{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PDAP2QN22Q66IITYJN32O4HNLF","short_pith_number":"pith:PDAP2QN2","schema_version":"1.0","canonical_sha256":"78c0fd41bad43de422784b77a770ed59622e55c2567eabef164fbbbf80bbff6f","source":{"kind":"arxiv","id":"1806.08730","version":1},"attestation_state":"computed","paper":{"title":"The Natural Language Decathlon: Multitask Learning as Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, Nitish Shirish Keskar, Richard Socher","submitted_at":"2018-06-20T16:39:26Z","abstract_excerpt":"Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answerin"},"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":"1806.08730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-20T16:39:26Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"412510f59669fb84e1ee8c64eb4b260036b25ce82c8f6859601cafe6c578f6a4","abstract_canon_sha256":"11b0084dca847d48fc274b3cdd4c921e6611ace48a86d1c8ff93a43059a5f4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:36.300741Z","signature_b64":"VkJ4efq/yIO+S9+pP3L1+05KoegVnrDz6NCFGmX0Psmto36QIji7evK2ZoGcK8eXosT3M90lAuRJPdVRz/HbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c0fd41bad43de422784b77a770ed59622e55c2567eabef164fbbbf80bbff6f","last_reissued_at":"2026-05-18T00:12:36.300177Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:36.300177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Natural Language Decathlon: Multitask Learning as Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, Nitish Shirish Keskar, Richard Socher","submitted_at":"2018-06-20T16:39:26Z","abstract_excerpt":"Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08730","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":"1806.08730","created_at":"2026-05-18T00:12:36.300262+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08730v1","created_at":"2026-05-18T00:12:36.300262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08730","created_at":"2026-05-18T00:12:36.300262+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDAP2QN22Q66","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDAP2QN22Q66IITY","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDAP2QN2","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2211.09110","citing_title":"Holistic Evaluation of Language Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2301.13688","citing_title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2104.08773","citing_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2009.01325","citing_title":"Learning to summarize from human feedback","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"1909.05858","citing_title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2304.06364","citing_title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"1905.00537","citing_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2110.08207","citing_title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1804.07461","citing_title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","ref_index":29,"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":48,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2206.07682","citing_title":"Emergent Abilities of Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF","json":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF.json","graph_json":"https://pith.science/api/pith-number/PDAP2QN22Q66IITYJN32O4HNLF/graph.json","events_json":"https://pith.science/api/pith-number/PDAP2QN22Q66IITYJN32O4HNLF/events.json","paper":"https://pith.science/paper/PDAP2QN2"},"agent_actions":{"view_html":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF","download_json":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF.json","view_paper":"https://pith.science/paper/PDAP2QN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08730&json=true","fetch_graph":"https://pith.science/api/pith-number/PDAP2QN22Q66IITYJN32O4HNLF/graph.json","fetch_events":"https://pith.science/api/pith-number/PDAP2QN22Q66IITYJN32O4HNLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF/action/storage_attestation","attest_author":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF/action/author_attestation","sign_citation":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF/action/citation_signature","submit_replication":"https://pith.science/pith/PDAP2QN22Q66IITYJN32O4HNLF/action/replication_record"}},"created_at":"2026-05-18T00:12:36.300262+00:00","updated_at":"2026-05-18T00:12:36.300262+00:00"}