{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G4TL5LADVM5EJCPRJCYFRSL6I4","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":"1cbb25879833a8f1678e2f5fc28b6a8c2620ab310884730fb2c0e0c7c3487bb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T16:54:24Z","title_canon_sha256":"f388ce3f587b20437ecfd4b9b05715257732fc2ca03b8fd3180b013b3e6359d4"},"schema_version":"1.0","source":{"id":"2305.18201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18201","created_at":"2026-07-05T06:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18201v1","created_at":"2026-07-05T06:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18201","created_at":"2026-07-05T06:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"G4TL5LADVM5E","created_at":"2026-07-05T06:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"G4TL5LADVM5EJCPR","created_at":"2026-07-05T06:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"G4TL5LAD","created_at":"2026-07-05T06:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:1e5684cdabc27a8f541b6ddd79200fdeaa0d7504e5c45eeb6f06c077b5ffef6c","target":"graph","created_at":"2026-07-05T06:14:53Z","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/2305.18201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study of the evaluation of long-form answers, covering both human and automatic evaluation practices. We hire domain experts in seven areas to provide preference judgments over pairs of answers, along with free-form justifications for their choices. We present a careful analysis of experts' evaluation, which focuses on new aspects such as the comprehensiveness of the answer. Next, we examine automatic text generation metric","authors_text":"Eunsol Choi, Fangyuan Xu, Mohit Iyyer, Yixiao Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T16:54:24Z","title":"A Critical Evaluation of Evaluations for Long-form Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18201","kind":"arxiv","version":1},"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:fe74e38497ad68f51c2a15984959a2102bbfc775e5a2aa70861d9f49b2b71c68","target":"record","created_at":"2026-07-05T06:14:53Z","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":"1cbb25879833a8f1678e2f5fc28b6a8c2620ab310884730fb2c0e0c7c3487bb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T16:54:24Z","title_canon_sha256":"f388ce3f587b20437ecfd4b9b05715257732fc2ca03b8fd3180b013b3e6359d4"},"schema_version":"1.0","source":{"id":"2305.18201","kind":"arxiv","version":1}},"canonical_sha256":"3726beac03ab3a4489f148b058c97e473dfa7dbaf53d5168a17e2e67761d05ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3726beac03ab3a4489f148b058c97e473dfa7dbaf53d5168a17e2e67761d05ea","first_computed_at":"2026-07-05T06:14:53.389743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:53.389743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAidClqWemjyVchzHuP7Dix8FTlx0reP1ntar3sPvZ8/HPAj/yVvFrRajM1e3PTvtjoi//P66EXruCw2OnHWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:53.390208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe74e38497ad68f51c2a15984959a2102bbfc775e5a2aa70861d9f49b2b71c68","sha256:1e5684cdabc27a8f541b6ddd79200fdeaa0d7504e5c45eeb6f06c077b5ffef6c"],"state_sha256":"f5c2634022ba963948a6827c6ca0b4d6ca784a7b4055752e2a329c3886b8fd0f"}