{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XPZZPEHF7IFD2LG6N7M25YCLQ3","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":"0903332e2192e077fd667ca38d1fbfff9a8e1397cb962e06b8641be335698a57","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T06:29:19Z","title_canon_sha256":"c1fa73bd4dbc82b0513bd26198ced5b570f87d2cadd3c13ef4148eee2a503690"},"schema_version":"1.0","source":{"id":"2606.01046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01046","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01046v1","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01046","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"XPZZPEHF7IFD","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"XPZZPEHF7IFD2LG6","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"XPZZPEHF","created_at":"2026-06-02T01:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:26e593bd253b6982b42bfa91d85f365a29d7eb64c06cac5016d7770ca4cf6c74","target":"graph","created_at":"2026-06-02T01:04:19Z","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/2606.01046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations: 1) overemphasis on constraint compliance, neglecting multi-dimensional qualities like spatio-temporal cost; 2) datasets lacking real-world authenticity and coverage in key areas (e.g., lodging, transport); and 3) isolated daily plan assessments that miss critical details (e.g., the impact of daily accommodation and visit pacing) needed for entire plan's evaluation. To address this gap, we introduce TravelEval, a real","authors_text":"Chen Jason Zhang, Kaichun Hu, Lei Chen, Shimin Di, Shuaixiong Wang, Wangze Ni, Weiyi Chen, Ziyun Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T06:29:19Z","title":"TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01046","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:a0596fe854a0fd8baec0f895f4b35a9d464b9af45aa1a83da4b9d826c9df99b9","target":"record","created_at":"2026-06-02T01:04:19Z","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":"0903332e2192e077fd667ca38d1fbfff9a8e1397cb962e06b8641be335698a57","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T06:29:19Z","title_canon_sha256":"c1fa73bd4dbc82b0513bd26198ced5b570f87d2cadd3c13ef4148eee2a503690"},"schema_version":"1.0","source":{"id":"2606.01046","kind":"arxiv","version":1}},"canonical_sha256":"bbf39790e5fa0a3d2cde6fd9aee04b86c0e6e671f4eecac8984421bf25e19fe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbf39790e5fa0a3d2cde6fd9aee04b86c0e6e671f4eecac8984421bf25e19fe5","first_computed_at":"2026-06-02T01:04:19.529683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:19.529683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uMgC07jdkCm+lknhH85M4qxDNW6Jl9yXosuYEB1NQFKjn+/F+9LYbnnbjETci0CRlOanmVsyvlfhhL2LM5bGCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:19.530351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0596fe854a0fd8baec0f895f4b35a9d464b9af45aa1a83da4b9d826c9df99b9","sha256:26e593bd253b6982b42bfa91d85f365a29d7eb64c06cac5016d7770ca4cf6c74"],"state_sha256":"88237ce59fa36d4c893df9f9c388d34b003e7a55bd8999d86adcf9707ba3fdd1"}