{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DJUL2EQXKIPWTJLSMLLA3JWDN4","short_pith_number":"pith:DJUL2EQX","schema_version":"1.0","canonical_sha256":"1a68bd1217521f69a57262d60da6c36f2b4f433b277ad8a7605ec48442811fe8","source":{"kind":"arxiv","id":"2605.18194","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Xiangyu Kong, Yajing Zhou","submitted_at":"2026-05-18T10:32:56Z","abstract_excerpt":"While Multi-Modal Large Language Models (MLLMs) demonstrate impressive capabilities in general reasoning, their embodied spatial intelligence remains hampered by a \"Cartesian Illusion\" - a reliance on text-based probability distributions that lack grounded, 3D topological understanding. This limitation is starkly exposed in multi-agent environments, which demand more than just scene perception; they require second-order Theory of Mind (ToM). Specifically, an Agent A must be able to infer Agent B's belief about the environment, governed strictly by Agent B's physical orientation and sensory lim"},"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":"2605.18194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T10:32:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3edca46959806b83642aa3db42129f35730db498bc4b8d5b87e4087e5cd46a45","abstract_canon_sha256":"dad7fb8656d87a256a0c7cadd35f934c7940bc6f251e037588f1267289a016cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:50.105440Z","signature_b64":"qvKFvNC3aokUzWZlfdAGKbXU/UJL9h1oCgymtwMXVvQN8Ha8gvLCNGS8dCCE9hbVWOjX47cbEwXey2glIE/FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a68bd1217521f69a57262d60da6c36f2b4f433b277ad8a7605ec48442811fe8","last_reissued_at":"2026-05-20T00:05:50.104905Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:50.104905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Xiangyu Kong, Yajing Zhou","submitted_at":"2026-05-18T10:32:56Z","abstract_excerpt":"While Multi-Modal Large Language Models (MLLMs) demonstrate impressive capabilities in general reasoning, their embodied spatial intelligence remains hampered by a \"Cartesian Illusion\" - a reliance on text-based probability distributions that lack grounded, 3D topological understanding. This limitation is starkly exposed in multi-agent environments, which demand more than just scene perception; they require second-order Theory of Mind (ToM). Specifically, an Agent A must be able to infer Agent B's belief about the environment, governed strictly by Agent B's physical orientation and sensory lim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18194","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/2605.18194/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.006200Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.328689Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3454d9e0d84bb091b835d238d79d8f4372699aa141592d4439736ee375c38ba4"},"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":"2605.18194","created_at":"2026-05-20T00:05:50.105001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18194v1","created_at":"2026-05-20T00:05:50.105001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18194","created_at":"2026-05-20T00:05:50.105001+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJUL2EQXKIPW","created_at":"2026-05-20T00:05:50.105001+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJUL2EQXKIPWTJLS","created_at":"2026-05-20T00:05:50.105001+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJUL2EQX","created_at":"2026-05-20T00:05:50.105001+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/DJUL2EQXKIPWTJLSMLLA3JWDN4","json":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4.json","graph_json":"https://pith.science/api/pith-number/DJUL2EQXKIPWTJLSMLLA3JWDN4/graph.json","events_json":"https://pith.science/api/pith-number/DJUL2EQXKIPWTJLSMLLA3JWDN4/events.json","paper":"https://pith.science/paper/DJUL2EQX"},"agent_actions":{"view_html":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4","download_json":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4.json","view_paper":"https://pith.science/paper/DJUL2EQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18194&json=true","fetch_graph":"https://pith.science/api/pith-number/DJUL2EQXKIPWTJLSMLLA3JWDN4/graph.json","fetch_events":"https://pith.science/api/pith-number/DJUL2EQXKIPWTJLSMLLA3JWDN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4/action/storage_attestation","attest_author":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4/action/author_attestation","sign_citation":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4/action/citation_signature","submit_replication":"https://pith.science/pith/DJUL2EQXKIPWTJLSMLLA3JWDN4/action/replication_record"}},"created_at":"2026-05-20T00:05:50.105001+00:00","updated_at":"2026-05-20T00:05:50.105001+00:00"}