{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EP5XEWGX4FIOCCACU46JSTGSOR","short_pith_number":"pith:EP5XEWGX","schema_version":"1.0","canonical_sha256":"23fb7258d7e150e10802a73c994cd2746d31847fb28175176113e0e1c1f5a16c","source":{"kind":"arxiv","id":"2301.12195","version":3},"attestation_state":"computed","paper":{"title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chao Du, Haozhe Feng, Min Lin, Shuicheng Yan, Tianyu Pang, Wei Chen","submitted_at":"2023-01-28T13:34:36Z","abstract_excerpt":"Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation "},"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":"2301.12195","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T13:34:36Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DC"],"title_canon_sha256":"b2eacaa754a87da2cb3e0dab1bbe3198cbb9ce2f4fe07de35ae888de52d17ab4","abstract_canon_sha256":"7b957e6fd79583e09e2ac5ed5a9204dc58f9350a3772c296329057bc5e025475"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:15.908539Z","signature_b64":"EPcIdnq74WNLNx2fztkQqOYmx52rY3SiWARdM+o1yqEhRR9NUyJCa4WgMmNRhyLvTAi8tOb9Etjcqxur9/eYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23fb7258d7e150e10802a73c994cd2746d31847fb28175176113e0e1c1f5a16c","last_reissued_at":"2026-07-05T08:46:15.908115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:15.908115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chao Du, Haozhe Feng, Min Lin, Shuicheng Yan, Tianyu Pang, Wei Chen","submitted_at":"2023-01-28T13:34:36Z","abstract_excerpt":"Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12195","kind":"arxiv","version":3},"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/2301.12195/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":"2301.12195","created_at":"2026-07-05T08:46:15.908171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12195v3","created_at":"2026-07-05T08:46:15.908171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12195","created_at":"2026-07-05T08:46:15.908171+00:00"},{"alias_kind":"pith_short_12","alias_value":"EP5XEWGX4FIO","created_at":"2026-07-05T08:46:15.908171+00:00"},{"alias_kind":"pith_short_16","alias_value":"EP5XEWGX4FIOCCAC","created_at":"2026-07-05T08:46:15.908171+00:00"},{"alias_kind":"pith_short_8","alias_value":"EP5XEWGX","created_at":"2026-07-05T08:46:15.908171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10239","citing_title":"Efficient Zeroth-Order Federated Finetuning of Language Models on Resource-Constrained Devices","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR","json":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR.json","graph_json":"https://pith.science/api/pith-number/EP5XEWGX4FIOCCACU46JSTGSOR/graph.json","events_json":"https://pith.science/api/pith-number/EP5XEWGX4FIOCCACU46JSTGSOR/events.json","paper":"https://pith.science/paper/EP5XEWGX"},"agent_actions":{"view_html":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR","download_json":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR.json","view_paper":"https://pith.science/paper/EP5XEWGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12195&json=true","fetch_graph":"https://pith.science/api/pith-number/EP5XEWGX4FIOCCACU46JSTGSOR/graph.json","fetch_events":"https://pith.science/api/pith-number/EP5XEWGX4FIOCCACU46JSTGSOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR/action/storage_attestation","attest_author":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR/action/author_attestation","sign_citation":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR/action/citation_signature","submit_replication":"https://pith.science/pith/EP5XEWGX4FIOCCACU46JSTGSOR/action/replication_record"}},"created_at":"2026-07-05T08:46:15.908171+00:00","updated_at":"2026-07-05T08:46:15.908171+00:00"}