{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZXVUILDWP2R6BTQKPAJ4DAVQMJ","short_pith_number":"pith:ZXVUILDW","schema_version":"1.0","canonical_sha256":"cdeb442c767ea3e0ce0a7813c182b0626fb0e36969fc8fe849dd0ddc5794aa1b","source":{"kind":"arxiv","id":"2605.18548","version":1},"attestation_state":"computed","paper":{"title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kun Zhan, Ning Miao, Pengyu Zhu, Sen Su, Tingfeng Hui","submitted_at":"2026-05-18T15:27:52Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.18548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T15:27:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d821bfad4e6e7c93dde8f054aa5497f452b8c0a8aaf84e87273d5d4d2948a84","abstract_canon_sha256":"fe7f523957413bdfcb8017c200ce1d89b6ac6f386a38dab51b89ae9811003b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:07.152814Z","signature_b64":"AakmFU22W9KLjtbz9/Z+psMFo7rRjDZn75PmHz8f8LA4w73A6Wq8fpPfB/D7kvfnFE/ngvhSh/J73gCJHZI2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdeb442c767ea3e0ce0a7813c182b0626fb0e36969fc8fe849dd0ddc5794aa1b","last_reissued_at":"2026-05-20T00:06:07.151992Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:07.151992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunxiao Liu, Hao Xu, Hongsheng Xin, Kun Zhan, Ning Miao, Pengyu Zhu, Sen Su, Tingfeng Hui","submitted_at":"2026-05-18T15:27:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18548","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18548/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.18548","created_at":"2026-05-20T00:06:07.152140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18548v1","created_at":"2026-05-20T00:06:07.152140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18548","created_at":"2026-05-20T00:06:07.152140+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXVUILDWP2R6","created_at":"2026-05-20T00:06:07.152140+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXVUILDWP2R6BTQK","created_at":"2026-05-20T00:06:07.152140+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXVUILDW","created_at":"2026-05-20T00:06:07.152140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ","json":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ.json","graph_json":"https://pith.science/api/pith-number/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/graph.json","events_json":"https://pith.science/api/pith-number/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/events.json","paper":"https://pith.science/paper/ZXVUILDW"},"agent_actions":{"view_html":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ","download_json":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ.json","view_paper":"https://pith.science/paper/ZXVUILDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18548&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZXVUILDWP2R6BTQKPAJ4DAVQMJ/action/replication_record"}},"created_at":"2026-05-20T00:06:07.152140+00:00","updated_at":"2026-05-20T00:06:07.152140+00:00"}