{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TCLKTCDI4JAQ45MU3GKJYMDWRL","short_pith_number":"pith:TCLKTCDI","schema_version":"1.0","canonical_sha256":"9896a98868e2410e7594d9949c30768aedd59079a7c0cfa0db10424883703354","source":{"kind":"arxiv","id":"2311.14625","version":2},"attestation_state":"computed","paper":{"title":"ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CV","authors_text":"Giacomo Tarroni, Jonathan Passerat-Palmbach, Sergio Naval-Marimont, Vasilis Siomos","submitted_at":"2023-11-24T17:40:31Z","abstract_excerpt":"Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server. Despite individual studies on how client models are aggregated, and, more recently, on the benefits of ImageNet pre-training, there is a lack of understanding of the effect the architecture chosen for the federation has, and of how the aforementioned elements interconnect. To this end, we conduct the first joint ARchitecture-In"},"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":"2311.14625","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T17:40:31Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"020216b47c163f32f1f602712eac2574cec1c242195adbb4b7d2d4b1b9a5f303","abstract_canon_sha256":"417f7c55cca0d83cf9c8977061075bb8e210593a29aa814043cb34e1edf8c5a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:53.998648Z","signature_b64":"fOmX0SnYhZLCzH6p4er+Hh7t6atabcb/se5hKIxrOlAcKqORnluw5UN5JOsKv/N8kvoNDp54s4zbxE4qB7YADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9896a98868e2410e7594d9949c30768aedd59079a7c0cfa0db10424883703354","last_reissued_at":"2026-07-05T07:50:53.998228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:53.998228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CV","authors_text":"Giacomo Tarroni, Jonathan Passerat-Palmbach, Sergio Naval-Marimont, Vasilis Siomos","submitted_at":"2023-11-24T17:40:31Z","abstract_excerpt":"Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server. Despite individual studies on how client models are aggregated, and, more recently, on the benefits of ImageNet pre-training, there is a lack of understanding of the effect the architecture chosen for the federation has, and of how the aforementioned elements interconnect. To this end, we conduct the first joint ARchitecture-In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14625","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/2311.14625/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":"2311.14625","created_at":"2026-07-05T07:50:53.998283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14625v2","created_at":"2026-07-05T07:50:53.998283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14625","created_at":"2026-07-05T07:50:53.998283+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCLKTCDI4JAQ","created_at":"2026-07-05T07:50:53.998283+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCLKTCDI4JAQ45MU","created_at":"2026-07-05T07:50:53.998283+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCLKTCDI","created_at":"2026-07-05T07:50:53.998283+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/TCLKTCDI4JAQ45MU3GKJYMDWRL","json":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL.json","graph_json":"https://pith.science/api/pith-number/TCLKTCDI4JAQ45MU3GKJYMDWRL/graph.json","events_json":"https://pith.science/api/pith-number/TCLKTCDI4JAQ45MU3GKJYMDWRL/events.json","paper":"https://pith.science/paper/TCLKTCDI"},"agent_actions":{"view_html":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL","download_json":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL.json","view_paper":"https://pith.science/paper/TCLKTCDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14625&json=true","fetch_graph":"https://pith.science/api/pith-number/TCLKTCDI4JAQ45MU3GKJYMDWRL/graph.json","fetch_events":"https://pith.science/api/pith-number/TCLKTCDI4JAQ45MU3GKJYMDWRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL/action/storage_attestation","attest_author":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL/action/author_attestation","sign_citation":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL/action/citation_signature","submit_replication":"https://pith.science/pith/TCLKTCDI4JAQ45MU3GKJYMDWRL/action/replication_record"}},"created_at":"2026-07-05T07:50:53.998283+00:00","updated_at":"2026-07-05T07:50:53.998283+00:00"}