{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EZSDCO2L5DLEHQODFUJBHMK4A3","short_pith_number":"pith:EZSDCO2L","schema_version":"1.0","canonical_sha256":"2664313b4be8d643c1c32d1213b15c06dfd77dab4b6d737c2a85d19d61b31950","source":{"kind":"arxiv","id":"2112.08812","version":2},"attestation_state":"computed","paper":{"title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Huihan Li, Manan Goenka, Tianyu Gao","submitted_at":"2021-12-16T11:57:56Z","abstract_excerpt":"Conversational question answering aims to provide natural-language answers to users in information-seeking conversations. Existing conversational QA benchmarks compare models with pre-collected human-human conversations, using ground-truth answers provided in conversational history. It remains unclear whether we can rely on this static evaluation for model development and whether current systems can well generalize to real-world human-machine conversations. In this work, we conduct the first large-scale human evaluation of state-of-the-art conversational QA systems, where human evaluators conv"},"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":"2112.08812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:57:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e7462887c19783744eb6ba14ddb3ab02a084b6aba86f5d0fbc569f48150a6c3c","abstract_canon_sha256":"a8db266381cd597c879997c34171c5aafb559b7f15b451be2fd2bd70bc8d9d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:07.022724Z","signature_b64":"NCB45xvca6bSR+XxTsBEkGQgTJ84aI5w9v06+ez4vEau8AMPlgjGKsOvfIxJrP79JFhJpbK0uYRz3YJS/zL3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2664313b4be8d643c1c32d1213b15c06dfd77dab4b6d737c2a85d19d61b31950","last_reissued_at":"2026-07-05T04:07:07.022276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:07.022276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Huihan Li, Manan Goenka, Tianyu Gao","submitted_at":"2021-12-16T11:57:56Z","abstract_excerpt":"Conversational question answering aims to provide natural-language answers to users in information-seeking conversations. Existing conversational QA benchmarks compare models with pre-collected human-human conversations, using ground-truth answers provided in conversational history. It remains unclear whether we can rely on this static evaluation for model development and whether current systems can well generalize to real-world human-machine conversations. In this work, we conduct the first large-scale human evaluation of state-of-the-art conversational QA systems, where human evaluators conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08812","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/2112.08812/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":"2112.08812","created_at":"2026-07-05T04:07:07.022342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08812v2","created_at":"2026-07-05T04:07:07.022342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08812","created_at":"2026-07-05T04:07:07.022342+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZSDCO2L5DLE","created_at":"2026-07-05T04:07:07.022342+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZSDCO2L5DLEHQOD","created_at":"2026-07-05T04:07:07.022342+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZSDCO2L","created_at":"2026-07-05T04:07:07.022342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10834","citing_title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3","json":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3.json","graph_json":"https://pith.science/api/pith-number/EZSDCO2L5DLEHQODFUJBHMK4A3/graph.json","events_json":"https://pith.science/api/pith-number/EZSDCO2L5DLEHQODFUJBHMK4A3/events.json","paper":"https://pith.science/paper/EZSDCO2L"},"agent_actions":{"view_html":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3","download_json":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3.json","view_paper":"https://pith.science/paper/EZSDCO2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08812&json=true","fetch_graph":"https://pith.science/api/pith-number/EZSDCO2L5DLEHQODFUJBHMK4A3/graph.json","fetch_events":"https://pith.science/api/pith-number/EZSDCO2L5DLEHQODFUJBHMK4A3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3/action/storage_attestation","attest_author":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3/action/author_attestation","sign_citation":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3/action/citation_signature","submit_replication":"https://pith.science/pith/EZSDCO2L5DLEHQODFUJBHMK4A3/action/replication_record"}},"created_at":"2026-07-05T04:07:07.022342+00:00","updated_at":"2026-07-05T04:07:07.022342+00:00"}