{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SE26JVK2IEE3WJVCCUE7BZRQTD","short_pith_number":"pith:SE26JVK2","canonical_record":{"source":{"id":"2402.12055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T11:19:02Z","cross_cats_sorted":[],"title_canon_sha256":"d9df608391810e4369682d974b24f518ef2321b4fb91a51ef2d7008135b78588","abstract_canon_sha256":"6b034a414ff587c9e44ceb48191a7ba47f36dc8c48439c60a821940da8f2e3bf"},"schema_version":"1.0"},"canonical_sha256":"9135e4d55a4109bb26a21509f0e63098da3cb23e3fe76f322d08fc20838e9cd6","source":{"kind":"arxiv","id":"2402.12055","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12055","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12055v2","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12055","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"SE26JVK2IEE3","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_16","alias_value":"SE26JVK2IEE3WJVC","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_8","alias_value":"SE26JVK2","created_at":"2026-07-05T08:37:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SE26JVK2IEE3WJVCCUE7BZRQTD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T11:19:02Z","cross_cats_sorted":[],"title_canon_sha256":"d9df608391810e4369682d974b24f518ef2321b4fb91a51ef2d7008135b78588","abstract_canon_sha256":"6b034a414ff587c9e44ceb48191a7ba47f36dc8c48439c60a821940da8f2e3bf"},"schema_version":"1.0"},"canonical_sha256":"9135e4d55a4109bb26a21509f0e63098da3cb23e3fe76f322d08fc20838e9cd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:51.401508Z","signature_b64":"PT58oXfSOtGH8rZ+NZCTLKZSWUE9pXjXLWQZ/AePKdri56o5W5yWOInpvd5U1efetJOcMLNiIPmV5SOoYgUdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9135e4d55a4109bb26a21509f0e63098da3cb23e3fe76f322d08fc20838e9cd6","last_reissued_at":"2026-07-05T08:37:51.401030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:51.401030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12055","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFCAV5z+P64i+1Va0CQEq9vYMea9zvWB253ju1EQy68H1gLdDgaR2s//sQPN3fplwazx6zYPL6+FGdiGJdoQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:35:32.203395Z"},"content_sha256":"0bd8175e8992fb84382ed0790ba5deda7de7384e4bbe132ec8cc8b337b2d9188","schema_version":"1.0","event_id":"sha256:0bd8175e8992fb84382ed0790ba5deda7de7384e4bbe132ec8cc8b337b2d9188"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SE26JVK2IEE3WJVCCUE7BZRQTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingqi Gao, Sen Hu, Teng Xu, Xiaojun Wan, Xinyu Hu, Yang Zhang, Yicheng Chen","submitted_at":"2024-02-19T11:19:02Z","abstract_excerpt":"Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces their reliability. For further verification, we first consider avoiding issues of inconsistent conceptualization and vague expression in existing NLG quality criteria themselves. So we summarize a clear hierarchical classification system for 11 common aspects with corresponding different criteria from previous studies involved. Inspired by behavioral testing, we elaborately design 18 types of aspect-targeted perturba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12055","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.12055/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CI1UkGLDUkHSzlIzVu1n+UhaJYrqOJnMp/G7rS/jSpHZF4CIVXUEdDorbL4fsi+E+3qRx6MfIDOX4VpEQF3SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:35:32.203885Z"},"content_sha256":"d5d1ebaf86983a5fd43c47e94831e2bbd24893e69895a82e87bb440770cf0719","schema_version":"1.0","event_id":"sha256:d5d1ebaf86983a5fd43c47e94831e2bbd24893e69895a82e87bb440770cf0719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/bundle.json","state_url":"https://pith.science/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T22:35:32Z","links":{"resolver":"https://pith.science/pith/SE26JVK2IEE3WJVCCUE7BZRQTD","bundle":"https://pith.science/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/bundle.json","state":"https://pith.science/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SE26JVK2IEE3WJVCCUE7BZRQTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SE26JVK2IEE3WJVCCUE7BZRQTD","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":"6b034a414ff587c9e44ceb48191a7ba47f36dc8c48439c60a821940da8f2e3bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T11:19:02Z","title_canon_sha256":"d9df608391810e4369682d974b24f518ef2321b4fb91a51ef2d7008135b78588"},"schema_version":"1.0","source":{"id":"2402.12055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12055","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12055v2","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12055","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"SE26JVK2IEE3","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_16","alias_value":"SE26JVK2IEE3WJVC","created_at":"2026-07-05T08:37:51Z"},{"alias_kind":"pith_short_8","alias_value":"SE26JVK2","created_at":"2026-07-05T08:37:51Z"}],"graph_snapshots":[{"event_id":"sha256:d5d1ebaf86983a5fd43c47e94831e2bbd24893e69895a82e87bb440770cf0719","target":"graph","created_at":"2026-07-05T08:37:51Z","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/2402.12055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces their reliability. For further verification, we first consider avoiding issues of inconsistent conceptualization and vague expression in existing NLG quality criteria themselves. So we summarize a clear hierarchical classification system for 11 common aspects with corresponding different criteria from previous studies involved. Inspired by behavioral testing, we elaborately design 18 types of aspect-targeted perturba","authors_text":"Mingqi Gao, Sen Hu, Teng Xu, Xiaojun Wan, Xinyu Hu, Yang Zhang, Yicheng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T11:19:02Z","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12055","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":"sha256:0bd8175e8992fb84382ed0790ba5deda7de7384e4bbe132ec8cc8b337b2d9188","target":"record","created_at":"2026-07-05T08:37:51Z","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":"6b034a414ff587c9e44ceb48191a7ba47f36dc8c48439c60a821940da8f2e3bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T11:19:02Z","title_canon_sha256":"d9df608391810e4369682d974b24f518ef2321b4fb91a51ef2d7008135b78588"},"schema_version":"1.0","source":{"id":"2402.12055","kind":"arxiv","version":2}},"canonical_sha256":"9135e4d55a4109bb26a21509f0e63098da3cb23e3fe76f322d08fc20838e9cd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9135e4d55a4109bb26a21509f0e63098da3cb23e3fe76f322d08fc20838e9cd6","first_computed_at":"2026-07-05T08:37:51.401030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:51.401030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PT58oXfSOtGH8rZ+NZCTLKZSWUE9pXjXLWQZ/AePKdri56o5W5yWOInpvd5U1efetJOcMLNiIPmV5SOoYgUdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:51.401508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bd8175e8992fb84382ed0790ba5deda7de7384e4bbe132ec8cc8b337b2d9188","sha256:d5d1ebaf86983a5fd43c47e94831e2bbd24893e69895a82e87bb440770cf0719"],"state_sha256":"2cc0e995eec6f9cab8f9a414bee6755a1406e28e22f67585c8f70fae00c1940e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGMnhblwrFXCb3ESBxVO7K5Is4iMThZ5lGHHAn+SL1fGY7HAWbu9POCONiPdCrjFGfv96j7ooS4yACIxYCqwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:35:32.207591Z","bundle_sha256":"8e0d7dd82a9d45bd70882c04bcede9104f3e99077f1f1b1eea8d713b87cd7fa2"}}