{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ABMCKEMYXYRPUSD6JTUMPEPSJH","short_pith_number":"pith:ABMCKEMY","schema_version":"1.0","canonical_sha256":"0058251198be22fa487e4ce8c791f249ee362d303e719c07a0124953e61e410e","source":{"kind":"arxiv","id":"2506.14224","version":1},"attestation_state":"computed","paper":{"title":"From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bochao Zou, Huimin Ma, Jiansheng Chen, Siqi Liu, Xinyang Li","submitted_at":"2025-06-17T06:27:42Z","abstract_excerpt":"As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large language models (MLLMs). Specifically, we first construct a multimodal ToM test dataset, GridToM, whi"},"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":"2506.14224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-17T06:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"9e01bd8c4714e977957b8f225ca6f19b9075fce46f27a9752e2d7c9f7e223646","abstract_canon_sha256":"23a103b1a526487bee482598da6469f642952e5a082ba3af767e39b4b7387a90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:51.324135Z","signature_b64":"IuRoktNPTGMRyOi3Gg9kUHz4KxuN4VnpUd+Fup+QaFmSXMPfMUKvdg3hU/tdnMnhE9XhmUk98rEZKdLDfX0XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0058251198be22fa487e4ce8c791f249ee362d303e719c07a0124953e61e410e","last_reissued_at":"2026-07-05T11:22:51.323651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:51.323651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bochao Zou, Huimin Ma, Jiansheng Chen, Siqi Liu, Xinyang Li","submitted_at":"2025-06-17T06:27:42Z","abstract_excerpt":"As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large language models (MLLMs). Specifically, we first construct a multimodal ToM test dataset, GridToM, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14224","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/2506.14224/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":"2506.14224","created_at":"2026-07-05T11:22:51.323709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14224v1","created_at":"2026-07-05T11:22:51.323709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14224","created_at":"2026-07-05T11:22:51.323709+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABMCKEMYXYRP","created_at":"2026-07-05T11:22:51.323709+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABMCKEMYXYRPUSD6","created_at":"2026-07-05T11:22:51.323709+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABMCKEMY","created_at":"2026-07-05T11:22:51.323709+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/ABMCKEMYXYRPUSD6JTUMPEPSJH","json":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH.json","graph_json":"https://pith.science/api/pith-number/ABMCKEMYXYRPUSD6JTUMPEPSJH/graph.json","events_json":"https://pith.science/api/pith-number/ABMCKEMYXYRPUSD6JTUMPEPSJH/events.json","paper":"https://pith.science/paper/ABMCKEMY"},"agent_actions":{"view_html":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH","download_json":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH.json","view_paper":"https://pith.science/paper/ABMCKEMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14224&json=true","fetch_graph":"https://pith.science/api/pith-number/ABMCKEMYXYRPUSD6JTUMPEPSJH/graph.json","fetch_events":"https://pith.science/api/pith-number/ABMCKEMYXYRPUSD6JTUMPEPSJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH/action/storage_attestation","attest_author":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH/action/author_attestation","sign_citation":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH/action/citation_signature","submit_replication":"https://pith.science/pith/ABMCKEMYXYRPUSD6JTUMPEPSJH/action/replication_record"}},"created_at":"2026-07-05T11:22:51.323709+00:00","updated_at":"2026-07-05T11:22:51.323709+00:00"}