{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M2LDPC6T2WJ34DGR7WSDJZAHY3","short_pith_number":"pith:M2LDPC6T","schema_version":"1.0","canonical_sha256":"6696378bd3d593be0cd1fda434e407c6f141d86fbe52c82875ead17559db9443","source":{"kind":"arxiv","id":"1903.09722","version":2},"attestation_state":"computed","paper":{"title":"Pre-trained Language Model Representations for Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Michael Auli, Sergey Edunov","submitted_at":"2019-03-22T22:14:51Z","abstract_excerpt":"Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and apply it to neural machine translation and abstractive summarization. We find that pre-trained representations are most effective when added to the encoder network which slows inference by only 14%. Our experiments in machine translation show gains of up to 5.3 BLEU in a simulated resource-poor setup. While returns diminish with more labeled data, we still obs"},"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":"1903.09722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-22T22:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"105032e0fb31c84105fe857b10a2a249dcf6e2f5ac75ec688e12329e4d6b89dd","abstract_canon_sha256":"d099c1d35336950ab0d9b27186c5930ce10cc38fe433c931d1f9fce629c1c5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:44.948165Z","signature_b64":"8z3HOXBedbicFlM2YRbSokDJ9yKR/Md9DunQkmJc0U6C1iKUAhoNJGVbwPkgkVU3w7a78HouWoODJQYkvg9qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6696378bd3d593be0cd1fda434e407c6f141d86fbe52c82875ead17559db9443","last_reissued_at":"2026-05-17T23:49:44.947702Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:44.947702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-trained Language Model Representations for Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Michael Auli, Sergey Edunov","submitted_at":"2019-03-22T22:14:51Z","abstract_excerpt":"Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and apply it to neural machine translation and abstractive summarization. We find that pre-trained representations are most effective when added to the encoder network which slows inference by only 14%. Our experiments in machine translation show gains of up to 5.3 BLEU in a simulated resource-poor setup. While returns diminish with more labeled data, we still obs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09722","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":""},"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":"1903.09722","created_at":"2026-05-17T23:49:44.947767+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.09722v2","created_at":"2026-05-17T23:49:44.947767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09722","created_at":"2026-05-17T23:49:44.947767+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2LDPC6T2WJ3","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2LDPC6T2WJ34DGR","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2LDPC6T","created_at":"2026-05-18T12:33:21.387695+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/M2LDPC6T2WJ34DGR7WSDJZAHY3","json":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3.json","graph_json":"https://pith.science/api/pith-number/M2LDPC6T2WJ34DGR7WSDJZAHY3/graph.json","events_json":"https://pith.science/api/pith-number/M2LDPC6T2WJ34DGR7WSDJZAHY3/events.json","paper":"https://pith.science/paper/M2LDPC6T"},"agent_actions":{"view_html":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3","download_json":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3.json","view_paper":"https://pith.science/paper/M2LDPC6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.09722&json=true","fetch_graph":"https://pith.science/api/pith-number/M2LDPC6T2WJ34DGR7WSDJZAHY3/graph.json","fetch_events":"https://pith.science/api/pith-number/M2LDPC6T2WJ34DGR7WSDJZAHY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3/action/storage_attestation","attest_author":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3/action/author_attestation","sign_citation":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3/action/citation_signature","submit_replication":"https://pith.science/pith/M2LDPC6T2WJ34DGR7WSDJZAHY3/action/replication_record"}},"created_at":"2026-05-17T23:49:44.947767+00:00","updated_at":"2026-05-17T23:49:44.947767+00:00"}