{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MYRJS5WUJEITROGSNXDZF6MIBN","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":"29e3c5da16ad9e219cc438271f210717bfbc689554c473914ee0a0655a9e885a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T07:31:04Z","title_canon_sha256":"3128847a9766e66252fde59dc3811dac7269c0ef4fdc4d97bf789581de4b711c"},"schema_version":"1.0","source":{"id":"2606.01815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01815","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01815v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01815","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"MYRJS5WUJEIT","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"MYRJS5WUJEITROGS","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"MYRJS5WU","created_at":"2026-06-02T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:7c31e9a1400f545253a3b9f22117483f72063dcd124e6913da84350084a3a841","target":"graph","created_at":"2026-06-02T02:04:57Z","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/2606.01815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating LLM agents in realistic service scenarios requires complex task dependencies, imperfect user behavior, and an evaluation that accommodates multiple valid solutions. We introduce CRAB-Bench (Constraint-based Realistic Agent Benchmark) and RUSE (Realistic User Simulation Engine) to address this gap. CRAB-Bench generates tasks via a constraint graph over multiple interdependent entities with structured distractors, requiring agents to reason carefully over thousands of misleading candidates where only a tiny fraction of solutions are valid. RUSE replaces cooperative, template-like simu","authors_text":"Akshay Sivaraman, Danqing Wang, Lei Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T07:31:04Z","title":"CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01815","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":"sha256:3f60ba9c259e66b7b801e06cc4894c55a559dacd36bb523297ddbba9575951e6","target":"record","created_at":"2026-06-02T02:04:57Z","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":"29e3c5da16ad9e219cc438271f210717bfbc689554c473914ee0a0655a9e885a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T07:31:04Z","title_canon_sha256":"3128847a9766e66252fde59dc3811dac7269c0ef4fdc4d97bf789581de4b711c"},"schema_version":"1.0","source":{"id":"2606.01815","kind":"arxiv","version":1}},"canonical_sha256":"66229976d4491138b8d26dc792f9880b7b2f1995b035d49a8028c5884ffbc060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66229976d4491138b8d26dc792f9880b7b2f1995b035d49a8028c5884ffbc060","first_computed_at":"2026-06-02T02:04:57.618835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:57.618835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l6pcuFYzO1nWt8oaoV4J1Z0VkuWEThqD8xgvG+Bb+k658YQ9fqSRLLasKTtWkUjZ3PUJ92dPsDlvKLDT7tZ2Dw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:57.619291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f60ba9c259e66b7b801e06cc4894c55a559dacd36bb523297ddbba9575951e6","sha256:7c31e9a1400f545253a3b9f22117483f72063dcd124e6913da84350084a3a841"],"state_sha256":"20649fdbf7e1179960b9773020b2722ef171fe377463de96e250af17b0a7221e"}