{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UI324YBAIHKR6AJPSJMXAZ62MJ","short_pith_number":"pith:UI324YBA","schema_version":"1.0","canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","source":{"kind":"arxiv","id":"2503.22093","version":2},"attestation_state":"computed","paper":{"title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anik Sen, Mallika Mainali, Ximing Wen","submitted_at":"2025-03-28T02:26:32Z","abstract_excerpt":"Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental states, remains underexplored. We propose an open-ended question framework to evaluate VLMs' performance across diverse categories of ToM tasks. We curated and annotated a benchmark dataset of 30 images and evaluated the performance of four VLMs of varying sizes. Our results show that the GPT-4 model outperformed all the others, with only one smaller model, GP"},"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":"2503.22093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T02:26:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52a26d33f376d0be7aa8d5346915058d4796fe5f43b0a3212a5b6f3b90dba8f1","abstract_canon_sha256":"cc537bc74648b782eabc1cb47dbda6bb62d9e90a40a2d69c5025a5e1a653764f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:16.603171Z","signature_b64":"zSVsvt9ZXJ8uz7HTrL9upXyoyMvsNWFvudV54XNqH34yl4U/urgglAs0QAlYw1FCY1N/xEzAL+Luu0uv6zuqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","last_reissued_at":"2026-07-05T10:53:16.602732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:16.602732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anik Sen, Mallika Mainali, Ximing Wen","submitted_at":"2025-03-28T02:26:32Z","abstract_excerpt":"Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental states, remains underexplored. We propose an open-ended question framework to evaluate VLMs' performance across diverse categories of ToM tasks. We curated and annotated a benchmark dataset of 30 images and evaluated the performance of four VLMs of varying sizes. Our results show that the GPT-4 model outperformed all the others, with only one smaller model, GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22093","kind":"arxiv","version":2},"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/2503.22093/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":"2503.22093","created_at":"2026-07-05T10:53:16.602793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22093v2","created_at":"2026-07-05T10:53:16.602793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22093","created_at":"2026-07-05T10:53:16.602793+00:00"},{"alias_kind":"pith_short_12","alias_value":"UI324YBAIHKR","created_at":"2026-07-05T10:53:16.602793+00:00"},{"alias_kind":"pith_short_16","alias_value":"UI324YBAIHKR6AJP","created_at":"2026-07-05T10:53:16.602793+00:00"},{"alias_kind":"pith_short_8","alias_value":"UI324YBA","created_at":"2026-07-05T10:53:16.602793+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/UI324YBAIHKR6AJPSJMXAZ62MJ","json":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ.json","graph_json":"https://pith.science/api/pith-number/UI324YBAIHKR6AJPSJMXAZ62MJ/graph.json","events_json":"https://pith.science/api/pith-number/UI324YBAIHKR6AJPSJMXAZ62MJ/events.json","paper":"https://pith.science/paper/UI324YBA"},"agent_actions":{"view_html":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ","download_json":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ.json","view_paper":"https://pith.science/paper/UI324YBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22093&json=true","fetch_graph":"https://pith.science/api/pith-number/UI324YBAIHKR6AJPSJMXAZ62MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UI324YBAIHKR6AJPSJMXAZ62MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/action/storage_attestation","attest_author":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/action/author_attestation","sign_citation":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/action/citation_signature","submit_replication":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/action/replication_record"}},"created_at":"2026-07-05T10:53:16.602793+00:00","updated_at":"2026-07-05T10:53:16.602793+00:00"}