{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X6Y4EP2L4I7447T77ALCNWMSUX","short_pith_number":"pith:X6Y4EP2L","schema_version":"1.0","canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","source":{"kind":"arxiv","id":"1905.03197","version":3},"attestation_state":"computed","paper":{"title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hsiao-Wuen Hon, Jianfeng Gao, Li Dong, Ming Zhou, Nan Yang, Wenhui Wang, XiaoDong Liu, Yu Wang","submitted_at":"2019-05-08T16:33:51Z","abstract_excerpt":"This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieve"},"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":"1905.03197","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","cross_cats_sorted":[],"title_canon_sha256":"2514f1db36b89ff10e5baf58e06b48cb0eb9a81fbccd53c0c8b61bd13135585f","abstract_canon_sha256":"1eae07da2cf3572311506acc8e637b099e8b61089a8f2fb46f10dc3f1bc0c8a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:59.460447Z","signature_b64":"xyNEDj43QVHJg+cJGMSG92tlY85QAxeMoP3i50v4UVf0A+6tupPRBnf7X0h6OjGQyFdAEGjqyXEY+HyhHu4cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","last_reissued_at":"2026-07-05T00:11:59.459979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:59.459979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hsiao-Wuen Hon, Jianfeng Gao, Li Dong, Ming Zhou, Nan Yang, Wenhui Wang, XiaoDong Liu, Yu Wang","submitted_at":"2019-05-08T16:33:51Z","abstract_excerpt":"This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03197","kind":"arxiv","version":3},"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/1905.03197/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":"1905.03197","created_at":"2026-07-05T00:11:59.460037+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03197v3","created_at":"2026-07-05T00:11:59.460037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03197","created_at":"2026-07-05T00:11:59.460037+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6Y4EP2L4I74","created_at":"2026-07-05T00:11:59.460037+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6Y4EP2L4I7447T7","created_at":"2026-07-05T00:11:59.460037+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6Y4EP2L","created_at":"2026-07-05T00:11:59.460037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.08722","citing_title":"What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2109.10616","citing_title":"Enriching and Controlling Global Semantics for Text Summarization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00761","citing_title":"Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"1910.13461","citing_title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"1907.11692","citing_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX","json":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX.json","graph_json":"https://pith.science/api/pith-number/X6Y4EP2L4I7447T77ALCNWMSUX/graph.json","events_json":"https://pith.science/api/pith-number/X6Y4EP2L4I7447T77ALCNWMSUX/events.json","paper":"https://pith.science/paper/X6Y4EP2L"},"agent_actions":{"view_html":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX","download_json":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX.json","view_paper":"https://pith.science/paper/X6Y4EP2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03197&json=true","fetch_graph":"https://pith.science/api/pith-number/X6Y4EP2L4I7447T77ALCNWMSUX/graph.json","fetch_events":"https://pith.science/api/pith-number/X6Y4EP2L4I7447T77ALCNWMSUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/action/storage_attestation","attest_author":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/action/author_attestation","sign_citation":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/action/citation_signature","submit_replication":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/action/replication_record"}},"created_at":"2026-07-05T00:11:59.460037+00:00","updated_at":"2026-07-05T00:11:59.460037+00:00"}