{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HPMHKLMGFV3OISLBJSW4RW5IEC","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":"aefdf90388bdbd8c2f35188ddbeba8ab82926df1ea0ed851409a4b379151b184","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-11T16:39:15Z","title_canon_sha256":"1540ddbd55e5f7b7cd9b7a16d591d4651352f9b6025d1a46616bedfc8a39709e"},"schema_version":"1.0","source":{"id":"2203.06063","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06063","created_at":"2026-07-05T04:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06063v2","created_at":"2026-07-05T04:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06063","created_at":"2026-07-05T04:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"HPMHKLMGFV3O","created_at":"2026-07-05T04:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"HPMHKLMGFV3OISLB","created_at":"2026-07-05T04:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"HPMHKLMG","created_at":"2026-07-05T04:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:39076c5b7b4bec86caac05172cbc903b8551d64a64578b8cb86610a967449c57","target":"graph","created_at":"2026-07-05T04:15:14Z","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/2203.06063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown the advantages of evaluating NLG systems using pairwise comparisons as opposed to direct assessment. Given $k$ systems, a naive approach for identifying the top-ranked system would be to uniformly obtain pairwise comparisons from all ${k \\choose 2}$ pairs of systems. However, this can be very expensive as the number of human annotations required would grow quadratically with $k$. In this work, we introduce Active Evaluation, a framework to efficiently identify the top-ranked system by actively choosing system pairs for comparison using dueling bandit algorithms. We pe","authors_text":"Akash Kumar Mohankumar, Mitesh M. Khapra","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-11T16:39:15Z","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06063","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:ad1a68aaf174e76b8bf1e5471020dd1b50a0357527e384c2321cdfabd560abe8","target":"record","created_at":"2026-07-05T04:15:14Z","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":"aefdf90388bdbd8c2f35188ddbeba8ab82926df1ea0ed851409a4b379151b184","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-11T16:39:15Z","title_canon_sha256":"1540ddbd55e5f7b7cd9b7a16d591d4651352f9b6025d1a46616bedfc8a39709e"},"schema_version":"1.0","source":{"id":"2203.06063","kind":"arxiv","version":2}},"canonical_sha256":"3bd8752d862d76e449614cadc8dba8208438705f02761bb7b707602b0c8f7818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bd8752d862d76e449614cadc8dba8208438705f02761bb7b707602b0c8f7818","first_computed_at":"2026-07-05T04:15:14.812336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:14.812336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ugqWMtO9wT/rROL/z0CrUscXK4m5bQ77gfdIn8aS9Bxzb8JJXxIQVq32Z03AtHDBMPqiixf0mActkheTnWOlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:14.812793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06063","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad1a68aaf174e76b8bf1e5471020dd1b50a0357527e384c2321cdfabd560abe8","sha256:39076c5b7b4bec86caac05172cbc903b8551d64a64578b8cb86610a967449c57"],"state_sha256":"e54568d4e95ae26cd2c905b2c003d439523b239ef9408fbb88338428a3336ea4"}