{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OWX26JF252HLWIHHODYVP76E2G","short_pith_number":"pith:OWX26JF2","canonical_record":{"source":{"id":"2306.05087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T10:41:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"034adee01f4bb1278e0c0aac6b7831eeb0d87281c9edbee5d86614df97783940","abstract_canon_sha256":"28d43162a32de8211594887c76ed16c7e224f04c0e821a9f78f9484f92330a41"},"schema_version":"1.0"},"canonical_sha256":"75afaf24baee8ebb20e770f157ffc4d1886d7d0e48fb2a168d34368c16964d2d","source":{"kind":"arxiv","id":"2306.05087","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05087","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05087v2","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05087","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"OWX26JF252HL","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"OWX26JF252HLWIHH","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"OWX26JF2","created_at":"2026-07-05T08:22:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OWX26JF252HLWIHHODYVP76E2G","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T10:41:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"034adee01f4bb1278e0c0aac6b7831eeb0d87281c9edbee5d86614df97783940","abstract_canon_sha256":"28d43162a32de8211594887c76ed16c7e224f04c0e821a9f78f9484f92330a41"},"schema_version":"1.0"},"canonical_sha256":"75afaf24baee8ebb20e770f157ffc4d1886d7d0e48fb2a168d34368c16964d2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:31.847767Z","signature_b64":"lLjHtfPReCMKekedJKdxaP6YXB/yejVeX71i6aXTJ5LSGS28M3nJ5a45LiPpuOrApaj2Fxpv/Iny+MrdunGVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75afaf24baee8ebb20e770f157ffc4d1886d7d0e48fb2a168d34368c16964d2d","last_reissued_at":"2026-07-05T08:22:31.847292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:31.847292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05087","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":"2026-07-05T08:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"meM8BTUS9foXPceIqgD8ajYttLPfK3vE3nsX28s6nS7gb93MYB9w0vHGUAIk1O4+ez/LBJfSEX0Ynl22qzmvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:52:04.513856Z"},"content_sha256":"0f15dadcd4940471e32606dbbb2825b0c46c869251aa7dccf1f0ee97ffe003b6","schema_version":"1.0","event_id":"sha256:0f15dadcd4940471e32606dbbb2825b0c46c869251aa7dccf1f0ee97ffe003b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OWX26JF252HLWIHHODYVP76E2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Cunxiang Wang, Hao Chen, Jindong Wang, Linyi Yang, Rui Xie, Shikun Zhang, Wei Ye, Xing Xie, Yidong Wang, Yue Zhang, Zhengran Zeng, Zhuohao Yu","submitted_at":"2023-06-08T10:41:56Z","abstract_excerpt":"Instruction tuning large language models (LLMs) remains a challenging task, owing to the complexity of hyperparameter selection and the difficulty involved in evaluating the tuned models. To determine the optimal hyperparameters, an automatic, robust, and reliable evaluation benchmark is essential. However, establishing such a benchmark is not a trivial task due to the challenges associated with evaluation accuracy and privacy protection. In response to these challenges, we introduce a judge large language model, named PandaLM, which is trained to distinguish the superior model given several L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05087","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/2306.05087/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":"2026-07-05T08:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcSYq1ldRn5rHcedDjK+1Pacx9DSflKr7Q6zyaRngUEeVLdFxvBuDMXkPH3uF4/JSESTEEQbRpyUqjDg76zXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:52:04.514247Z"},"content_sha256":"c8d3e487d3b2af71db4d312a97888ebe16c7071912a1ff8a3bf40f52eaf81e98","schema_version":"1.0","event_id":"sha256:c8d3e487d3b2af71db4d312a97888ebe16c7071912a1ff8a3bf40f52eaf81e98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWX26JF252HLWIHHODYVP76E2G/bundle.json","state_url":"https://pith.science/pith/OWX26JF252HLWIHHODYVP76E2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWX26JF252HLWIHHODYVP76E2G/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":"2026-07-13T00:52:04Z","links":{"resolver":"https://pith.science/pith/OWX26JF252HLWIHHODYVP76E2G","bundle":"https://pith.science/pith/OWX26JF252HLWIHHODYVP76E2G/bundle.json","state":"https://pith.science/pith/OWX26JF252HLWIHHODYVP76E2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWX26JF252HLWIHHODYVP76E2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OWX26JF252HLWIHHODYVP76E2G","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":"28d43162a32de8211594887c76ed16c7e224f04c0e821a9f78f9484f92330a41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T10:41:56Z","title_canon_sha256":"034adee01f4bb1278e0c0aac6b7831eeb0d87281c9edbee5d86614df97783940"},"schema_version":"1.0","source":{"id":"2306.05087","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05087","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05087v2","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05087","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"OWX26JF252HL","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"OWX26JF252HLWIHH","created_at":"2026-07-05T08:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"OWX26JF2","created_at":"2026-07-05T08:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:c8d3e487d3b2af71db4d312a97888ebe16c7071912a1ff8a3bf40f52eaf81e98","target":"graph","created_at":"2026-07-05T08:22:31Z","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/2306.05087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning large language models (LLMs) remains a challenging task, owing to the complexity of hyperparameter selection and the difficulty involved in evaluating the tuned models. To determine the optimal hyperparameters, an automatic, robust, and reliable evaluation benchmark is essential. However, establishing such a benchmark is not a trivial task due to the challenges associated with evaluation accuracy and privacy protection. In response to these challenges, we introduce a judge large language model, named PandaLM, which is trained to distinguish the superior model given several L","authors_text":"Chaoya Jiang, Cunxiang Wang, Hao Chen, Jindong Wang, Linyi Yang, Rui Xie, Shikun Zhang, Wei Ye, Xing Xie, Yidong Wang, Yue Zhang, Zhengran Zeng, Zhuohao Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T10:41:56Z","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05087","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":"sha256:0f15dadcd4940471e32606dbbb2825b0c46c869251aa7dccf1f0ee97ffe003b6","target":"record","created_at":"2026-07-05T08:22:31Z","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":"28d43162a32de8211594887c76ed16c7e224f04c0e821a9f78f9484f92330a41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T10:41:56Z","title_canon_sha256":"034adee01f4bb1278e0c0aac6b7831eeb0d87281c9edbee5d86614df97783940"},"schema_version":"1.0","source":{"id":"2306.05087","kind":"arxiv","version":2}},"canonical_sha256":"75afaf24baee8ebb20e770f157ffc4d1886d7d0e48fb2a168d34368c16964d2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75afaf24baee8ebb20e770f157ffc4d1886d7d0e48fb2a168d34368c16964d2d","first_computed_at":"2026-07-05T08:22:31.847292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:31.847292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLjHtfPReCMKekedJKdxaP6YXB/yejVeX71i6aXTJ5LSGS28M3nJ5a45LiPpuOrApaj2Fxpv/Iny+MrdunGVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:31.847767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05087","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f15dadcd4940471e32606dbbb2825b0c46c869251aa7dccf1f0ee97ffe003b6","sha256:c8d3e487d3b2af71db4d312a97888ebe16c7071912a1ff8a3bf40f52eaf81e98"],"state_sha256":"c560701076b391fa94b25bd196f7c0b85f9301cc352bf3e13a7b50c0a48e9714"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qj9HYv5yXJv+27cu3SpxexhzSMAJ+DVuHNKwJUzbs6C32U36VocJKda4Z2pcTHxN6DJdUrm8c8XY3xiC/rczCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:52:04.517565Z","bundle_sha256":"bbc1f2de25cc4024b7f1cbcce6d702b8bb270f6166dbf2926554df30390f0873"}}