{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZXVUILDWP2R6BTQKPAJ4DAVQMJ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe7f523957413bdfcb8017c200ce1d89b6ac6f386a38dab51b89ae9811003b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T15:27:52Z","title_canon_sha256":"8d821bfad4e6e7c93dde8f054aa5497f452b8c0a8aaf84e87273d5d4d2948a84"},"schema_version":"1.0","source":{"id":"2605.18548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18548","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18548v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18548","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZXVUILDWP2R6","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZXVUILDWP2R6BTQK","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZXVUILDW","created_at":"2026-05-20T00:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:1b9f95cae60b51a28245f5806a1d58b453eda769f730261b8dff3d64a885bbca","target":"graph","created_at":"2026-05-20T00:06:07Z","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/2605.18548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kun Zhan, Ning Miao, Pengyu Zhu, Sen Su, Tingfeng Hui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T15:27:52Z","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18548","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":"sha256:906f6c083fb914e11181254940018d6948beaab82ef658fb3084cde7fea76e16","target":"record","created_at":"2026-05-20T00:06:07Z","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":"fe7f523957413bdfcb8017c200ce1d89b6ac6f386a38dab51b89ae9811003b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T15:27:52Z","title_canon_sha256":"8d821bfad4e6e7c93dde8f054aa5497f452b8c0a8aaf84e87273d5d4d2948a84"},"schema_version":"1.0","source":{"id":"2605.18548","kind":"arxiv","version":1}},"canonical_sha256":"cdeb442c767ea3e0ce0a7813c182b0626fb0e36969fc8fe849dd0ddc5794aa1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdeb442c767ea3e0ce0a7813c182b0626fb0e36969fc8fe849dd0ddc5794aa1b","first_computed_at":"2026-05-20T00:06:07.151992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:07.151992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AakmFU22W9KLjtbz9/Z+psMFo7rRjDZn75PmHz8f8LA4w73A6Wq8fpPfB/D7kvfnFE/ngvhSh/J73gCJHZI2DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:07.152814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:906f6c083fb914e11181254940018d6948beaab82ef658fb3084cde7fea76e16","sha256:1b9f95cae60b51a28245f5806a1d58b453eda769f730261b8dff3d64a885bbca","sha256:2b8826039e46798ff497a682de8aa24de641c56c33092d4da59cf179b89b2b7f"],"state_sha256":"4d7663ec15e17d8164f8a63ef25f314054735b2aa9b9514258e74985e503695b"}