{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2YQSWQRQOO5C6T5JKIZFWJOCMD","short_pith_number":"pith:2YQSWQRQ","schema_version":"1.0","canonical_sha256":"d6212b423073ba2f4fa952325b25c260d77db65b30270ebafd9fa950f738f593","source":{"kind":"arxiv","id":"2406.16528","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony G Cohn, Robert E Blackwell","submitted_at":"2024-06-24T11:07:01Z","abstract_excerpt":"We investigate the abilities of a representative set of Large language Models (LLMs) to reason about cardinal directions (CDs). To do so, we create two datasets: the first, co-created with ChatGPT, focuses largely on recall of world knowledge about CDs; the second is generated from a set of templates, comprehensively testing an LLM's ability to determine the correct CD given a particular scenario. The templates allow for a number of degrees of variation such as means of locomotion of the agent involved, and whether set in the first , second or third person. Even with a temperature setting of z"},"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":"2406.16528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T11:07:01Z","cross_cats_sorted":[],"title_canon_sha256":"5690a8f94aadcf303de4319466eb334d5cdffc09431071efc55f5b34a4a6b0d1","abstract_canon_sha256":"6825a0ff313aa59059cfd93bcd0465d5d0352fa8a5cf4a0381ad0655b321749c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:17.109385Z","signature_b64":"5QLm+6g/tBLnr/UB0YfUHtbKEAX8pzxuw48NdcN9+C8GLZF2wuNaXp7VfR3v+LUGr6L/WB3GaaWlGeGXo00SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6212b423073ba2f4fa952325b25c260d77db65b30270ebafd9fa950f738f593","last_reissued_at":"2026-07-05T09:05:17.108895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:17.108895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony G Cohn, Robert E Blackwell","submitted_at":"2024-06-24T11:07:01Z","abstract_excerpt":"We investigate the abilities of a representative set of Large language Models (LLMs) to reason about cardinal directions (CDs). To do so, we create two datasets: the first, co-created with ChatGPT, focuses largely on recall of world knowledge about CDs; the second is generated from a set of templates, comprehensively testing an LLM's ability to determine the correct CD given a particular scenario. The templates allow for a number of degrees of variation such as means of locomotion of the agent involved, and whether set in the first , second or third person. Even with a temperature setting of z"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16528","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/2406.16528/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":"2406.16528","created_at":"2026-07-05T09:05:17.108962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16528v1","created_at":"2026-07-05T09:05:17.108962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16528","created_at":"2026-07-05T09:05:17.108962+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YQSWQRQOO5C","created_at":"2026-07-05T09:05:17.108962+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YQSWQRQOO5C6T5J","created_at":"2026-07-05T09:05:17.108962+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YQSWQRQ","created_at":"2026-07-05T09:05:17.108962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19589","citing_title":"Can Large Language Models Reason about the Region Connection Calculus?","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD","json":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD.json","graph_json":"https://pith.science/api/pith-number/2YQSWQRQOO5C6T5JKIZFWJOCMD/graph.json","events_json":"https://pith.science/api/pith-number/2YQSWQRQOO5C6T5JKIZFWJOCMD/events.json","paper":"https://pith.science/paper/2YQSWQRQ"},"agent_actions":{"view_html":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD","download_json":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD.json","view_paper":"https://pith.science/paper/2YQSWQRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16528&json=true","fetch_graph":"https://pith.science/api/pith-number/2YQSWQRQOO5C6T5JKIZFWJOCMD/graph.json","fetch_events":"https://pith.science/api/pith-number/2YQSWQRQOO5C6T5JKIZFWJOCMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD/action/storage_attestation","attest_author":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD/action/author_attestation","sign_citation":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD/action/citation_signature","submit_replication":"https://pith.science/pith/2YQSWQRQOO5C6T5JKIZFWJOCMD/action/replication_record"}},"created_at":"2026-07-05T09:05:17.108962+00:00","updated_at":"2026-07-05T09:05:17.108962+00:00"}