e889cdc9705f7587ab2253a75c4fe79c47933ca62053b00b47d","last_reissued_at":"2026-07-05T12:04:43.198469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:43.198469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi Attribute Bias Mitigation via Representation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankur Kumar, Rajeev Ranjan Dwivedi, Vinod K Kurmi","submitted_at":"2025-09-03T18:08:59Z","abstract_excerpt":"Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the performance of modern vision models, undermining both their robustness and fairness. Addressing these biases individually proves inadequate, as mitigating one bias often permits or intensifies others. We tackle this multi bias problem with Generalized Multi Bias Mitigation (GMBM), a lean two stage framework that needs group labels only while training and minimizes bias at test time. First, Adaptive Bias Integrated Le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03616","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/2509.03616/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.03616","created_at":"2026-07-05T12:04:43.198528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03616v1","created_at":"2026-07-05T12:04:43.198528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03616","created_at":"2026-07-05T12:04:43.198528+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPTPMKR7XVPI","created_at":"2026-07-05T12:04:43.198528+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPTPMKR7XVPIRHG4","created_at":"2026-07-05T12:04:43.198528+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPTPMKR7","created_at":"2026-07-05T12:04:43.198528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI","json":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI.json","graph_json":"https://pith.science/api/pith-number/PPTPMKR7XVPIRHG4S4C7OWD2WI/graph.json","events_json":"https://pith.science/api/pith-number/PPTPMKR7XVPIRHG4S4C7OWD2WI/events.json","paper":"https://pith.science/paper/PPTPMKR7"},"agent_actions":{"view_html":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI","download_json":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI.json","view_paper":"https://pith.science/paper/PPTPMKR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03616&json=true","fetch_graph":"https://pith.science/api/pith-number/PPTPMKR7XVPIRHG4S4C7OWD2WI/graph.json","fetch_events":"https://pith.science/api/pith-number/PPTPMKR7XVPIRHG4S4C7OWD2WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI/action/storage_attestation","attest_author":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI/action/author_attestation","sign_citation":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI/action/citation_signature","submit_replication":"https://pith.science/pith/PPTPMKR7XVPIRHG4S4C7OWD2WI/action/replication_record"}},"created_at":"2026-07-05T12:04:43.198528+00:00","updated_at":"2026-07-05T12:04:43.198528+00:00"}