{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DY35HGZ44CLLE25TFIBWAYB4EJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c83c1d3a5b972af4d094a0236adbd437d25d59594ca6a79bd53d4eed4c50ad04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:09:22Z","title_canon_sha256":"ae0b070712d28aba2147fe6b960386ab94d402d8da54c7f3efa7571ea36693b8"},"schema_version":"1.0","source":{"id":"2004.14911","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14911","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14911v2","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14911","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"DY35HGZ44CLL","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"DY35HGZ44CLLE25T","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"DY35HGZ4","created_at":"2026-07-05T04:33:17Z"}],"graph_snapshots":[{"event_id":"sha256:bd7eb074a4a3625b6f297b9f6ee85ecffce15c6d5e4aa1b8619e4c2fd2be655b","target":"graph","created_at":"2026-07-05T04:33:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.14911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been recent success in pre-training on monolingual data and fine-tuning on Machine Translation (MT), but it remains unclear how to best leverage a pre-trained model for a given MT task. This paper investigates the benefits and drawbacks of freezing parameters, and adding new ones, when fine-tuning a pre-trained model on MT. We focus on 1) Fine-tuning a model trained only on English monolingual data, BART. 2) Fine-tuning a model trained on monolingual data from 25 languages, mBART. For BART we get the best performance by freezing most of the model parameters, and adding extra position","authors_text":"Asa Cooper Stickland, Marjan Ghazvininejad, Xian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:09:22Z","title":"Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14911","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:afaa1f28902b7d2f49c6b1a2bc6d04d90c266332aca25487f83880f92bd5ac1e","target":"record","created_at":"2026-07-05T04:33:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c83c1d3a5b972af4d094a0236adbd437d25d59594ca6a79bd53d4eed4c50ad04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:09:22Z","title_canon_sha256":"ae0b070712d28aba2147fe6b960386ab94d402d8da54c7f3efa7571ea36693b8"},"schema_version":"1.0","source":{"id":"2004.14911","kind":"arxiv","version":2}},"canonical_sha256":"1e37d39b3ce096b26bb32a0360603c22494bdb08dc85d12622c3ae43a3c8aa8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e37d39b3ce096b26bb32a0360603c22494bdb08dc85d12622c3ae43a3c8aa8c","first_computed_at":"2026-07-05T04:33:17.556044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:17.556044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"biKHZRtJfHRhOswDuJSxEskptnk/J+YFpaIDypiTzv7dGHdFzLxt1bkKHEuT/9cbKw2/DtnBYQhARi4+kp6+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:17.556456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14911","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afaa1f28902b7d2f49c6b1a2bc6d04d90c266332aca25487f83880f92bd5ac1e","sha256:bd7eb074a4a3625b6f297b9f6ee85ecffce15c6d5e4aa1b8619e4c2fd2be655b"],"state_sha256":"f895f1d44fbc1b5432d73fdeb61864659ac548c6a3cfb2f7ed71f827d3190911"}