{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QBWDMAEA2LQWM56EY3R7WMBQP4","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":"ff21f5307e707d61ce6cf5b795c0ffb1331d8b1ac0cd38a8818fc26ca0077b91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T01:42:16Z","title_canon_sha256":"be6344f74d3cbb4cc9d7de299859d39ba57645e4d0495d37d48abc88b4e89bc0"},"schema_version":"1.0","source":{"id":"2310.03249","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03249","created_at":"2026-07-05T10:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03249v3","created_at":"2026-07-05T10:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03249","created_at":"2026-07-05T10:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"QBWDMAEA2LQW","created_at":"2026-07-05T10:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"QBWDMAEA2LQWM56E","created_at":"2026-07-05T10:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"QBWDMAEA","created_at":"2026-07-05T10:18:33Z"}],"graph_snapshots":[{"event_id":"sha256:06130f26bbec1677fe6daf6fc716580e8fbe606ad3ffc3e9734ebec7f4cfd2b5","target":"graph","created_at":"2026-07-05T10:18:33Z","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/2310.03249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success across a wide spectrum of tasks; however, they still face limitations in scenarios that demand long-term planning and spatial reasoning. To facilitate this line of research, in this work, we propose a new benchmark, termed $\\textbf{P}$ath $\\textbf{P}$lanning from $\\textbf{N}$atural $\\textbf{L}$anguage ($\\textbf{PPNL}$). Our benchmark evaluates LLMs' spatial-temporal reasoning by formulating ''path planning'' tasks that require an LLM to navigate to target locations while avoiding obstacles and adhering to constraints. Leveraging thi","authors_text":"Erion Plaku, Mohamed Aghzal, Ziyu Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T01:42:16Z","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03249","kind":"arxiv","version":3},"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:d964cf2facd0798d0f467b3b42fc6516fd050f8059d34b3413e8461e65d6c574","target":"record","created_at":"2026-07-05T10:18:33Z","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":"ff21f5307e707d61ce6cf5b795c0ffb1331d8b1ac0cd38a8818fc26ca0077b91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T01:42:16Z","title_canon_sha256":"be6344f74d3cbb4cc9d7de299859d39ba57645e4d0495d37d48abc88b4e89bc0"},"schema_version":"1.0","source":{"id":"2310.03249","kind":"arxiv","version":3}},"canonical_sha256":"806c360080d2e16677c4c6e3fb30307f1c288fbdf4887145e57ad89bf8c34cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"806c360080d2e16677c4c6e3fb30307f1c288fbdf4887145e57ad89bf8c34cd2","first_computed_at":"2026-07-05T10:18:33.065116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:33.065116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hu2X+Sn08oz9ijpLFLzZsNiAmUp2aTyiLAl5BOHMXf7NjnXtpAW3t7eiI+skXR0rt6ydZWl7ArDhYWAcaULlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:33.065572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03249","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d964cf2facd0798d0f467b3b42fc6516fd050f8059d34b3413e8461e65d6c574","sha256:06130f26bbec1677fe6daf6fc716580e8fbe606ad3ffc3e9734ebec7f4cfd2b5"],"state_sha256":"b668ced9e4c11ccdcdeac0a6f7d16ce2c116b8d9befc9be72eee0016c9fedf41"}