{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7ZOPIX2DSHDCGFLGYFYKUVSWUN","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":"87ae245dbb72fdef2930592391385581d32d36a1563ad5e98d971cfa0ec54549","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T15:35:32Z","title_canon_sha256":"053f2a601207f156db49927a7432873ed5aab13179a2b2fa5a3170cb390ed99e"},"schema_version":"1.0","source":{"id":"2411.18444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18444","created_at":"2026-07-05T10:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18444v1","created_at":"2026-07-05T10:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18444","created_at":"2026-07-05T10:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"7ZOPIX2DSHDC","created_at":"2026-07-05T10:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"7ZOPIX2DSHDCGFLG","created_at":"2026-07-05T10:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"7ZOPIX2D","created_at":"2026-07-05T10:16:17Z"}],"graph_snapshots":[{"event_id":"sha256:1e4d2a46a5493ab490987e6c1a31921e6897b8d424026397daea8ff86b17765a","target":"graph","created_at":"2026-07-05T10:16:17Z","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/2411.18444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors. Recent studies suggest using large language models (LLMs), which have the benefit of better context understanding and adaption of error definitions without training on a large number of human preference judgments. However, current LLM-based evaluators risk masking errors and can only serve as a weak proxy, leaving human evaluation the go","authors_text":"Bela Gipp, Frederic Kirstein, Terry Ruas","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T15:35:32Z","title":"Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18444","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":"sha256:3f61f507733d85de98b2a2fc078210a7897c6069ac2e8fee55d864b83b90f383","target":"record","created_at":"2026-07-05T10:16:17Z","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":"87ae245dbb72fdef2930592391385581d32d36a1563ad5e98d971cfa0ec54549","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T15:35:32Z","title_canon_sha256":"053f2a601207f156db49927a7432873ed5aab13179a2b2fa5a3170cb390ed99e"},"schema_version":"1.0","source":{"id":"2411.18444","kind":"arxiv","version":1}},"canonical_sha256":"fe5cf45f4391c6231566c170aa5656a3666ef5d1c20a3bc17787dd029143e4e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe5cf45f4391c6231566c170aa5656a3666ef5d1c20a3bc17787dd029143e4e4","first_computed_at":"2026-07-05T10:16:17.301972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:17.301972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TR5iDtrBqDGCmjbgN3F1jnpq3xNeIR+O95gJkPSEX2YCsldeCt5qTwXXqLXBPxFY+GRrmfYMJ3EVnnovNlfoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:17.302471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f61f507733d85de98b2a2fc078210a7897c6069ac2e8fee55d864b83b90f383","sha256:1e4d2a46a5493ab490987e6c1a31921e6897b8d424026397daea8ff86b17765a"],"state_sha256":"44f6a71aa0753b79b2f76f8f9a5d998968101339e27fde0f962d4ea62ad7a37c"}