{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RAD35KTOFTBNZLHTNMKOY7KCIL","short_pith_number":"pith:RAD35KTO","schema_version":"1.0","canonical_sha256":"8807beaa6e2cc2dcacf36b14ec7d4242f45eb3f7e2ab4e0b84c278b3f5579815","source":{"kind":"arxiv","id":"2606.19129","version":1},"attestation_state":"computed","paper":{"title":"Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"C\\'esar Sabater, Mohamed Maouche, Ousmane Touat, Sonia Ben Mokhtar","submitted_at":"2026-06-17T14:40:19Z","abstract_excerpt":"Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors. While enforcing confidentiality calls for hiding the exchanged model parameters/gradients (e.g., by using cryptographic techniques), dealing with Byzantine contributions often requires inspecting the latter. Hence, most research works address these objectives separately. A recent line of work proposes"},"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":"2606.19129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-17T14:40:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdb0817dfdb11678929b470ac2c27aa49d3b072d1aae128ed1fd27feabc58698","abstract_canon_sha256":"037ff7a6c87dc1abcd42b62b24dc836dad02aaaf5c1a72999f80a772884fea51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:57.388359Z","signature_b64":"s7L142yddgD6ECulvEn83qr7OibnPiBhlazgucELfF8bXpkzcd2mpc2w35AriH6OZnt1ryRSCNN5xygWQoPGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8807beaa6e2cc2dcacf36b14ec7d4242f45eb3f7e2ab4e0b84c278b3f5579815","last_reissued_at":"2026-06-19T16:11:57.387997Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:57.387997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"C\\'esar Sabater, Mohamed Maouche, Ousmane Touat, Sonia Ben Mokhtar","submitted_at":"2026-06-17T14:40:19Z","abstract_excerpt":"Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors. While enforcing confidentiality calls for hiding the exchanged model parameters/gradients (e.g., by using cryptographic techniques), dealing with Byzantine contributions often requires inspecting the latter. Hence, most research works address these objectives separately. A recent line of work proposes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19129","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/2606.19129/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":"2606.19129","created_at":"2026-06-19T16:11:57.388058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19129v1","created_at":"2026-06-19T16:11:57.388058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19129","created_at":"2026-06-19T16:11:57.388058+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAD35KTOFTBN","created_at":"2026-06-19T16:11:57.388058+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAD35KTOFTBNZLHT","created_at":"2026-06-19T16:11:57.388058+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAD35KTO","created_at":"2026-06-19T16:11:57.388058+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/RAD35KTOFTBNZLHTNMKOY7KCIL","json":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL.json","graph_json":"https://pith.science/api/pith-number/RAD35KTOFTBNZLHTNMKOY7KCIL/graph.json","events_json":"https://pith.science/api/pith-number/RAD35KTOFTBNZLHTNMKOY7KCIL/events.json","paper":"https://pith.science/paper/RAD35KTO"},"agent_actions":{"view_html":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL","download_json":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL.json","view_paper":"https://pith.science/paper/RAD35KTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19129&json=true","fetch_graph":"https://pith.science/api/pith-number/RAD35KTOFTBNZLHTNMKOY7KCIL/graph.json","fetch_events":"https://pith.science/api/pith-number/RAD35KTOFTBNZLHTNMKOY7KCIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL/action/storage_attestation","attest_author":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL/action/author_attestation","sign_citation":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL/action/citation_signature","submit_replication":"https://pith.science/pith/RAD35KTOFTBNZLHTNMKOY7KCIL/action/replication_record"}},"created_at":"2026-06-19T16:11:57.388058+00:00","updated_at":"2026-06-19T16:11:57.388058+00:00"}