{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YFKQINBL6766OAZCNUB3UHORLE","short_pith_number":"pith:YFKQINBL","canonical_record":{"source":{"id":"2305.01937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T07:28:50Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ff53edb56af6081336386260d993753caa9f25c3a22676bf4f576f397dff7a05","abstract_canon_sha256":"559411a704d265404e2ad0cf128a04f7d4d764b9ec160dd61215b904c64e5507"},"schema_version":"1.0"},"canonical_sha256":"c15504342bf7fde703226d03ba1dd15901fff1b0d440f44a497dec68684ce015","source":{"kind":"arxiv","id":"2305.01937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01937","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01937v1","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01937","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"YFKQINBL6766","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"YFKQINBL6766OAZC","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"YFKQINBL","created_at":"2026-07-05T06:06:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YFKQINBL6766OAZCNUB3UHORLE","target":"record","payload":{"canonical_record":{"source":{"id":"2305.01937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T07:28:50Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ff53edb56af6081336386260d993753caa9f25c3a22676bf4f576f397dff7a05","abstract_canon_sha256":"559411a704d265404e2ad0cf128a04f7d4d764b9ec160dd61215b904c64e5507"},"schema_version":"1.0"},"canonical_sha256":"c15504342bf7fde703226d03ba1dd15901fff1b0d440f44a497dec68684ce015","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:45.720835Z","signature_b64":"maG3BeeagTM8pv/CK/tSycvmvIXbddkcR2iyLobMzVJVAXl9ocezhlBmm92v0VMvHcBjIDOm0H7QivwtZciGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15504342bf7fde703226d03ba1dd15901fff1b0d440f44a497dec68684ce015","last_reissued_at":"2026-07-05T06:06:45.720355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:45.720355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.01937","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLaIoT4zpUIkOjhRqD6XbKHSW9qNW2Qm6quVC3gDgK4ywNh22gak49dMkWGuoG0ja9CwEGVO8ZCAwALu9i4aDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:46:30.478794Z"},"content_sha256":"b47bb1f1bc16ab0940eec6e22a8cce289c715ba7b199f0fe549ed99c40d7ac9d","schema_version":"1.0","event_id":"sha256:b47bb1f1bc16ab0940eec6e22a8cce289c715ba7b199f0fe549ed99c40d7ac9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YFKQINBL6766OAZCNUB3UHORLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Large Language Models Be an Alternative to Human Evaluations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Cheng-Han Chiang, Hung-yi Lee","submitted_at":"2023-05-03T07:28:50Z","abstract_excerpt":"Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable, hindering fair comparisons among different natural language processing (NLP) models and algorithms. Recently, large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided. In this paper, we explore if such an ability of the LLMs can be used as an alternative to human evaluation. We prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01937","kind":"arxiv","version":1},"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/2305.01937/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":"2026-07-05T06:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AStav2+1TzYW1rJMJxlyKXsQw/83sQ2JCQyw8vbpcAhTFRwT1vrrfRUnxh0rP+rVYubGqEEt0WGH1+zJTDczDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:46:30.479318Z"},"content_sha256":"f43667ef5933e4c5d28f29ef925e4c756ab26bdba700b9fe2559a5945306f390","schema_version":"1.0","event_id":"sha256:f43667ef5933e4c5d28f29ef925e4c756ab26bdba700b9fe2559a5945306f390"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFKQINBL6766OAZCNUB3UHORLE/bundle.json","state_url":"https://pith.science/pith/YFKQINBL6766OAZCNUB3UHORLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFKQINBL6766OAZCNUB3UHORLE/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":"2026-08-03T15:46:30Z","links":{"resolver":"https://pith.science/pith/YFKQINBL6766OAZCNUB3UHORLE","bundle":"https://pith.science/pith/YFKQINBL6766OAZCNUB3UHORLE/bundle.json","state":"https://pith.science/pith/YFKQINBL6766OAZCNUB3UHORLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFKQINBL6766OAZCNUB3UHORLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YFKQINBL6766OAZCNUB3UHORLE","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":"559411a704d265404e2ad0cf128a04f7d4d764b9ec160dd61215b904c64e5507","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T07:28:50Z","title_canon_sha256":"ff53edb56af6081336386260d993753caa9f25c3a22676bf4f576f397dff7a05"},"schema_version":"1.0","source":{"id":"2305.01937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01937","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01937v1","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01937","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"YFKQINBL6766","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"YFKQINBL6766OAZC","created_at":"2026-07-05T06:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"YFKQINBL","created_at":"2026-07-05T06:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:f43667ef5933e4c5d28f29ef925e4c756ab26bdba700b9fe2559a5945306f390","target":"graph","created_at":"2026-07-05T06:06:45Z","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/2305.01937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable, hindering fair comparisons among different natural language processing (NLP) models and algorithms. Recently, large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided. In this paper, we explore if such an ability of the LLMs can be used as an alternative to human evaluation. We prese","authors_text":"Cheng-Han Chiang, Hung-yi Lee","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T07:28:50Z","title":"Can Large Language Models Be an Alternative to Human Evaluations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01937","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:b47bb1f1bc16ab0940eec6e22a8cce289c715ba7b199f0fe549ed99c40d7ac9d","target":"record","created_at":"2026-07-05T06:06:45Z","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":"559411a704d265404e2ad0cf128a04f7d4d764b9ec160dd61215b904c64e5507","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T07:28:50Z","title_canon_sha256":"ff53edb56af6081336386260d993753caa9f25c3a22676bf4f576f397dff7a05"},"schema_version":"1.0","source":{"id":"2305.01937","kind":"arxiv","version":1}},"canonical_sha256":"c15504342bf7fde703226d03ba1dd15901fff1b0d440f44a497dec68684ce015","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c15504342bf7fde703226d03ba1dd15901fff1b0d440f44a497dec68684ce015","first_computed_at":"2026-07-05T06:06:45.720355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:06:45.720355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"maG3BeeagTM8pv/CK/tSycvmvIXbddkcR2iyLobMzVJVAXl9ocezhlBmm92v0VMvHcBjIDOm0H7QivwtZciGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:06:45.720835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b47bb1f1bc16ab0940eec6e22a8cce289c715ba7b199f0fe549ed99c40d7ac9d","sha256:f43667ef5933e4c5d28f29ef925e4c756ab26bdba700b9fe2559a5945306f390"],"state_sha256":"99a454cf4b889d055856957f980f68fc6b1110f2a864f948a4da5f73a60ac6ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMbtrzr0EfA5yJeb4qIvw1UOSOO34J2tMHH8aAKvG6X8spo2+ta/AaGmXmM3x2FzSHMQhDllWZ/nHrutgtN4CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:46:30.486284Z","bundle_sha256":"045391ae570bd0e2604b688ca818b6a5ad8749619acecdb1914343f34a38b80e"}}