{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7T7T54KFBBBGVP7OMH6RQKBXIT","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":"157d6d2126e325110aea7549ab34d95c7278c8f4653eef1ef9c324d44cba269a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:38:33Z","title_canon_sha256":"a43fe49d5592ed4168dfed87789227e38be114130a813312aa833e6e63561f1a"},"schema_version":"1.0","source":{"id":"2402.13125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13125","created_at":"2026-07-05T09:48:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13125v2","created_at":"2026-07-05T09:48:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13125","created_at":"2026-07-05T09:48:31Z"},{"alias_kind":"pith_short_12","alias_value":"7T7T54KFBBBG","created_at":"2026-07-05T09:48:31Z"},{"alias_kind":"pith_short_16","alias_value":"7T7T54KFBBBGVP7O","created_at":"2026-07-05T09:48:31Z"},{"alias_kind":"pith_short_8","alias_value":"7T7T54KF","created_at":"2026-07-05T09:48:31Z"}],"graph_snapshots":[{"event_id":"sha256:fddb44634f8f2605019ad854bc119e952eee6a7853fcd245fc0c1519a14d06a0","target":"graph","created_at":"2026-07-05T09:48:31Z","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/2402.13125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge. However, these approaches suffer from data leakage due to the open access of the benchmark and inflexible evaluation process. To address this issue, we introduce $\\textbf{TreeEval}$, a benchmark-free evaluation method for LLMs that let a high-performance LLM host an irreproducible evaluation session and essentially avoids the data leakage. Moreover, this LLM performs as an examiner to raise up a series of ","authors_text":"Chao Yang, Xiang Li, Yunshi Lan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:38:33Z","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13125","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":"sha256:160e5edff652a76d511a6790d7fa2798d6d49b224a9f3797c5b28539feed4676","target":"record","created_at":"2026-07-05T09:48:31Z","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":"157d6d2126e325110aea7549ab34d95c7278c8f4653eef1ef9c324d44cba269a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:38:33Z","title_canon_sha256":"a43fe49d5592ed4168dfed87789227e38be114130a813312aa833e6e63561f1a"},"schema_version":"1.0","source":{"id":"2402.13125","kind":"arxiv","version":2}},"canonical_sha256":"fcff3ef14508426abfee61fd18283744ff3ab3d7cf54b83425004edcf7865615","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcff3ef14508426abfee61fd18283744ff3ab3d7cf54b83425004edcf7865615","first_computed_at":"2026-07-05T09:48:31.359580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:31.359580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RN3VfGWeyRxYGzrWyp+9PZFDSr2zKR49yHT1zP/++o2lk3CoHwtkN/C+x4gVF2n/AgfqRGiALeuZWTKpvppkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:31.359991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:160e5edff652a76d511a6790d7fa2798d6d49b224a9f3797c5b28539feed4676","sha256:fddb44634f8f2605019ad854bc119e952eee6a7853fcd245fc0c1519a14d06a0"],"state_sha256":"aa0e2fb3b4d9e669988a866e80758c69df56df870d38f57336c53ef2e3b25178"}