{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HMXFZHIIW6YN75WYFJSECE3JO4","short_pith_number":"pith:HMXFZHII","schema_version":"1.0","canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","source":{"kind":"arxiv","id":"1901.11504","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Deep Neural Networks for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Pengcheng He, Weizhu Chen, XiaoDong Liu","submitted_at":"2019-01-31T18:07:25Z","abstract_excerpt":"In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTai"},"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":"1901.11504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"f7f03101d77075e3c232a14f053d0ff50872cf58ce2fac6c76dce64f9848e512","abstract_canon_sha256":"63025ca624c5ac5bc37ea5414af23b3e3d29b90654e850eace380e97076d0d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:42.532202Z","signature_b64":"93LsFEpgkxxodJay15axX9DkJ80qV5V2Ue5RCHscgWyWGPpk4m8pU7SisbN6nIE/lJq2dAQ5BL6fVaHs5t98Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","last_reissued_at":"2026-05-17T23:44:42.531685Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:42.531685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Deep Neural Networks for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Pengcheng He, Weizhu Chen, XiaoDong Liu","submitted_at":"2019-01-31T18:07:25Z","abstract_excerpt":"In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11504","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":"1901.11504","created_at":"2026-05-17T23:44:42.531773+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.11504v2","created_at":"2026-05-17T23:44:42.531773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11504","created_at":"2026-05-17T23:44:42.531773+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMXFZHIIW6YN","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMXFZHIIW6YN75WY","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMXFZHII","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.23919","citing_title":"Unified Multi-Task Relevance Modeling for E-Commerce: Comparing Task Routing Architectures Across LLMs and Cross-Encoders","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05338","citing_title":"To Tune or Not To Tune? How About the Best of Both Worlds?","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.08237","citing_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1905.00537","citing_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","ref_index":120,"is_internal_anchor":true},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"1909.08053","citing_title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14833","citing_title":"Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"1907.11692","citing_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4","json":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4.json","graph_json":"https://pith.science/api/pith-number/HMXFZHIIW6YN75WYFJSECE3JO4/graph.json","events_json":"https://pith.science/api/pith-number/HMXFZHIIW6YN75WYFJSECE3JO4/events.json","paper":"https://pith.science/paper/HMXFZHII"},"agent_actions":{"view_html":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4","download_json":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4.json","view_paper":"https://pith.science/paper/HMXFZHII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.11504&json=true","fetch_graph":"https://pith.science/api/pith-number/HMXFZHIIW6YN75WYFJSECE3JO4/graph.json","fetch_events":"https://pith.science/api/pith-number/HMXFZHIIW6YN75WYFJSECE3JO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/action/storage_attestation","attest_author":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/action/author_attestation","sign_citation":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/action/citation_signature","submit_replication":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/action/replication_record"}},"created_at":"2026-05-17T23:44:42.531773+00:00","updated_at":"2026-05-17T23:44:42.531773+00:00"}