{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FRWCXIOKPMAY53MJ5ZB4VXG4Z6","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":"d89f7b43d36536f443a1424db0a90f433745fac953244f0cf78061e9d4342a02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T08:48:15Z","title_canon_sha256":"910bc52ca800fdd9b41a0c32566b5ad5c61ce3628e311f37e000cc515ca1ba68"},"schema_version":"1.0","source":{"id":"2606.01912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01912","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01912v1","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01912","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"FRWCXIOKPMAY","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"FRWCXIOKPMAY53MJ","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"FRWCXIOK","created_at":"2026-06-02T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:d5976e0a80a9313e37a439bc6a424bbe4f6dfb69b630c3ad343a3c20cd45fefc","target":"graph","created_at":"2026-06-02T02:05:00Z","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/2606.01912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferences, and multi-device interactions. However, existing smart-home benchmarks often focus on static instruction-to-API mapping or limited simulations, failing to evaluate whether LLMs can reason, interact, and act reliably in realistic household scenarios. To address these limitations, we introduce SMH-Bench, a comprehensive benchmark for evaluating LLMs in smart-home environments. Built upon HomeEnv, an executable and verifiable smart-home simul","authors_text":"Chen Liu, Fangzhou Yu, Huacan Wang, Kuan Li, Lei Xue, Ronghao Chen, Sen Hu, Shuo Zhang, Siyue Lin, Weipeng Ming, Xiaofeng Mou, Yi Gu, Yi Xu, Yuqing Hou, Zecheng Sheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T08:48:15Z","title":"SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01912","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":"sha256:047109da1c46296c3432dd2e8e8ae55464bedf66bdc94c41a88494f02009f7f3","target":"record","created_at":"2026-06-02T02:05:00Z","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":"d89f7b43d36536f443a1424db0a90f433745fac953244f0cf78061e9d4342a02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T08:48:15Z","title_canon_sha256":"910bc52ca800fdd9b41a0c32566b5ad5c61ce3628e311f37e000cc515ca1ba68"},"schema_version":"1.0","source":{"id":"2606.01912","kind":"arxiv","version":1}},"canonical_sha256":"2c6c2ba1ca7b018eed89ee43cadcdccf955b57797fb633ffbbb588db78057ae5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6c2ba1ca7b018eed89ee43cadcdccf955b57797fb633ffbbb588db78057ae5","first_computed_at":"2026-06-02T02:05:00.293833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:00.293833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Zuhv/A4NWwlcFb3QeoMbgx2fIPNahj2Xd0HmK2hripjmIEWMUPbrHAYdcPnouWm1kqyWupJEyanhu85nAw8DA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:00.294224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:047109da1c46296c3432dd2e8e8ae55464bedf66bdc94c41a88494f02009f7f3","sha256:d5976e0a80a9313e37a439bc6a424bbe4f6dfb69b630c3ad343a3c20cd45fefc"],"state_sha256":"b6e022d928056c90a4b591f4911d56e3e871a989343aa4e686fb2a7141fc99c4"}