{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R22L6ARN4PC6SZTNK7EAOWIV5B","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":"f612d1c448928cbeacedcf342a46c3138b63f53a5d0a522b4693602d9f56eef2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T18:44:49Z","title_canon_sha256":"1c1737366acfa6e78aba3b736b503aaceba4de433f88636d3d2b0af98e978768"},"schema_version":"1.0","source":{"id":"1909.03087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03087","created_at":"2026-07-05T00:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03087v1","created_at":"2026-07-05T00:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03087","created_at":"2026-07-05T00:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"R22L6ARN4PC6","created_at":"2026-07-05T00:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"R22L6ARN4PC6SZTN","created_at":"2026-07-05T00:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"R22L6ARN","created_at":"2026-07-05T00:03:02Z"}],"graph_snapshots":[{"event_id":"sha256:643364c77b494ce1c2657dd0d9f0ba73887e5bad5f3135ef54818e31f161a2c3","target":"graph","created_at":"2026-07-05T00:03:02Z","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/1909.03087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While dialogue remains an important end-goal of natural language research, the difficulty of evaluation is an oft-quoted reason why it remains troublesome to make real progress towards its solution. Evaluation difficulties are actually two-fold: not only do automatic metrics not correlate well with human judgments, but also human judgments themselves are in fact difficult to measure. The two most used human judgment tests, single-turn pairwise evaluation and multi-turn Likert scores, both have serious flaws as we discuss in this work.\n  We instead provide a novel procedure involving comparing ","authors_text":"Jason Weston, Margaret Li, Stephen Roller","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T18:44:49Z","title":"ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03087","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":"sha256:3eb60e50e759834b07cbafb6c1dcf1d8569f73398179a5462a6bef08441ab76f","target":"record","created_at":"2026-07-05T00:03:02Z","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":"f612d1c448928cbeacedcf342a46c3138b63f53a5d0a522b4693602d9f56eef2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T18:44:49Z","title_canon_sha256":"1c1737366acfa6e78aba3b736b503aaceba4de433f88636d3d2b0af98e978768"},"schema_version":"1.0","source":{"id":"1909.03087","kind":"arxiv","version":1}},"canonical_sha256":"8eb4bf022de3c5e9666d57c8075915e8787cc4edcf44eb4c24ffdcb7b6543548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb4bf022de3c5e9666d57c8075915e8787cc4edcf44eb4c24ffdcb7b6543548","first_computed_at":"2026-07-05T00:03:02.573894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:02.573894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pOepMBYGX0EOnrAiPycm7IwLSxiyVwtokbyVWu55GQQT0MBbdWrjGzlmNBHJSgbkvV/fFS/OiNcmmEiBB7PUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:02.574236Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eb60e50e759834b07cbafb6c1dcf1d8569f73398179a5462a6bef08441ab76f","sha256:643364c77b494ce1c2657dd0d9f0ba73887e5bad5f3135ef54818e31f161a2c3"],"state_sha256":"9f260dcab360730e24c84cc33f1edd75532b4c373fc75f4ccf2bfef7db65c0f9"}