{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QDF5NZG7SPMJD6O7H2537YF7PU","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":"9435b2a2aeecfa115c50eb641b453cd323737b5d39febbbd4d7648578cea3517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:30:20Z","title_canon_sha256":"4b1c3dae6e54e417427b8ae5bfb34cb0662ef08c5c001666d9a37defbc99e7c1"},"schema_version":"1.0","source":{"id":"2010.12834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12834","created_at":"2026-07-05T02:46:25Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12834v2","created_at":"2026-07-05T02:46:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12834","created_at":"2026-07-05T02:46:25Z"},{"alias_kind":"pith_short_12","alias_value":"QDF5NZG7SPMJ","created_at":"2026-07-05T02:46:25Z"},{"alias_kind":"pith_short_16","alias_value":"QDF5NZG7SPMJD6O7","created_at":"2026-07-05T02:46:25Z"},{"alias_kind":"pith_short_8","alias_value":"QDF5NZG7","created_at":"2026-07-05T02:46:25Z"}],"graph_snapshots":[{"event_id":"sha256:35908ea52c68a9d48633423e3eff78477ac6ebac7e99942f2a950aff0da6f8cd","target":"graph","created_at":"2026-07-05T02:46:25Z","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/2010.12834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While neural language models can generate text with remarkable fluency and coherence, controlling for factual correctness in generation remains an open research question. This major discrepancy between the surface-level fluency and the content-level correctness of neural generation has motivated a new line of research that seeks automatic metrics for evaluating the factuality of machine text. In this paper, we introduce GO FIGURE, a meta-evaluation framework for evaluating factuality evaluation metrics. We propose five necessary and intuitive conditions to evaluate factuality metrics on diagno","authors_text":"Asli Celikyilmaz, Jianfeng Gao, Rahul Jha, Saadia Gabriel, Yejin Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:30:20Z","title":"GO FIGURE: A Meta Evaluation of Factuality in Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12834","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":"sha256:9c0517230a08271d9503376bcc9dcf8047bc0f9ebc85ae486eff8b7e75ba0e01","target":"record","created_at":"2026-07-05T02:46:25Z","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":"9435b2a2aeecfa115c50eb641b453cd323737b5d39febbbd4d7648578cea3517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T08:30:20Z","title_canon_sha256":"4b1c3dae6e54e417427b8ae5bfb34cb0662ef08c5c001666d9a37defbc99e7c1"},"schema_version":"1.0","source":{"id":"2010.12834","kind":"arxiv","version":2}},"canonical_sha256":"80cbd6e4df93d891f9df3ebbbfe0bf7d2ffabf0aa3e65d59c179c2e807faea11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80cbd6e4df93d891f9df3ebbbfe0bf7d2ffabf0aa3e65d59c179c2e807faea11","first_computed_at":"2026-07-05T02:46:25.151841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:25.151841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vWTSmMZtUtSZ2PxSENhbtTngZCnXqsXPC2e7QrNmhUIBbKgtuV7bAlJfWEo71v0lfqztuFWpHtRSFAr7HB4uAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:25.152348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c0517230a08271d9503376bcc9dcf8047bc0f9ebc85ae486eff8b7e75ba0e01","sha256:35908ea52c68a9d48633423e3eff78477ac6ebac7e99942f2a950aff0da6f8cd"],"state_sha256":"5d2e3937b0d8682b6765d0c040ef171de99b9f7ea9842b6fecb62bc393c196d3"}