{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OKDF3QSDWNDDCP2Q4FZGZ5GB4K","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":"cf28a323daea167d2e2b2ab9b6cb4e758adad0bf8d4901cf008c6c811e0224fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T07:37:12Z","title_canon_sha256":"d580c6197ebd646d7463ff1790b0d7539e4dc72f6379ce7699f2f31d44250f6b"},"schema_version":"1.0","source":{"id":"2508.11280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11280","created_at":"2026-07-05T11:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11280v2","created_at":"2026-07-05T11:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11280","created_at":"2026-07-05T11:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"OKDF3QSDWNDD","created_at":"2026-07-05T11:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"OKDF3QSDWNDDCP2Q","created_at":"2026-07-05T11:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"OKDF3QSD","created_at":"2026-07-05T11:58:35Z"}],"graph_snapshots":[{"event_id":"sha256:8aef6a889f45b89e9cb934417ee28dffdf9017cc28ce6e1c7c4408f22a8edc30","target":"graph","created_at":"2026-07-05T11:58:35Z","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/2508.11280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) in specific domain like tourism remains challenging due to the prohibitive cost of annotated benchmarks and persistent issues like hallucinations. We propose $\\textbf{L}$able-Free $\\textbf{E}$valuation of LLM on $\\textbf{T}$ourism using Expert $\\textbf{T}$ree-$\\textbf{o}$f-$\\textbf{T}$hought (LETToT), a framework that leverages expert-derived reasoning structures-instead of labeled data-to access LLMs in tourism. First, we iteratively refine and validate hierarchical ToT components through alignment with generic quality dimensions and expert feedback. Re","authors_text":"Congding Wen, Jiwei Li, Lingbo Li, Ruiyan Qi, Shangsong Liang, Weibo Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T07:37:12Z","title":"LETToT: Label-Free Evaluation of Large Language Models On Tourism Using Expert Tree-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11280","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":"sha256:2359001ddcaa8300c119a330dfecd437a77878382c2b399500acf70d54144116","target":"record","created_at":"2026-07-05T11:58:35Z","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":"cf28a323daea167d2e2b2ab9b6cb4e758adad0bf8d4901cf008c6c811e0224fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T07:37:12Z","title_canon_sha256":"d580c6197ebd646d7463ff1790b0d7539e4dc72f6379ce7699f2f31d44250f6b"},"schema_version":"1.0","source":{"id":"2508.11280","kind":"arxiv","version":2}},"canonical_sha256":"72865dc243b346313f50e1726cf4c1e2a1faba42d1787c8fdfd2f02d54903943","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72865dc243b346313f50e1726cf4c1e2a1faba42d1787c8fdfd2f02d54903943","first_computed_at":"2026-07-05T11:58:35.011900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:35.011900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NKRWs6WIqyVgczf6FdNg/hsPPKL1Ta2fvUNEQ5AIbsUHTaKxiaBozn5TlJiWd/n/8ZP9ETcsus1IE/S4fQoLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:35.012343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2359001ddcaa8300c119a330dfecd437a77878382c2b399500acf70d54144116","sha256:8aef6a889f45b89e9cb934417ee28dffdf9017cc28ce6e1c7c4408f22a8edc30"],"state_sha256":"847b1e71d904fce765c04ebaf076fc0a943cbd89bf24b0b64c7bf0db2d6478a1"}