{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4JYVJR2ORS3C2R2QWCESVGVAC4","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":"5e83de5b5b66d17f3c9d1f267dbbd9546f467e77ce702cf3dab722de29baaa1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T13:26:14Z","title_canon_sha256":"8b426f8841baf91aa977ff474d66808ae6a81a34729df3beaab8c328db010246"},"schema_version":"1.0","source":{"id":"2605.18380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18380","created_at":"2026-05-20T00:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18380v1","created_at":"2026-05-20T00:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18380","created_at":"2026-05-20T00:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"4JYVJR2ORS3C","created_at":"2026-05-20T00:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"4JYVJR2ORS3C2R2Q","created_at":"2026-05-20T00:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"4JYVJR2O","created_at":"2026-05-20T00:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:f7923e919bf8d87a88e836c6d995f88312c3c2c88803ff24c15a8bd45163f31d","target":"graph","created_at":"2026-05-20T00:05:58Z","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":[{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T23:50:04.476501Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.998439Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T23:31:47.113943Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.760952Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18380/integrity.json","findings":[],"snapshot_sha256":"d922268edbb6c9467fb8c533ede938a98f0c6519277cd99d2ca3d19af12b37b7","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce an extensive qualitative spatial and temporal reasoning (QSTR) benchmark for evaluating large language models (LLMs). We pose questions concerning compositional reasoning (using composition tables, CT), converse relations, and conceptual neighbourhoods (CN) for QSTR calculi, Point Algebra (PA), Allen's Interval Algebra, Interval and Duration (INDU), Region Connection Calculus (RCC-5, RCC-8, and RCC-22), the nine intersection model, cardinal direction calculus, and STAR. The RCC-22 CN is published here for the first time. An extended benchmark systematically varies question present","authors_text":"Anthony G. Cohn, Robert E. Blackwell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T13:26:14Z","title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18380","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":"sha256:167d51ddae6fd7e96ad4c836957372c6de79ec604e0db3b6bb0fbb9ebe38f85b","target":"record","created_at":"2026-05-20T00:05:58Z","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":"5e83de5b5b66d17f3c9d1f267dbbd9546f467e77ce702cf3dab722de29baaa1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T13:26:14Z","title_canon_sha256":"8b426f8841baf91aa977ff474d66808ae6a81a34729df3beaab8c328db010246"},"schema_version":"1.0","source":{"id":"2605.18380","kind":"arxiv","version":1}},"canonical_sha256":"e27154c74e8cb62d4750b0892a9aa0170a9af4c677bfe2d7bfd0538d15b01882","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e27154c74e8cb62d4750b0892a9aa0170a9af4c677bfe2d7bfd0538d15b01882","first_computed_at":"2026-05-20T00:05:58.007572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:58.007572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wA/dK+y1QqJfA/3+llnyM3QG7kLhrWrVG78gfpP1zqGDk88WDAK2OKdWEHfECjgs5QDzSb5w64Ms7E/i6mj/Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:58.008431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:167d51ddae6fd7e96ad4c836957372c6de79ec604e0db3b6bb0fbb9ebe38f85b","sha256:f7923e919bf8d87a88e836c6d995f88312c3c2c88803ff24c15a8bd45163f31d"],"state_sha256":"725cd0124ccc4400abbf61584f681eaa4273919bb34b5b00acd7fc5dcd037d4e"}