{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4","short_pith_number":"pith:FKL2ZZFC","schema_version":"1.0","canonical_sha256":"2a97ace4a22f94ad1a89ee43065e284f13c6dacfb17a9756c98315616b757655","source":{"kind":"arxiv","id":"1611.09830","version":3},"attestation_state":"computed","paper":{"title":"NewsQA: A Machine Comprehension Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Alessandro Sordoni, Justin Harris, Kaheer Suleman, Philip Bachman, Tong Wang, Xingdi Yuan","submitted_at":"2016-11-29T20:38:07Z","abstract_excerpt":"We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text from the corresponding articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. A thorough analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several "},"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":"1611.09830","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-29T20:38:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73d88bafac923a4ecdb634706d30683f011b4cdc4a7433575aece69260d1a0ae","abstract_canon_sha256":"cb7b3bd37039f1cb8bdedcdd522b74c2889acbd1920f218127ccd42ce774d2ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:12.937448Z","signature_b64":"KZN1/Jy7XmAc+0zo42CGw/gFitBhZoOnJWZ5VUimSvSrR2oSj2Da1ZJLT7eGSBhSI4S1lfLBdrB4ZebRRjY6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a97ace4a22f94ad1a89ee43065e284f13c6dacfb17a9756c98315616b757655","last_reissued_at":"2026-05-18T00:51:12.936681Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:12.936681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NewsQA: A Machine Comprehension Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Alessandro Sordoni, Justin Harris, Kaheer Suleman, Philip Bachman, Tong Wang, Xingdi Yuan","submitted_at":"2016-11-29T20:38:07Z","abstract_excerpt":"We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text from the corresponding articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. A thorough analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09830","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":""},"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":"1611.09830","created_at":"2026-05-18T00:51:12.936804+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09830v3","created_at":"2026-05-18T00:51:12.936804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09830","created_at":"2026-05-18T00:51:12.936804+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKL2ZZFCF6KK","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKL2ZZFCF6KK2GUJ","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKL2ZZFC","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.01686","citing_title":"Machine Reading Comprehension: a Literature Review","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":211,"is_internal_anchor":true},{"citing_arxiv_id":"1909.05858","citing_title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","ref_index":45,"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":73,"is_internal_anchor":false},{"citing_arxiv_id":"1705.03551","citing_title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4","json":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4.json","graph_json":"https://pith.science/api/pith-number/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/graph.json","events_json":"https://pith.science/api/pith-number/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/events.json","paper":"https://pith.science/paper/FKL2ZZFC"},"agent_actions":{"view_html":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4","download_json":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4.json","view_paper":"https://pith.science/paper/FKL2ZZFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09830&json=true","fetch_graph":"https://pith.science/api/pith-number/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/action/storage_attestation","attest_author":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/action/author_attestation","sign_citation":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/action/citation_signature","submit_replication":"https://pith.science/pith/FKL2ZZFCF6KK2GUJ5ZBQMXRIJ4/action/replication_record"}},"created_at":"2026-05-18T00:51:12.936804+00:00","updated_at":"2026-05-18T00:51:12.936804+00:00"}