{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K4XKZVT2P2R3N4ZX7GXADYU25F","short_pith_number":"pith:K4XKZVT2","schema_version":"1.0","canonical_sha256":"572eacd67a7ea3b6f337f9ae01e29ae97b357c6576feb7b221f16bb1a77822cf","source":{"kind":"arxiv","id":"2206.15030","version":1},"attestation_state":"computed","paper":{"title":"Modern Question Answering Datasets and Benchmarks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Zhen Wang","submitted_at":"2022-06-30T05:53:56Z","abstract_excerpt":"Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. With the development of deep learning, more and more challenging QA datasets are being proposed, and lots of new methods for solving them are also emerging. In this paper, we investigate influential QA datasets that have been released in the era of deep learning. Specifically, we begin with introducing two of the most common QA tasks - textual question answer and visual quest"},"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":"2206.15030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T05:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"57406c68d21c00442cfdde5d53b44ced83801c3b69f0425d70121620915d5d09","abstract_canon_sha256":"bd76955d620aa56139d5fce67638a38c586853212f013b74c59bf88ad8c35fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:24.312109Z","signature_b64":"eKg0PMljRKlKfP7YXDUOOZ+mXxjg52AbzSWUnSVgG8hhAZbnENQ9BECQ4hRrDxbMoog6uImVo0FhwqjuCK/5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572eacd67a7ea3b6f337f9ae01e29ae97b357c6576feb7b221f16bb1a77822cf","last_reissued_at":"2026-07-05T04:36:24.311702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:24.311702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modern Question Answering Datasets and Benchmarks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Zhen Wang","submitted_at":"2022-06-30T05:53:56Z","abstract_excerpt":"Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. With the development of deep learning, more and more challenging QA datasets are being proposed, and lots of new methods for solving them are also emerging. In this paper, we investigate influential QA datasets that have been released in the era of deep learning. Specifically, we begin with introducing two of the most common QA tasks - textual question answer and visual quest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15030","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.15030/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":"2206.15030","created_at":"2026-07-05T04:36:24.311762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15030v1","created_at":"2026-07-05T04:36:24.311762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15030","created_at":"2026-07-05T04:36:24.311762+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4XKZVT2P2R3","created_at":"2026-07-05T04:36:24.311762+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4XKZVT2P2R3N4ZX","created_at":"2026-07-05T04:36:24.311762+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4XKZVT2","created_at":"2026-07-05T04:36:24.311762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01093","citing_title":"Natural Context Drift Undermines the Natural Language Understanding of Large Language Models","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F","json":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F.json","graph_json":"https://pith.science/api/pith-number/K4XKZVT2P2R3N4ZX7GXADYU25F/graph.json","events_json":"https://pith.science/api/pith-number/K4XKZVT2P2R3N4ZX7GXADYU25F/events.json","paper":"https://pith.science/paper/K4XKZVT2"},"agent_actions":{"view_html":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F","download_json":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F.json","view_paper":"https://pith.science/paper/K4XKZVT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15030&json=true","fetch_graph":"https://pith.science/api/pith-number/K4XKZVT2P2R3N4ZX7GXADYU25F/graph.json","fetch_events":"https://pith.science/api/pith-number/K4XKZVT2P2R3N4ZX7GXADYU25F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F/action/storage_attestation","attest_author":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F/action/author_attestation","sign_citation":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F/action/citation_signature","submit_replication":"https://pith.science/pith/K4XKZVT2P2R3N4ZX7GXADYU25F/action/replication_record"}},"created_at":"2026-07-05T04:36:24.311762+00:00","updated_at":"2026-07-05T04:36:24.311762+00:00"}