{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PELQBYWEAHJAYTBL4YTO2RHWZJ","short_pith_number":"pith:PELQBYWE","schema_version":"1.0","canonical_sha256":"791700e2c401d20c4c2be626ed44f6ca7c4dfe8ef9676bc54b1af21a55d325c5","source":{"kind":"arxiv","id":"2110.07731","version":2},"attestation_state":"computed","paper":{"title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Armen Aghajanyan, Barlas O\\u{g}uz, Dmytro Okhonko, Patrick Huber, Sonal Gupta, Wen-tau Yih, Xilun Chen","submitted_at":"2021-10-14T21:23:01Z","abstract_excerpt":"With the rise of large-scale pre-trained language models, open-domain question-answering (ODQA) has become an important research topic in NLP. Based on the popular pre-training fine-tuning approach, we posit that an additional in-domain pre-training stage using a large-scale, natural, and diverse question-answering (QA) dataset can be beneficial for ODQA. Consequently, we propose a novel QA dataset based on the Common Crawl project in this paper. Using the readily available schema.org annotation, we extract around 130 million multilingual question-answer pairs, including about 60 million Engli"},"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":"2110.07731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T21:23:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f6ccad6462ae392e2d8d152019b96fbc3ca76a53a63ca5244badda6a5cfdee56","abstract_canon_sha256":"0b8361bf171f3fba16e4593293e7fa88d1abfddf110cf2d93a3c9c35a3a24721"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:22.634172Z","signature_b64":"X++5SRVpQm4wdaigR67v+VhMlBi6aq4Y3SzcEtSXY8bo8wPtGtQCLUdl0zWSliLXQgfMNSculcO/Pmu2YMD+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"791700e2c401d20c4c2be626ed44f6ca7c4dfe8ef9676bc54b1af21a55d325c5","last_reissued_at":"2026-07-05T04:19:22.633760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:22.633760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Armen Aghajanyan, Barlas O\\u{g}uz, Dmytro Okhonko, Patrick Huber, Sonal Gupta, Wen-tau Yih, Xilun Chen","submitted_at":"2021-10-14T21:23:01Z","abstract_excerpt":"With the rise of large-scale pre-trained language models, open-domain question-answering (ODQA) has become an important research topic in NLP. Based on the popular pre-training fine-tuning approach, we posit that an additional in-domain pre-training stage using a large-scale, natural, and diverse question-answering (QA) dataset can be beneficial for ODQA. Consequently, we propose a novel QA dataset based on the Common Crawl project in this paper. Using the readily available schema.org annotation, we extract around 130 million multilingual question-answer pairs, including about 60 million Engli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07731","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.07731/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":"2110.07731","created_at":"2026-07-05T04:19:22.633814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07731v2","created_at":"2026-07-05T04:19:22.633814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07731","created_at":"2026-07-05T04:19:22.633814+00:00"},{"alias_kind":"pith_short_12","alias_value":"PELQBYWEAHJA","created_at":"2026-07-05T04:19:22.633814+00:00"},{"alias_kind":"pith_short_16","alias_value":"PELQBYWEAHJAYTBL","created_at":"2026-07-05T04:19:22.633814+00:00"},{"alias_kind":"pith_short_8","alias_value":"PELQBYWE","created_at":"2026-07-05T04:19:22.633814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ","json":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ.json","graph_json":"https://pith.science/api/pith-number/PELQBYWEAHJAYTBL4YTO2RHWZJ/graph.json","events_json":"https://pith.science/api/pith-number/PELQBYWEAHJAYTBL4YTO2RHWZJ/events.json","paper":"https://pith.science/paper/PELQBYWE"},"agent_actions":{"view_html":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ","download_json":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ.json","view_paper":"https://pith.science/paper/PELQBYWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07731&json=true","fetch_graph":"https://pith.science/api/pith-number/PELQBYWEAHJAYTBL4YTO2RHWZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PELQBYWEAHJAYTBL4YTO2RHWZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ/action/storage_attestation","attest_author":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ/action/author_attestation","sign_citation":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ/action/citation_signature","submit_replication":"https://pith.science/pith/PELQBYWEAHJAYTBL4YTO2RHWZJ/action/replication_record"}},"created_at":"2026-07-05T04:19:22.633814+00:00","updated_at":"2026-07-05T04:19:22.633814+00:00"}