{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QBWDMAEA2LQWM56EY3R7WMBQP4","short_pith_number":"pith:QBWDMAEA","canonical_record":{"source":{"id":"2310.03249","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T01:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"be6344f74d3cbb4cc9d7de299859d39ba57645e4d0495d37d48abc88b4e89bc0","abstract_canon_sha256":"ff21f5307e707d61ce6cf5b795c0ffb1331d8b1ac0cd38a8818fc26ca0077b91"},"schema_version":"1.0"},"canonical_sha256":"806c360080d2e16677c4c6e3fb30307f1c288fbdf4887145e57ad89bf8c34cd2","source":{"kind":"arxiv","id":"2310.03249","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QBWDMAEA2LQWM56EY3R7WMBQP4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03249","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T01:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"be6344f74d3cbb4cc9d7de299859d39ba57645e4d0495d37d48abc88b4e89bc0","abstract_canon_sha256":"ff21f5307e707d61ce6cf5b795c0ffb1331d8b1ac0cd38a8818fc26ca0077b91"},"schema_version":"1.0"},"canonical_sha256":"806c360080d2e16677c4c6e3fb30307f1c288fbdf4887145e57ad89bf8c34cd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:33.065572Z","signature_b64":"hu2X+Sn08oz9ijpLFLzZsNiAmUp2aTyiLAl5BOHMXf7NjnXtpAW3t7eiI+skXR0rt6ydZWl7ArDhYWAcaULlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"806c360080d2e16677c4c6e3fb30307f1c288fbdf4887145e57ad89bf8c34cd2","last_reissued_at":"2026-07-05T10:18:33.065116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:33.065116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03249","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Si5vCB9Cmc2CAcwUhzTT6MgXGRz2FvIqogNMpjDYZRd9Gc3N3WgLXSN7apWNL3Lxu4+PdVAuiW4ZXjBnDKxcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:06:55.203178Z"},"content_sha256":"d964cf2facd0798d0f467b3b42fc6516fd050f8059d34b3413e8461e65d6c574","schema_version":"1.0","event_id":"sha256:d964cf2facd0798d0f467b3b42fc6516fd050f8059d34b3413e8461e65d6c574"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QBWDMAEA2LQWM56EY3R7WMBQP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Erion Plaku, Mohamed Aghzal, Ziyu Yao","submitted_at":"2023-10-05T01:42:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03249","kind":"arxiv","version":3},"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/2310.03249/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XPilOpuptsSlQMsy4n3YtXH8XifMo2guf8OuDnR+eCzCyFGwEreKjKRDtq7o3yZkXK+lAfELZhXKckYaDcDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:06:55.203713Z"},"content_sha256":"06130f26bbec1677fe6daf6fc716580e8fbe606ad3ffc3e9734ebec7f4cfd2b5","schema_version":"1.0","event_id":"sha256:06130f26bbec1677fe6daf6fc716580e8fbe606ad3ffc3e9734ebec7f4cfd2b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/bundle.json","state_url":"https://pith.science/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T09:06:55Z","links":{"resolver":"https://pith.science/pith/QBWDMAEA2LQWM56EY3R7WMBQP4","bundle":"https://pith.science/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/bundle.json","state":"https://pith.science/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBWDMAEA2LQWM56EY3R7WMBQP4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WWEqQXyobqjLyYFZyP0b+0I4yt93wiRJQLr57NfpVfxZxmygiPdAnYjuJdbUabn+WOMywOeXTV5UpPOuH8/UDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:06:55.207600Z","bundle_sha256":"e66173e7f817a949a83e5d1fd19f07285be83663558b9347d6cdb00c8c30c239"}}