{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BKWVIYH4PSLFVMBR6JAONO3AKA","short_pith_number":"pith:BKWVIYH4","schema_version":"1.0","canonical_sha256":"0aad5460fc7c965ab031f240e6bb605000d297c1b0209aae28c18daf3ee40b9a","source":{"kind":"arxiv","id":"1905.08836","version":1},"attestation_state":"computed","paper":{"title":"Sample Efficient Text Summarization Using a Single Pre-Trained Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Kevin Clark, Lukasz Kaiser, Urvashi Khandelwal","submitted_at":"2019-05-21T19:13:16Z","abstract_excerpt":"Language model (LM) pre-training has resulted in impressive performance and sample efficiency on a variety of language understanding tasks. However, it remains unclear how to best use pre-trained LMs for generation tasks such as abstractive summarization, particularly to enhance sample efficiency. In these sequence-to-sequence settings, prior work has experimented with loading pre-trained weights into the encoder and/or decoder networks, but used non-pre-trained encoder-decoder attention weights. We instead use a pre-trained decoder-only network, where the same Transformer LM both encodes the "},"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":"1905.08836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-21T19:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"09a673ed7115ea276aec4ae8cb0a01a202af6ca897e708ee01f8ae39055efb81","abstract_canon_sha256":"286c77bfa8c8eb8fd3f124204301f6efd81d61dc485bdbd29da7e51f76f96e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:25.106297Z","signature_b64":"djWOVcM3kHNAiIOl8cOEHM/XVvOLeKYzlk0xynOXPP8oVDyjuug8Lxjt3eWDYC0ofQ/cEg9tZmSw/8QR7y+pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aad5460fc7c965ab031f240e6bb605000d297c1b0209aae28c18daf3ee40b9a","last_reissued_at":"2026-05-17T23:45:25.105780Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:25.105780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Efficient Text Summarization Using a Single Pre-Trained Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Kevin Clark, Lukasz Kaiser, Urvashi Khandelwal","submitted_at":"2019-05-21T19:13:16Z","abstract_excerpt":"Language model (LM) pre-training has resulted in impressive performance and sample efficiency on a variety of language understanding tasks. However, it remains unclear how to best use pre-trained LMs for generation tasks such as abstractive summarization, particularly to enhance sample efficiency. In these sequence-to-sequence settings, prior work has experimented with loading pre-trained weights into the encoder and/or decoder networks, but used non-pre-trained encoder-decoder attention weights. We instead use a pre-trained decoder-only network, where the same Transformer LM both encodes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08836","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":""},"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":"1905.08836","created_at":"2026-05-17T23:45:25.105868+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08836v1","created_at":"2026-05-17T23:45:25.105868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08836","created_at":"2026-05-17T23:45:25.105868+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKWVIYH4PSLF","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKWVIYH4PSLFVMBR","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKWVIYH4","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1909.08593","citing_title":"Fine-Tuning Language Models from Human Preferences","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA","json":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA.json","graph_json":"https://pith.science/api/pith-number/BKWVIYH4PSLFVMBR6JAONO3AKA/graph.json","events_json":"https://pith.science/api/pith-number/BKWVIYH4PSLFVMBR6JAONO3AKA/events.json","paper":"https://pith.science/paper/BKWVIYH4"},"agent_actions":{"view_html":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA","download_json":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA.json","view_paper":"https://pith.science/paper/BKWVIYH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08836&json=true","fetch_graph":"https://pith.science/api/pith-number/BKWVIYH4PSLFVMBR6JAONO3AKA/graph.json","fetch_events":"https://pith.science/api/pith-number/BKWVIYH4PSLFVMBR6JAONO3AKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA/action/storage_attestation","attest_author":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA/action/author_attestation","sign_citation":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA/action/citation_signature","submit_replication":"https://pith.science/pith/BKWVIYH4PSLFVMBR6JAONO3AKA/action/replication_record"}},"created_at":"2026-05-17T23:45:25.105868+00:00","updated_at":"2026-05-17T23:45:25.105868+00:00"}