{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H3MM5KNYWX6FGNSV7ZD6DFBC3U","short_pith_number":"pith:H3MM5KNY","schema_version":"1.0","canonical_sha256":"3ed8cea9b8b5fc533655fe47e19422dd277c246c8e458afc1c5b54b2e65536b1","source":{"kind":"arxiv","id":"2104.08727","version":2},"attestation_state":"computed","paper":{"title":"GooAQ: Open Question Answering with Diverse Answer Types","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amos Ng, Ashish Sabharwal, Chris Callison-Burch, Daniel Khashabi, Hannaneh Hajishirzi, Tushar Khot","submitted_at":"2021-04-18T05:40:39Z","abstract_excerpt":"While day-to-day questions come with a variety of answer types, the current question-answering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GooAQ, a large-scale dataset with a variety of answer types. This dataset contains over 5 million questions and 3 million answers collected from Google. GooAQ questions are collected semi-automatically from the Google search engine using its autocomplete feature. This results in naturalistic questions of practical interest that are nonetheless short and expressed using simple language. GooAQ an"},"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":"2104.08727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T05:40:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a338910d5969779fdf58bdc4ca50cb29232b10c1697c9c355f2ac23f4812019","abstract_canon_sha256":"856874927d2c006c8229f899590f927434f0e073b03ef52570c84323efebf7d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:27.469504Z","signature_b64":"oMcHkl+qpHrCZmTwS22jnLBW4HctbPSAS6tkBv7n4tC51gccuoE+tmMKVaESarwmlk+0q8gFFm1xaEQoMB2XBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed8cea9b8b5fc533655fe47e19422dd277c246c8e458afc1c5b54b2e65536b1","last_reissued_at":"2026-07-05T03:13:27.469005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:27.469005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GooAQ: Open Question Answering with Diverse Answer Types","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amos Ng, Ashish Sabharwal, Chris Callison-Burch, Daniel Khashabi, Hannaneh Hajishirzi, Tushar Khot","submitted_at":"2021-04-18T05:40:39Z","abstract_excerpt":"While day-to-day questions come with a variety of answer types, the current question-answering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GooAQ, a large-scale dataset with a variety of answer types. This dataset contains over 5 million questions and 3 million answers collected from Google. GooAQ questions are collected semi-automatically from the Google search engine using its autocomplete feature. This results in naturalistic questions of practical interest that are nonetheless short and expressed using simple language. GooAQ an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08727","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/2104.08727/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":"2104.08727","created_at":"2026-07-05T03:13:27.469066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08727v2","created_at":"2026-07-05T03:13:27.469066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08727","created_at":"2026-07-05T03:13:27.469066+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3MM5KNYWX6F","created_at":"2026-07-05T03:13:27.469066+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3MM5KNYWX6FGNSV","created_at":"2026-07-05T03:13:27.469066+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3MM5KNY","created_at":"2026-07-05T03:13:27.469066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06563","citing_title":"DS@GT at CheckThat! 2025: Exploring Retrieval and Reranking Pipelines for Scientific Claim Source Retrieval on Social Media Discourse","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U","json":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U.json","graph_json":"https://pith.science/api/pith-number/H3MM5KNYWX6FGNSV7ZD6DFBC3U/graph.json","events_json":"https://pith.science/api/pith-number/H3MM5KNYWX6FGNSV7ZD6DFBC3U/events.json","paper":"https://pith.science/paper/H3MM5KNY"},"agent_actions":{"view_html":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U","download_json":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U.json","view_paper":"https://pith.science/paper/H3MM5KNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08727&json=true","fetch_graph":"https://pith.science/api/pith-number/H3MM5KNYWX6FGNSV7ZD6DFBC3U/graph.json","fetch_events":"https://pith.science/api/pith-number/H3MM5KNYWX6FGNSV7ZD6DFBC3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U/action/storage_attestation","attest_author":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U/action/author_attestation","sign_citation":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U/action/citation_signature","submit_replication":"https://pith.science/pith/H3MM5KNYWX6FGNSV7ZD6DFBC3U/action/replication_record"}},"created_at":"2026-07-05T03:13:27.469066+00:00","updated_at":"2026-07-05T03:13:27.469066+00:00"}