{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J5W6YDIOSLDHLX4QRB32GOPBOW","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":"c875a87873b7add18f45e92d57af8ee79f8f09997db03c5c2aa7ffd877371c6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:52:48Z","title_canon_sha256":"4b0df74081f192c85e558e20c1ba8adb0bdff27e93804236b5d01b3662c2b3de"},"schema_version":"1.0","source":{"id":"2305.14658","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14658","created_at":"2026-07-05T08:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14658v3","created_at":"2026-07-05T08:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14658","created_at":"2026-07-05T08:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"J5W6YDIOSLDH","created_at":"2026-07-05T08:15:36Z"},{"alias_kind":"pith_short_16","alias_value":"J5W6YDIOSLDHLX4Q","created_at":"2026-07-05T08:15:36Z"},{"alias_kind":"pith_short_8","alias_value":"J5W6YDIO","created_at":"2026-07-05T08:15:36Z"}],"graph_snapshots":[{"event_id":"sha256:62bd2578cd1c31b12b1f7a9b88cb4cb5d4237f638a3d9d7acc8d8614418ff436","target":"graph","created_at":"2026-07-05T08:15:36Z","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/2305.14658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs (large language models) such as ChatGPT have shown remarkable language understanding and generation capabilities. Although reference-free evaluators based on LLMs show better human alignment than traditional reference-based evaluators, there are many challenges in using reference-free evaluators based on LLMs. Reference-free evaluators are more suitable for open-ended examples with different semantics responses. But not all examples are open-ended. For closed-ended examples with unique correct semantic response, reference-free evaluators will still consider it high quality when giving a r","authors_text":"Daling Wang, Hinrich Sch\\\"utze, Shi Feng, Yifei Zhang, Yongkang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:52:48Z","title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14658","kind":"arxiv","version":3},"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:ad2cdbec81c49fa385837689001cc64175a0deb721244efb0cf9591a8b8a88b8","target":"record","created_at":"2026-07-05T08:15:36Z","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":"c875a87873b7add18f45e92d57af8ee79f8f09997db03c5c2aa7ffd877371c6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:52:48Z","title_canon_sha256":"4b0df74081f192c85e558e20c1ba8adb0bdff27e93804236b5d01b3662c2b3de"},"schema_version":"1.0","source":{"id":"2305.14658","kind":"arxiv","version":3}},"canonical_sha256":"4f6dec0d0e92c675df908877a339e175acfc33509a146fdad1b13f27d9947ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f6dec0d0e92c675df908877a339e175acfc33509a146fdad1b13f27d9947ff3","first_computed_at":"2026-07-05T08:15:36.125035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:36.125035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f54BnPpdfsKZChPw0Mwy42AT2H6F0q/VyEM5wOrYD5Nb+R2Aa4+u1LRbTK4Oq6nsGZMC4jx2a3piO3ZwJ83HCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:36.125512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14658","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad2cdbec81c49fa385837689001cc64175a0deb721244efb0cf9591a8b8a88b8","sha256:62bd2578cd1c31b12b1f7a9b88cb4cb5d4237f638a3d9d7acc8d8614418ff436"],"state_sha256":"4565bcb867d8abe3d755717de61186bf5d56d66c8b600882c006f8ac72c1e334"}