{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5IO2DY2QOYWGH6FZIU6IALWZNZ","short_pith_number":"pith:5IO2DY2Q","schema_version":"1.0","canonical_sha256":"ea1da1e350762c63f8b9453c802ed96e69e0c6491633dabf34a56f0ecdaba00b","source":{"kind":"arxiv","id":"2605.28277","version":1},"attestation_state":"computed","paper":{"title":"Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chih-Ting Liao, Chunlei Meng, Chunrui Liu, Xin Cao, Xi Xiao, Yitong Qiao, Zhangquan Chen, Zhikai Pan","submitted_at":"2026-05-27T10:20:53Z","abstract_excerpt":"Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages has not been systematically studied. We introduce MentalMap, a multilingual diagnostic benchmark with a six-level capability hierarchy (L0-L5) spanning atomic spatial facts to generative world-graph construction, together with four diagnostic axes probing frame of reference, reading-direction bias, reasoning-effort allocation, and hallucination. MentalMap is built from 100 ProcTHOR household scenes, covers eight typo"},"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":"2605.28277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:20:53Z","cross_cats_sorted":[],"title_canon_sha256":"6dfbbb63b2217a16bbfaf5478ed305151581b7e3f8412b3d1fa117c25f365390","abstract_canon_sha256":"bda4c4707fd67a036de5631c4a60020d4ad8b2d8ecfcd27366a70ecb9bedc298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:04.990157Z","signature_b64":"yFHbCCy9mdQ3fYSve1bZMwGmJnxLhB7JK9NrwsCDOINzosRJwmD3E9nBjMwpyZBjM9EHgbGYFbXeckHyhgNJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea1da1e350762c63f8b9453c802ed96e69e0c6491633dabf34a56f0ecdaba00b","last_reissued_at":"2026-05-28T01:05:04.989713Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:04.989713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chih-Ting Liao, Chunlei Meng, Chunrui Liu, Xin Cao, Xi Xiao, Yitong Qiao, Zhangquan Chen, Zhikai Pan","submitted_at":"2026-05-27T10:20:53Z","abstract_excerpt":"Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages has not been systematically studied. We introduce MentalMap, a multilingual diagnostic benchmark with a six-level capability hierarchy (L0-L5) spanning atomic spatial facts to generative world-graph construction, together with four diagnostic axes probing frame of reference, reading-direction bias, reasoning-effort allocation, and hallucination. MentalMap is built from 100 ProcTHOR household scenes, covers eight typo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28277","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/2605.28277/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":"2605.28277","created_at":"2026-05-28T01:05:04.989783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28277v1","created_at":"2026-05-28T01:05:04.989783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28277","created_at":"2026-05-28T01:05:04.989783+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IO2DY2QOYWG","created_at":"2026-05-28T01:05:04.989783+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IO2DY2QOYWGH6FZ","created_at":"2026-05-28T01:05:04.989783+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IO2DY2Q","created_at":"2026-05-28T01:05:04.989783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ","json":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ.json","graph_json":"https://pith.science/api/pith-number/5IO2DY2QOYWGH6FZIU6IALWZNZ/graph.json","events_json":"https://pith.science/api/pith-number/5IO2DY2QOYWGH6FZIU6IALWZNZ/events.json","paper":"https://pith.science/paper/5IO2DY2Q"},"agent_actions":{"view_html":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ","download_json":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ.json","view_paper":"https://pith.science/paper/5IO2DY2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28277&json=true","fetch_graph":"https://pith.science/api/pith-number/5IO2DY2QOYWGH6FZIU6IALWZNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5IO2DY2QOYWGH6FZIU6IALWZNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ/action/storage_attestation","attest_author":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ/action/author_attestation","sign_citation":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ/action/citation_signature","submit_replication":"https://pith.science/pith/5IO2DY2QOYWGH6FZIU6IALWZNZ/action/replication_record"}},"created_at":"2026-05-28T01:05:04.989783+00:00","updated_at":"2026-05-28T01:05:04.989783+00:00"}