{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PELQBYWEAHJAYTBL4YTO2RHWZJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b8361bf171f3fba16e4593293e7fa88d1abfddf110cf2d93a3c9c35a3a24721","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T21:23:01Z","title_canon_sha256":"f6ccad6462ae392e2d8d152019b96fbc3ca76a53a63ca5244badda6a5cfdee56"},"schema_version":"1.0","source":{"id":"2110.07731","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07731","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07731v2","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07731","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"PELQBYWEAHJA","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"PELQBYWEAHJAYTBL","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"PELQBYWE","created_at":"2026-07-05T04:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:f3d1598b58824d802de498fb26ec4639feb4e29022e3364b22420644141086cb","target":"graph","created_at":"2026-07-05T04:19:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.07731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Armen Aghajanyan, Barlas O\\u{g}uz, Dmytro Okhonko, Patrick Huber, Sonal Gupta, Wen-tau Yih, Xilun Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T21:23:01Z","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07731","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b25091fa1ad54c7519ddc5f2d7c8fd51a578215c5194887d5edc28a418921a99","target":"record","created_at":"2026-07-05T04:19:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b8361bf171f3fba16e4593293e7fa88d1abfddf110cf2d93a3c9c35a3a24721","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T21:23:01Z","title_canon_sha256":"f6ccad6462ae392e2d8d152019b96fbc3ca76a53a63ca5244badda6a5cfdee56"},"schema_version":"1.0","source":{"id":"2110.07731","kind":"arxiv","version":2}},"canonical_sha256":"791700e2c401d20c4c2be626ed44f6ca7c4dfe8ef9676bc54b1af21a55d325c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"791700e2c401d20c4c2be626ed44f6ca7c4dfe8ef9676bc54b1af21a55d325c5","first_computed_at":"2026-07-05T04:19:22.633760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:22.633760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X++5SRVpQm4wdaigR67v+VhMlBi6aq4Y3SzcEtSXY8bo8wPtGtQCLUdl0zWSliLXQgfMNSculcO/Pmu2YMD+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:22.634172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07731","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b25091fa1ad54c7519ddc5f2d7c8fd51a578215c5194887d5edc28a418921a99","sha256:f3d1598b58824d802de498fb26ec4639feb4e29022e3364b22420644141086cb"],"state_sha256":"5511ad632288c33abbe0f58255034cbb5178f8e858876522499665d64e97dc68"}