{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IPORX7SX6PM47ICTVNW3UVGYMF","short_pith_number":"pith:IPORX7SX","schema_version":"1.0","canonical_sha256":"43dd1bfe57f3d9cfa053ab6dba54d86161f64b8bced2e82ec91bced007869f2b","source":{"kind":"arxiv","id":"2205.01557","version":1},"attestation_state":"computed","paper":{"title":"Training Mixed-Domain Translation Models via Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankit Chadha, Clement Chung, Peyman Passban, Rahul Gupta, Tanya Roosta","submitted_at":"2022-05-03T15:16:51Z","abstract_excerpt":"Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates that with slight modifications in the training process, neural machine translation (NMT) engines can be easily adapted when an FL-based aggregation is applied to fuse different domains. Experimental results also show that engines built via FL are able to perform on par with state-of-the-art baselines that rely on centralized training techniques. We e"},"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":"2205.01557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-03T15:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"331ec8f7bd70ff332954846ab4d2541487af9184663ea31cfe6b471dd66f83fb","abstract_canon_sha256":"59ab8ebe7af3285ea3a4f3d81d145b0030a5ca2d86ee96179768c22592b8cb0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:06.287066Z","signature_b64":"M4wk5IMfgr4rhUi/+D4qivYaJMt2+NgnN5aTZiCs/4XtUEZnEIiYt9bnRHINerKoajsoGLd6xNfpzh32TG8LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43dd1bfe57f3d9cfa053ab6dba54d86161f64b8bced2e82ec91bced007869f2b","last_reissued_at":"2026-07-05T04:20:06.286652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:06.286652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Mixed-Domain Translation Models via Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankit Chadha, Clement Chung, Peyman Passban, Rahul Gupta, Tanya Roosta","submitted_at":"2022-05-03T15:16:51Z","abstract_excerpt":"Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates that with slight modifications in the training process, neural machine translation (NMT) engines can be easily adapted when an FL-based aggregation is applied to fuse different domains. Experimental results also show that engines built via FL are able to perform on par with state-of-the-art baselines that rely on centralized training techniques. We e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01557","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/2205.01557/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":"2205.01557","created_at":"2026-07-05T04:20:06.286723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01557v1","created_at":"2026-07-05T04:20:06.286723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01557","created_at":"2026-07-05T04:20:06.286723+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPORX7SX6PM4","created_at":"2026-07-05T04:20:06.286723+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPORX7SX6PM47ICT","created_at":"2026-07-05T04:20:06.286723+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPORX7SX","created_at":"2026-07-05T04:20:06.286723+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/IPORX7SX6PM47ICTVNW3UVGYMF","json":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF.json","graph_json":"https://pith.science/api/pith-number/IPORX7SX6PM47ICTVNW3UVGYMF/graph.json","events_json":"https://pith.science/api/pith-number/IPORX7SX6PM47ICTVNW3UVGYMF/events.json","paper":"https://pith.science/paper/IPORX7SX"},"agent_actions":{"view_html":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF","download_json":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF.json","view_paper":"https://pith.science/paper/IPORX7SX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01557&json=true","fetch_graph":"https://pith.science/api/pith-number/IPORX7SX6PM47ICTVNW3UVGYMF/graph.json","fetch_events":"https://pith.science/api/pith-number/IPORX7SX6PM47ICTVNW3UVGYMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF/action/storage_attestation","attest_author":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF/action/author_attestation","sign_citation":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF/action/citation_signature","submit_replication":"https://pith.science/pith/IPORX7SX6PM47ICTVNW3UVGYMF/action/replication_record"}},"created_at":"2026-07-05T04:20:06.286723+00:00","updated_at":"2026-07-05T04:20:06.286723+00:00"}