{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4NV3OKTZVJULAEGDVH6MJNMCMW","short_pith_number":"pith:4NV3OKTZ","canonical_record":{"source":{"id":"2408.14438","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:25:16Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"a6b85c4917c6231c4d46c8ba365c3477da34c786d18436ee1091b42bee081dbf","abstract_canon_sha256":"4fdb42c774b8222871cc6c490928e5a5c930c4080dc3b778a94fd7041a4d4568"},"schema_version":"1.0"},"canonical_sha256":"e36bb72a79aa68b010c3a9fcc4b58265b286008d21dfd07c58cf79854d17f6c0","source":{"kind":"arxiv","id":"2408.14438","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14438","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14438v4","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14438","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"4NV3OKTZVJUL","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"4NV3OKTZVJULAEGD","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"4NV3OKTZ","created_at":"2026-07-05T09:56:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4NV3OKTZVJULAEGDVH6MJNMCMW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14438","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:25:16Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"a6b85c4917c6231c4d46c8ba365c3477da34c786d18436ee1091b42bee081dbf","abstract_canon_sha256":"4fdb42c774b8222871cc6c490928e5a5c930c4080dc3b778a94fd7041a4d4568"},"schema_version":"1.0"},"canonical_sha256":"e36bb72a79aa68b010c3a9fcc4b58265b286008d21dfd07c58cf79854d17f6c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:21.932235Z","signature_b64":"2GTqbpKOV4x+BV+8eey4BZ3Lhyr/R7DIiP4O1sRr1OPNUL41LIRM7QY4GZGvZ/mvr7BGOBez3PqAJFokiF8UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36bb72a79aa68b010c3a9fcc4b58265b286008d21dfd07c58cf79854d17f6c0","last_reissued_at":"2026-07-05T09:56:21.931616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:21.931616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14438","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ejXTVFJDu+UWd+2Pl6hkcXu9+wvYCv+DqoXLGAe4dnyFumYcgFCTF4OUaggiWyM6LrMV9KM4QQn3EtAD6foRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:35:37.207983Z"},"content_sha256":"6f24fc21c497f27d64671266c84bbee43f0bd2ef064add4643722e804be546cf","schema_version":"1.0","event_id":"sha256:6f24fc21c497f27d64671266c84bbee43f0bd2ef064add4643722e804be546cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4NV3OKTZVJULAEGDVH6MJNMCMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Hailin Feng, Liuchang Xu, LuYao Chen, Qianqian Luo, Qingming Lin, Sensen Wu, Shuo Zhao, Xinyue Ye, Zhenhong Du","submitted_at":"2024-08-26T17:25:16Z","abstract_excerpt":"The emergence of large language models such as ChatGPT, Gemini, and others highlights the importance of evaluating their diverse capabilities, ranging from natural language understanding to code generation. However, their performance on spatial tasks has not been thoroughly assessed. This study addresses this gap by introducing a new multi-task spatial evaluation dataset designed to systematically explore and compare the performance of several advanced models on spatial tasks. The dataset includes twelve distinct task types, such as spatial understanding and simple route planning, each with ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14438","kind":"arxiv","version":4},"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/2408.14438/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":"2026-07-05T09:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jar8uqTLVq0mAZn5C6W71VFIXX6FOQHG9PDpXpM/E8rYAx4izJehYBfCbdQ08tt7Bec1b5XPqg6IkIAKppfBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:35:37.208492Z"},"content_sha256":"3f0163d28586730cc05d90e234be3d1926daff0184e74324255b245d44a07369","schema_version":"1.0","event_id":"sha256:3f0163d28586730cc05d90e234be3d1926daff0184e74324255b245d44a07369"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/bundle.json","state_url":"https://pith.science/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/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":"2026-08-14T16:35:37Z","links":{"resolver":"https://pith.science/pith/4NV3OKTZVJULAEGDVH6MJNMCMW","bundle":"https://pith.science/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/bundle.json","state":"https://pith.science/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NV3OKTZVJULAEGDVH6MJNMCMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4NV3OKTZVJULAEGDVH6MJNMCMW","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":"4fdb42c774b8222871cc6c490928e5a5c930c4080dc3b778a94fd7041a4d4568","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:25:16Z","title_canon_sha256":"a6b85c4917c6231c4d46c8ba365c3477da34c786d18436ee1091b42bee081dbf"},"schema_version":"1.0","source":{"id":"2408.14438","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14438","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14438v4","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14438","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"4NV3OKTZVJUL","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"4NV3OKTZVJULAEGD","created_at":"2026-07-05T09:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"4NV3OKTZ","created_at":"2026-07-05T09:56:21Z"}],"graph_snapshots":[{"event_id":"sha256:3f0163d28586730cc05d90e234be3d1926daff0184e74324255b245d44a07369","target":"graph","created_at":"2026-07-05T09:56:21Z","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/2408.14438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of large language models such as ChatGPT, Gemini, and others highlights the importance of evaluating their diverse capabilities, ranging from natural language understanding to code generation. However, their performance on spatial tasks has not been thoroughly assessed. This study addresses this gap by introducing a new multi-task spatial evaluation dataset designed to systematically explore and compare the performance of several advanced models on spatial tasks. The dataset includes twelve distinct task types, such as spatial understanding and simple route planning, each with ve","authors_text":"Hailin Feng, Liuchang Xu, LuYao Chen, Qianqian Luo, Qingming Lin, Sensen Wu, Shuo Zhao, Xinyue Ye, Zhenhong Du","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:25:16Z","title":"Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14438","kind":"arxiv","version":4},"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":"sha256:6f24fc21c497f27d64671266c84bbee43f0bd2ef064add4643722e804be546cf","target":"record","created_at":"2026-07-05T09:56:21Z","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":"4fdb42c774b8222871cc6c490928e5a5c930c4080dc3b778a94fd7041a4d4568","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:25:16Z","title_canon_sha256":"a6b85c4917c6231c4d46c8ba365c3477da34c786d18436ee1091b42bee081dbf"},"schema_version":"1.0","source":{"id":"2408.14438","kind":"arxiv","version":4}},"canonical_sha256":"e36bb72a79aa68b010c3a9fcc4b58265b286008d21dfd07c58cf79854d17f6c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36bb72a79aa68b010c3a9fcc4b58265b286008d21dfd07c58cf79854d17f6c0","first_computed_at":"2026-07-05T09:56:21.931616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:21.931616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GTqbpKOV4x+BV+8eey4BZ3Lhyr/R7DIiP4O1sRr1OPNUL41LIRM7QY4GZGvZ/mvr7BGOBez3PqAJFokiF8UCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:21.932235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14438","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f24fc21c497f27d64671266c84bbee43f0bd2ef064add4643722e804be546cf","sha256:3f0163d28586730cc05d90e234be3d1926daff0184e74324255b245d44a07369"],"state_sha256":"43f7b398c6c592383db864334a266d47166565913171c1a5257a0c2329b9bfa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OgzggMg2YQRL/bvPWEMREB0hymWZWPurb0yHy3eEryKnLeVkmv0i7s/4JUBdtlR+sPCyJr3dz7XVdNNxNqKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T16:35:37.212848Z","bundle_sha256":"f8b257d79be01119f3e322abdfd0e7b32df62069cc57e8005c68b13f3240352b"}}