{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J5W6YDIOSLDHLX4QRB32GOPBOW","short_pith_number":"pith:J5W6YDIO","schema_version":"1.0","canonical_sha256":"4f6dec0d0e92c675df908877a339e175acfc33509a146fdad1b13f27d9947ff3","source":{"kind":"arxiv","id":"2305.14658","version":3},"attestation_state":"computed","paper":{"title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daling Wang, Hinrich Sch\\\"utze, Shi Feng, Yifei Zhang, Yongkang Liu","submitted_at":"2023-05-24T02:52:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.14658","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"4b0df74081f192c85e558e20c1ba8adb0bdff27e93804236b5d01b3662c2b3de","abstract_canon_sha256":"c875a87873b7add18f45e92d57af8ee79f8f09997db03c5c2aa7ffd877371c6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:36.125512Z","signature_b64":"f54BnPpdfsKZChPw0Mwy42AT2H6F0q/VyEM5wOrYD5Nb+R2Aa4+u1LRbTK4Oq6nsGZMC4jx2a3piO3ZwJ83HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f6dec0d0e92c675df908877a339e175acfc33509a146fdad1b13f27d9947ff3","last_reissued_at":"2026-07-05T08:15:36.125035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:36.125035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daling Wang, Hinrich Sch\\\"utze, Shi Feng, Yifei Zhang, Yongkang Liu","submitted_at":"2023-05-24T02:52:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14658","kind":"arxiv","version":3},"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/2305.14658/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.14658","created_at":"2026-07-05T08:15:36.125095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14658v3","created_at":"2026-07-05T08:15:36.125095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14658","created_at":"2026-07-05T08:15:36.125095+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5W6YDIOSLDH","created_at":"2026-07-05T08:15:36.125095+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5W6YDIOSLDHLX4Q","created_at":"2026-07-05T08:15:36.125095+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5W6YDIO","created_at":"2026-07-05T08:15:36.125095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18416","citing_title":"Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles","ref_index":8939,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW","json":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW.json","graph_json":"https://pith.science/api/pith-number/J5W6YDIOSLDHLX4QRB32GOPBOW/graph.json","events_json":"https://pith.science/api/pith-number/J5W6YDIOSLDHLX4QRB32GOPBOW/events.json","paper":"https://pith.science/paper/J5W6YDIO"},"agent_actions":{"view_html":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW","download_json":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW.json","view_paper":"https://pith.science/paper/J5W6YDIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14658&json=true","fetch_graph":"https://pith.science/api/pith-number/J5W6YDIOSLDHLX4QRB32GOPBOW/graph.json","fetch_events":"https://pith.science/api/pith-number/J5W6YDIOSLDHLX4QRB32GOPBOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW/action/storage_attestation","attest_author":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW/action/author_attestation","sign_citation":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW/action/citation_signature","submit_replication":"https://pith.science/pith/J5W6YDIOSLDHLX4QRB32GOPBOW/action/replication_record"}},"created_at":"2026-07-05T08:15:36.125095+00:00","updated_at":"2026-07-05T08:15:36.125095+00:00"}