{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CNMCHIE6VNICY5S45UJULALMTQ","short_pith_number":"pith:CNMCHIE6","schema_version":"1.0","canonical_sha256":"135823a09eab502c765ced1345816c9c152b5804466f750a54d6486ad0989058","source":{"kind":"arxiv","id":"2505.01851","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Group-Level Fairness Disparities in Federated Visual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaomeng Chen, Junhao Dong, Linlin Shen, Sen Su, Shutao Xia, Xiaochun Cao, Zitong Yu","submitted_at":"2025-05-03T16:09:52Z","abstract_excerpt":"Visual language models (VLMs) have shown remarkable capabilities in multimodal tasks but face challenges in maintaining fairness across demographic groups, particularly when deployed in federated learning (FL) environments. This paper addresses the critical issue of group fairness in federated VLMs by introducing FVL-FP, a novel framework that combines FL with fair prompt tuning techniques. We focus on mitigating demographic biases while preserving model performance through three innovative components: (1) Cross-Layer Demographic Fair Prompting (CDFP), which adjusts potentially biased embeddin"},"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":"2505.01851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-03T16:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"97dc6600ae59e11924b1ad72ecaf0c9d7ce1267dce9e517fe5ec27f7536962e2","abstract_canon_sha256":"30d67786e00da2d56c4efb1c753c48523be3b7c78c2daa7ec22cd8e1553f70b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:05.768634Z","signature_b64":"gfgz+jjSfDlmsBfcAwgXXyRi1uNbXc5JXt5wbxVVqVSFszJCtNpW0d9PrWl+Eyscn/ozv1qcwhJLLxo3Ox9wAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"135823a09eab502c765ced1345816c9c152b5804466f750a54d6486ad0989058","last_reissued_at":"2026-07-05T10:58:05.768117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:05.768117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Group-Level Fairness Disparities in Federated Visual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaomeng Chen, Junhao Dong, Linlin Shen, Sen Su, Shutao Xia, Xiaochun Cao, Zitong Yu","submitted_at":"2025-05-03T16:09:52Z","abstract_excerpt":"Visual language models (VLMs) have shown remarkable capabilities in multimodal tasks but face challenges in maintaining fairness across demographic groups, particularly when deployed in federated learning (FL) environments. This paper addresses the critical issue of group fairness in federated VLMs by introducing FVL-FP, a novel framework that combines FL with fair prompt tuning techniques. We focus on mitigating demographic biases while preserving model performance through three innovative components: (1) Cross-Layer Demographic Fair Prompting (CDFP), which adjusts potentially biased embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01851","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/2505.01851/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":"2505.01851","created_at":"2026-07-05T10:58:05.768173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01851v1","created_at":"2026-07-05T10:58:05.768173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01851","created_at":"2026-07-05T10:58:05.768173+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNMCHIE6VNIC","created_at":"2026-07-05T10:58:05.768173+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNMCHIE6VNICY5S4","created_at":"2026-07-05T10:58:05.768173+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNMCHIE6","created_at":"2026-07-05T10:58:05.768173+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/CNMCHIE6VNICY5S45UJULALMTQ","json":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ.json","graph_json":"https://pith.science/api/pith-number/CNMCHIE6VNICY5S45UJULALMTQ/graph.json","events_json":"https://pith.science/api/pith-number/CNMCHIE6VNICY5S45UJULALMTQ/events.json","paper":"https://pith.science/paper/CNMCHIE6"},"agent_actions":{"view_html":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ","download_json":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ.json","view_paper":"https://pith.science/paper/CNMCHIE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01851&json=true","fetch_graph":"https://pith.science/api/pith-number/CNMCHIE6VNICY5S45UJULALMTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CNMCHIE6VNICY5S45UJULALMTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ/action/storage_attestation","attest_author":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ/action/author_attestation","sign_citation":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ/action/citation_signature","submit_replication":"https://pith.science/pith/CNMCHIE6VNICY5S45UJULALMTQ/action/replication_record"}},"created_at":"2026-07-05T10:58:05.768173+00:00","updated_at":"2026-07-05T10:58:05.768173+00:00"}