{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G7OILYCDPA5TUJFPFYES3ND4ZX","short_pith_number":"pith:G7OILYCD","schema_version":"1.0","canonical_sha256":"37dc85e043783b3a24af2e092db47ccdcb7372cedbad6c573062874bcd9463ea","source":{"kind":"arxiv","id":"1908.06938","version":2},"attestation_state":"computed","paper":{"title":"Encoder-Agnostic Adaptation for Conditional Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Luke Melas-Kyriazi, Sebastian Gehrmann, Zachary M. Ziegler","submitted_at":"2019-08-19T17:22:58Z","abstract_excerpt":"Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks. However it is an open-question how to use similar techniques for language generation. Early results in the encoder-agnostic setting have been mostly negative. In this work we explore methods for adapting a pretrained language model to arbitrary conditional input. We observe that pretrained transformer models are sensitive to large parameter changes during tuning. We th"},"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":"1908.06938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-19T17:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"669ed8577a7065ec51625788553491803f7538a072bbf73c3208ab9cb436ca7a","abstract_canon_sha256":"a258ed9bc8cb9fbf7821a776cfd4561c6a2a06996bfd0cfbaf7bfa4ddd80bf6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:58.254292Z","signature_b64":"tBcuyI7qO6Occ0qlUB7YL8j2CNP4MDU+QYZCAOS0k26mSPM8+i5xlBNRXpd1MExkK/SAqQfIpqAzjeiwbNTvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37dc85e043783b3a24af2e092db47ccdcb7372cedbad6c573062874bcd9463ea","last_reissued_at":"2026-07-05T00:03:58.253905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:58.253905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encoder-Agnostic Adaptation for Conditional Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Luke Melas-Kyriazi, Sebastian Gehrmann, Zachary M. Ziegler","submitted_at":"2019-08-19T17:22:58Z","abstract_excerpt":"Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks. However it is an open-question how to use similar techniques for language generation. Early results in the encoder-agnostic setting have been mostly negative. In this work we explore methods for adapting a pretrained language model to arbitrary conditional input. We observe that pretrained transformer models are sensitive to large parameter changes during tuning. We th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06938","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/1908.06938/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":"1908.06938","created_at":"2026-07-05T00:03:58.253960+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06938v2","created_at":"2026-07-05T00:03:58.253960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06938","created_at":"2026-07-05T00:03:58.253960+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7OILYCDPA5T","created_at":"2026-07-05T00:03:58.253960+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7OILYCDPA5TUJFP","created_at":"2026-07-05T00:03:58.253960+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7OILYCD","created_at":"2026-07-05T00:03:58.253960+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/G7OILYCDPA5TUJFPFYES3ND4ZX","json":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX.json","graph_json":"https://pith.science/api/pith-number/G7OILYCDPA5TUJFPFYES3ND4ZX/graph.json","events_json":"https://pith.science/api/pith-number/G7OILYCDPA5TUJFPFYES3ND4ZX/events.json","paper":"https://pith.science/paper/G7OILYCD"},"agent_actions":{"view_html":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX","download_json":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX.json","view_paper":"https://pith.science/paper/G7OILYCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06938&json=true","fetch_graph":"https://pith.science/api/pith-number/G7OILYCDPA5TUJFPFYES3ND4ZX/graph.json","fetch_events":"https://pith.science/api/pith-number/G7OILYCDPA5TUJFPFYES3ND4ZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX/action/storage_attestation","attest_author":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX/action/author_attestation","sign_citation":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX/action/citation_signature","submit_replication":"https://pith.science/pith/G7OILYCDPA5TUJFPFYES3ND4ZX/action/replication_record"}},"created_at":"2026-07-05T00:03:58.253960+00:00","updated_at":"2026-07-05T00:03:58.253960+00:00"}