{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TRDILBJYTIHDXKPKEDYIM74RLQ","short_pith_number":"pith:TRDILBJY","schema_version":"1.0","canonical_sha256":"9c468585389a0e3ba9ea20f0867f915c13bc10ebc52b7ae5a3c2d7bb9e43a8de","source":{"kind":"arxiv","id":"2505.02949","version":1},"attestation_state":"computed","paper":{"title":"Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Nichani, Haewon Jeong, Rasta Tadayontahmasebi, Tian Qiu","submitted_at":"2025-05-05T18:27:11Z","abstract_excerpt":"Neural compression methods are gaining popularity due to their superior rate-distortion performance over traditional methods, even at extremely low bitrates below 0.1 bpp. As deep learning architectures, these models are prone to bias during the training process, potentially leading to unfair outcomes for individuals in different groups. In this paper, we present a general, structured, scalable framework for evaluating bias in neural image compression models. Using this framework, we investigate racial bias in neural compression algorithms by analyzing nine popular models and their variants. T"},"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":"2505.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T18:27:11Z","cross_cats_sorted":[],"title_canon_sha256":"8a2b8dbf7270545dcf51a72c7a5eabe3d179fe9f0d42431b1f9432ec76c306ff","abstract_canon_sha256":"8046250eb00212b7e73e6923680d33d76a16498da3f4da3b4b65a3728a7891f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:49.854229Z","signature_b64":"9Y+CFNfjUUJIDYlLv1YLueQa0ZE0RYMqTBrD51CVZmTCY9Q0cUGDughM7itt837xMp9r+bnsacOpNT8CKxkrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c468585389a0e3ba9ea20f0867f915c13bc10ebc52b7ae5a3c2d7bb9e43a8de","last_reissued_at":"2026-07-05T10:58:49.853744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:49.853744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Nichani, Haewon Jeong, Rasta Tadayontahmasebi, Tian Qiu","submitted_at":"2025-05-05T18:27:11Z","abstract_excerpt":"Neural compression methods are gaining popularity due to their superior rate-distortion performance over traditional methods, even at extremely low bitrates below 0.1 bpp. As deep learning architectures, these models are prone to bias during the training process, potentially leading to unfair outcomes for individuals in different groups. In this paper, we present a general, structured, scalable framework for evaluating bias in neural image compression models. Using this framework, we investigate racial bias in neural compression algorithms by analyzing nine popular models and their variants. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02949","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/2505.02949/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":"2505.02949","created_at":"2026-07-05T10:58:49.853812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02949v1","created_at":"2026-07-05T10:58:49.853812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02949","created_at":"2026-07-05T10:58:49.853812+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRDILBJYTIHD","created_at":"2026-07-05T10:58:49.853812+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRDILBJYTIHDXKPK","created_at":"2026-07-05T10:58:49.853812+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRDILBJY","created_at":"2026-07-05T10:58:49.853812+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/TRDILBJYTIHDXKPKEDYIM74RLQ","json":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ.json","graph_json":"https://pith.science/api/pith-number/TRDILBJYTIHDXKPKEDYIM74RLQ/graph.json","events_json":"https://pith.science/api/pith-number/TRDILBJYTIHDXKPKEDYIM74RLQ/events.json","paper":"https://pith.science/paper/TRDILBJY"},"agent_actions":{"view_html":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ","download_json":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ.json","view_paper":"https://pith.science/paper/TRDILBJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02949&json=true","fetch_graph":"https://pith.science/api/pith-number/TRDILBJYTIHDXKPKEDYIM74RLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TRDILBJYTIHDXKPKEDYIM74RLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ/action/storage_attestation","attest_author":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ/action/author_attestation","sign_citation":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ/action/citation_signature","submit_replication":"https://pith.science/pith/TRDILBJYTIHDXKPKEDYIM74RLQ/action/replication_record"}},"created_at":"2026-07-05T10:58:49.853812+00:00","updated_at":"2026-07-05T10:58:49.853812+00:00"}