{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7ERZDXYL7TK3WXY2KKQX5IYFNT","short_pith_number":"pith:7ERZDXYL","schema_version":"1.0","canonical_sha256":"f92391df0bfcd5bb5f1a52a17ea3056cd545539e079b0b0e8a8b5edc5bfee877","source":{"kind":"arxiv","id":"2209.12617","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amer Farea, Frank Emmert-Streib, Kien Duong, Nadeesha Perera, Zhen Yang","submitted_at":"2022-09-10T12:29:04Z","abstract_excerpt":"Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP). A reason, therefore, is that a QA system allows humans to interact more naturally with a machine, e.g., via a virtual assistant or search engine. In the last decades, many QA systems have been proposed to address the requirements of different question-answering tasks. Furthermore, many error scores have been introduced, e.g., based on n-gram matching, word embeddings, or contextual embeddings to measure the performance of a QA system. This survey attempts to"},"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":"2209.12617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-10T12:29:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39064146f3cf541797576b43a760cc28c7af93ae5b45aaf4cad7c497a0885f45","abstract_canon_sha256":"86611623845e4c583c767e46a7d4c2529b53b640d371dba16b5e4ec0cc9e0dfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:54.312708Z","signature_b64":"Hd3w9RkfK+027Qjr7A05VDotSLJ1mX8qx/2NqIotfpWoVJzW9E92StzLZxZpZOWqc8r3heGKE0PkLVKWgw0sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92391df0bfcd5bb5f1a52a17ea3056cd545539e079b0b0e8a8b5edc5bfee877","last_reissued_at":"2026-07-05T05:00:54.312261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:54.312261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amer Farea, Frank Emmert-Streib, Kien Duong, Nadeesha Perera, Zhen Yang","submitted_at":"2022-09-10T12:29:04Z","abstract_excerpt":"Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP). A reason, therefore, is that a QA system allows humans to interact more naturally with a machine, e.g., via a virtual assistant or search engine. In the last decades, many QA systems have been proposed to address the requirements of different question-answering tasks. Furthermore, many error scores have been introduced, e.g., based on n-gram matching, word embeddings, or contextual embeddings to measure the performance of a QA system. This survey attempts to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12617","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/2209.12617/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":"2209.12617","created_at":"2026-07-05T05:00:54.312325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12617v1","created_at":"2026-07-05T05:00:54.312325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12617","created_at":"2026-07-05T05:00:54.312325+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ERZDXYL7TK3","created_at":"2026-07-05T05:00:54.312325+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ERZDXYL7TK3WXY2","created_at":"2026-07-05T05:00:54.312325+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ERZDXYL","created_at":"2026-07-05T05:00:54.312325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12143","citing_title":"Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT","json":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT.json","graph_json":"https://pith.science/api/pith-number/7ERZDXYL7TK3WXY2KKQX5IYFNT/graph.json","events_json":"https://pith.science/api/pith-number/7ERZDXYL7TK3WXY2KKQX5IYFNT/events.json","paper":"https://pith.science/paper/7ERZDXYL"},"agent_actions":{"view_html":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT","download_json":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT.json","view_paper":"https://pith.science/paper/7ERZDXYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12617&json=true","fetch_graph":"https://pith.science/api/pith-number/7ERZDXYL7TK3WXY2KKQX5IYFNT/graph.json","fetch_events":"https://pith.science/api/pith-number/7ERZDXYL7TK3WXY2KKQX5IYFNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT/action/storage_attestation","attest_author":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT/action/author_attestation","sign_citation":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT/action/citation_signature","submit_replication":"https://pith.science/pith/7ERZDXYL7TK3WXY2KKQX5IYFNT/action/replication_record"}},"created_at":"2026-07-05T05:00:54.312325+00:00","updated_at":"2026-07-05T05:00:54.312325+00:00"}