{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T6UXLZHDGTWI3HI42B2GH6SFHR","short_pith_number":"pith:T6UXLZHD","canonical_record":{"source":{"id":"2310.05657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb","abstract_canon_sha256":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f"},"schema_version":"1.0"},"canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","source":{"kind":"arxiv","id":"2310.05657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05657v1","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"T6UXLZHDGTWI","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"T6UXLZHDGTWI3HI4","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"T6UXLZHD","created_at":"2026-07-05T06:58:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T6UXLZHDGTWI3HI42B2GH6SFHR","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb","abstract_canon_sha256":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f"},"schema_version":"1.0"},"canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:48.165472Z","signature_b64":"HEPKEkIjmLluoHVToa4+iCGgwbxWVvAgsgVZAXmruBtj3euuOa6RM8unCKq9zg9Yt0l0CWcGCBZiqlMuN30rBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","last_reissued_at":"2026-07-05T06:58:48.164986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:48.164986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05657","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":"2026-07-05T06:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9idvmyAIg3TQo3Un0g3Yuuvow+cU28clCTqNKPrrWga7kW0pyUjOO0Epi5yklK41Sm2kkVOvCh0595MIbuC6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:55.697861Z"},"content_sha256":"3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5","schema_version":"1.0","event_id":"sha256:3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T6UXLZHDGTWI3HI42B2GH6SFHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look into Automatic Evaluation Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Han Chiang, Hung-yi Lee","submitted_at":"2023-10-09T12:12:55Z","abstract_excerpt":"Using large language models (LLMs) to evaluate text quality has recently gained popularity. Some prior works explore the idea of using LLMs for evaluation, while they differ in some details of the evaluation process. In this paper, we analyze LLM evaluation (Chiang and Lee, 2023) and G-Eval (Liu et al., 2023), and we discuss how those details in the evaluation process change how well the ratings given by LLMs correlate with human ratings. We find that the auto Chain-of-Thought (CoT) used in G-Eval does not always make G-Eval more aligned with human ratings. We also show that forcing the LLM to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05657","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/2310.05657/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":"2026-07-05T06:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXyeiUkFeQScpTkrFCYrQ8RKBaaBzGCbsmYpnQu9GrbRFZqLY8oKH2rEdRmVhVyJGqKw7+6SMeoyJuh95A7pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:55.698354Z"},"content_sha256":"99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7","schema_version":"1.0","event_id":"sha256:99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/bundle.json","state_url":"https://pith.science/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/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":"2026-08-08T16:17:55Z","links":{"resolver":"https://pith.science/pith/T6UXLZHDGTWI3HI42B2GH6SFHR","bundle":"https://pith.science/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/bundle.json","state":"https://pith.science/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6UXLZHDGTWI3HI42B2GH6SFHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T6UXLZHDGTWI3HI42B2GH6SFHR","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":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb"},"schema_version":"1.0","source":{"id":"2310.05657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05657v1","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"T6UXLZHDGTWI","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"T6UXLZHDGTWI3HI4","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"T6UXLZHD","created_at":"2026-07-05T06:58:48Z"}],"graph_snapshots":[{"event_id":"sha256:99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7","target":"graph","created_at":"2026-07-05T06:58:48Z","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/2310.05657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using large language models (LLMs) to evaluate text quality has recently gained popularity. Some prior works explore the idea of using LLMs for evaluation, while they differ in some details of the evaluation process. In this paper, we analyze LLM evaluation (Chiang and Lee, 2023) and G-Eval (Liu et al., 2023), and we discuss how those details in the evaluation process change how well the ratings given by LLMs correlate with human ratings. We find that the auto Chain-of-Thought (CoT) used in G-Eval does not always make G-Eval more aligned with human ratings. We also show that forcing the LLM to","authors_text":"Cheng-Han Chiang, Hung-yi Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title":"A Closer Look into Automatic Evaluation Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05657","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":"sha256:3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5","target":"record","created_at":"2026-07-05T06:58:48Z","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":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb"},"schema_version":"1.0","source":{"id":"2310.05657","kind":"arxiv","version":1}},"canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","first_computed_at":"2026-07-05T06:58:48.164986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:48.164986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HEPKEkIjmLluoHVToa4+iCGgwbxWVvAgsgVZAXmruBtj3euuOa6RM8unCKq9zg9Yt0l0CWcGCBZiqlMuN30rBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:48.165472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5","sha256:99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7"],"state_sha256":"5c144ed56d266368eff2f792a43de5601f76d3c3c9dde4cca96f6a02267e99f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1i11ORXUcRJHo6AaVLdm8wF28Ej/m09GVc2hiFlPjImNXB7pnbhSQk6oWsOjWWEK+s9gUlSyKhct1MfYTCqRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:17:55.703072Z","bundle_sha256":"87292305272b1910c902b9c6c46d085586d8f076d0dbecec43ca264c2cc96b78"}}