{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZGMJBAZ6QC35DTSLLWFOZJ4TBB","short_pith_number":"pith:ZGMJBAZ6","schema_version":"1.0","canonical_sha256":"c99890833e80b7d1ce4b5d8aeca7930846406685f08d99e6423d0d266faf082e","source":{"kind":"arxiv","id":"2103.09876","version":2},"attestation_state":"computed","paper":{"title":"Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Lalana Kagal, Shlomo Dubnov, Vaikkunth Mugunthan, Vignesh Gokul","submitted_at":"2021-03-17T19:27:08Z","abstract_excerpt":"Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. Also, we propose Bias-Free FedGAN, an approach to generate bias-free synthetic datasets using FedGAN. Our approach generates metadata at the aggregator using the models received from clients and retrains the federated model to achieve bias-free results for i"},"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":"2103.09876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-17T19:27:08Z","cross_cats_sorted":["cs.CV","cs.DC"],"title_canon_sha256":"2da07c0a4999e21532e06cd9b25c7a91a421ac678f93ce57774ed6cd0bb36e27","abstract_canon_sha256":"c26e01d0f3767afe6c5f0c293b3ba47fe0d09d84f8a0e13bb46c7cb124386bda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:36.085842Z","signature_b64":"zF/Vxwb928ziwVqFjxRVUdKnEf/FR0sw4pxF9MRjNNA+mJsrovn5FiKdJdGZVS+Y3CuhlV1rzgne1XBjvVKXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99890833e80b7d1ce4b5d8aeca7930846406685f08d99e6423d0d266faf082e","last_reissued_at":"2026-07-05T02:32:36.085333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:36.085333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Lalana Kagal, Shlomo Dubnov, Vaikkunth Mugunthan, Vignesh Gokul","submitted_at":"2021-03-17T19:27:08Z","abstract_excerpt":"Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. Also, we propose Bias-Free FedGAN, an approach to generate bias-free synthetic datasets using FedGAN. Our approach generates metadata at the aggregator using the models received from clients and retrains the federated model to achieve bias-free results for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09876","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/2103.09876/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":"2103.09876","created_at":"2026-07-05T02:32:36.085394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09876v2","created_at":"2026-07-05T02:32:36.085394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09876","created_at":"2026-07-05T02:32:36.085394+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGMJBAZ6QC35","created_at":"2026-07-05T02:32:36.085394+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGMJBAZ6QC35DTSL","created_at":"2026-07-05T02:32:36.085394+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGMJBAZ6","created_at":"2026-07-05T02:32:36.085394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09755","citing_title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB","json":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB.json","graph_json":"https://pith.science/api/pith-number/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/graph.json","events_json":"https://pith.science/api/pith-number/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/events.json","paper":"https://pith.science/paper/ZGMJBAZ6"},"agent_actions":{"view_html":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB","download_json":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB.json","view_paper":"https://pith.science/paper/ZGMJBAZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09876&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/action/storage_attestation","attest_author":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/action/author_attestation","sign_citation":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/action/citation_signature","submit_replication":"https://pith.science/pith/ZGMJBAZ6QC35DTSLLWFOZJ4TBB/action/replication_record"}},"created_at":"2026-07-05T02:32:36.085394+00:00","updated_at":"2026-07-05T02:32:36.085394+00:00"}