{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EZSDCO2L5DLEHQODFUJBHMK4A3","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":"a8db266381cd597c879997c34171c5aafb559b7f15b451be2fd2bd70bc8d9d3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:57:56Z","title_canon_sha256":"e7462887c19783744eb6ba14ddb3ab02a084b6aba86f5d0fbc569f48150a6c3c"},"schema_version":"1.0","source":{"id":"2112.08812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08812","created_at":"2026-07-05T04:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08812v2","created_at":"2026-07-05T04:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08812","created_at":"2026-07-05T04:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"EZSDCO2L5DLE","created_at":"2026-07-05T04:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"EZSDCO2L5DLEHQOD","created_at":"2026-07-05T04:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"EZSDCO2L","created_at":"2026-07-05T04:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:ab1765f992802e33244eb4498e687910babab8e6af66792a0b0f80874fb5eac2","target":"graph","created_at":"2026-07-05T04:07:07Z","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/2112.08812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Danqi Chen, Huihan Li, Manan Goenka, Tianyu Gao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:57:56Z","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08812","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":"sha256:0dc51a238b8507d3e7bf7ce5445bca67d77f286e5888840a6b5b8e4073798bdf","target":"record","created_at":"2026-07-05T04:07:07Z","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":"a8db266381cd597c879997c34171c5aafb559b7f15b451be2fd2bd70bc8d9d3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:57:56Z","title_canon_sha256":"e7462887c19783744eb6ba14ddb3ab02a084b6aba86f5d0fbc569f48150a6c3c"},"schema_version":"1.0","source":{"id":"2112.08812","kind":"arxiv","version":2}},"canonical_sha256":"2664313b4be8d643c1c32d1213b15c06dfd77dab4b6d737c2a85d19d61b31950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2664313b4be8d643c1c32d1213b15c06dfd77dab4b6d737c2a85d19d61b31950","first_computed_at":"2026-07-05T04:07:07.022276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:07.022276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCB45xvca6bSR+XxTsBEkGQgTJ84aI5w9v06+ez4vEau8AMPlgjGKsOvfIxJrP79JFhJpbK0uYRz3YJS/zL3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:07.022724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dc51a238b8507d3e7bf7ce5445bca67d77f286e5888840a6b5b8e4073798bdf","sha256:ab1765f992802e33244eb4498e687910babab8e6af66792a0b0f80874fb5eac2"],"state_sha256":"c92bf37bf35112413522ac8f3d58964285dabc38cd372583db0fc304133ddf4f"}