{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QLTVUHNXJQSN3SGJD7AJ64F7IR","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":"f1403f0f18eb17db9d7d50d5172f51d01937a430bf3f6fbfaab7c8c0f64bbb71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-27T19:33:45Z","title_canon_sha256":"cebb27bb8b0b129e09e16765fddf6dec9bd5711400244bcc8f275a7a346df2e5"},"schema_version":"1.0","source":{"id":"2507.20395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20395","created_at":"2026-07-05T11:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20395v1","created_at":"2026-07-05T11:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20395","created_at":"2026-07-05T11:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"QLTVUHNXJQSN","created_at":"2026-07-05T11:44:18Z"},{"alias_kind":"pith_short_16","alias_value":"QLTVUHNXJQSN3SGJ","created_at":"2026-07-05T11:44:18Z"},{"alias_kind":"pith_short_8","alias_value":"QLTVUHNX","created_at":"2026-07-05T11:44:18Z"}],"graph_snapshots":[{"event_id":"sha256:0cfdbe511d4ee117e92ed4f4f857c64ce32d3672e3ab938fe0012b573955355e","target":"graph","created_at":"2026-07-05T11:44:18Z","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/2507.20395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) increasingly power autonomous agents in robotics and embodied AI, understanding their spatial reasoning capabilities becomes crucial for ensuring reliable real-world deployment. Despite advances in language understanding, current research lacks evaluation of how LLMs perform spatial navigation without visual cues, a fundamental requirement for agents operating with limited sensory information. This paper addresses this gap by introducing MazeEval, a benchmark designed to isolate and evaluate pure spatial reasoning in LLMs through coordinate-based maze navigation","authors_text":"Hafsteinn Einarsson","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-27T19:33:45Z","title":"MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20395","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":"sha256:97a71250f89f6fb3dc613af41c2db5e4b67a315f9f436c1b8bf68ad3651e16a7","target":"record","created_at":"2026-07-05T11:44:18Z","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":"f1403f0f18eb17db9d7d50d5172f51d01937a430bf3f6fbfaab7c8c0f64bbb71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-27T19:33:45Z","title_canon_sha256":"cebb27bb8b0b129e09e16765fddf6dec9bd5711400244bcc8f275a7a346df2e5"},"schema_version":"1.0","source":{"id":"2507.20395","kind":"arxiv","version":1}},"canonical_sha256":"82e75a1db74c24ddc8c91fc09f70bf44708f105ea3bbcc694a37b67e9e2e6911","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82e75a1db74c24ddc8c91fc09f70bf44708f105ea3bbcc694a37b67e9e2e6911","first_computed_at":"2026-07-05T11:44:18.531708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:18.531708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D274oUImpAoJ3Zp619at/GfccOOdu4in2ax8U8J/8CJVzbkZH5ZxERDpag88/OJRgd0gCVlSOOj69m99S+ZxAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:18.532163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97a71250f89f6fb3dc613af41c2db5e4b67a315f9f436c1b8bf68ad3651e16a7","sha256:0cfdbe511d4ee117e92ed4f4f857c64ce32d3672e3ab938fe0012b573955355e"],"state_sha256":"5b108302b2dd7a92ca203302833d2de8144d63c6a15a1f5e1b5fb92c3a2c6092"}