{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7T7T54KFBBBGVP7OMH6RQKBXIT","short_pith_number":"pith:7T7T54KF","schema_version":"1.0","canonical_sha256":"fcff3ef14508426abfee61fd18283744ff3ab3d7cf54b83425004edcf7865615","source":{"kind":"arxiv","id":"2402.13125","version":2},"attestation_state":"computed","paper":{"title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Yang, Xiang Li, Yunshi Lan","submitted_at":"2024-02-20T16:38:33Z","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 "},"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":"2402.13125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:38:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a43fe49d5592ed4168dfed87789227e38be114130a813312aa833e6e63561f1a","abstract_canon_sha256":"157d6d2126e325110aea7549ab34d95c7278c8f4653eef1ef9c324d44cba269a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:31.359991Z","signature_b64":"RN3VfGWeyRxYGzrWyp+9PZFDSr2zKR49yHT1zP/++o2lk3CoHwtkN/C+x4gVF2n/AgfqRGiALeuZWTKpvppkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcff3ef14508426abfee61fd18283744ff3ab3d7cf54b83425004edcf7865615","last_reissued_at":"2026-07-05T09:48:31.359580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:31.359580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Yang, Xiang Li, Yunshi Lan","submitted_at":"2024-02-20T16:38:33Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13125","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/2402.13125/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":"2402.13125","created_at":"2026-07-05T09:48:31.359636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13125v2","created_at":"2026-07-05T09:48:31.359636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13125","created_at":"2026-07-05T09:48:31.359636+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T7T54KFBBBG","created_at":"2026-07-05T09:48:31.359636+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T7T54KFBBBGVP7O","created_at":"2026-07-05T09:48:31.359636+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T7T54KF","created_at":"2026-07-05T09:48:31.359636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT","json":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT.json","graph_json":"https://pith.science/api/pith-number/7T7T54KFBBBGVP7OMH6RQKBXIT/graph.json","events_json":"https://pith.science/api/pith-number/7T7T54KFBBBGVP7OMH6RQKBXIT/events.json","paper":"https://pith.science/paper/7T7T54KF"},"agent_actions":{"view_html":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT","download_json":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT.json","view_paper":"https://pith.science/paper/7T7T54KF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13125&json=true","fetch_graph":"https://pith.science/api/pith-number/7T7T54KFBBBGVP7OMH6RQKBXIT/graph.json","fetch_events":"https://pith.science/api/pith-number/7T7T54KFBBBGVP7OMH6RQKBXIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT/action/storage_attestation","attest_author":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT/action/author_attestation","sign_citation":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT/action/citation_signature","submit_replication":"https://pith.science/pith/7T7T54KFBBBGVP7OMH6RQKBXIT/action/replication_record"}},"created_at":"2026-07-05T09:48:31.359636+00:00","updated_at":"2026-07-05T09:48:31.359636+00:00"}