{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UI324YBAIHKR6AJPSJMXAZ62MJ","short_pith_number":"pith:UI324YBA","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"},"canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","source":{"kind":"arxiv","id":"2503.22093","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22093","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22093v2","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22093","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"UI324YBAIHKR","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"UI324YBAIHKR6AJP","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"UI324YBA","created_at":"2026-07-05T10:53:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UI324YBAIHKR6AJPSJMXAZ62MJ","target":"record","payload":{"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"},"canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","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"},"source_kind":"arxiv","source_id":"2503.22093","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63HwAzGvGDRh/gSv/lUccbxJpKSMqrOrArj7wIzH4RaPpWVLFLMSOTJuxfCh7J0efNSBx7J/wUj6QJsj3wAsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:23:23.880983Z"},"content_sha256":"23ccdb8d552e9313411e7d70b96ae38492d4fdd44ccd7c6d91f801e047176032","schema_version":"1.0","event_id":"sha256:23ccdb8d552e9313411e7d70b96ae38492d4fdd44ccd7c6d91f801e047176032"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UI324YBAIHKR6AJPSJMXAZ62MJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vf0e/icVr6FIoL+8jf1FhP6/wkxT/MrjyQj0DVH1Glaqi3Fu83hqBgvih02kwn/N4Rp5bwiH/DN0zy1M3gSrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:23:23.881479Z"},"content_sha256":"a51197e3f9d16962f792af15b1fc87bf0b41c8d35d4018f50fdc8897488c1beb","schema_version":"1.0","event_id":"sha256:a51197e3f9d16962f792af15b1fc87bf0b41c8d35d4018f50fdc8897488c1beb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/bundle.json","state_url":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/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":"2026-07-31T14:23:23Z","links":{"resolver":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ","bundle":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/bundle.json","state":"https://pith.science/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UI324YBAIHKR6AJPSJMXAZ62MJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UI324YBAIHKR6AJPSJMXAZ62MJ","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":"cc537bc74648b782eabc1cb47dbda6bb62d9e90a40a2d69c5025a5e1a653764f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T02:26:32Z","title_canon_sha256":"52a26d33f376d0be7aa8d5346915058d4796fe5f43b0a3212a5b6f3b90dba8f1"},"schema_version":"1.0","source":{"id":"2503.22093","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22093","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22093v2","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22093","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"UI324YBAIHKR","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"UI324YBAIHKR6AJP","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"UI324YBA","created_at":"2026-07-05T10:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:a51197e3f9d16962f792af15b1fc87bf0b41c8d35d4018f50fdc8897488c1beb","target":"graph","created_at":"2026-07-05T10:53:16Z","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/2503.22093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anik Sen, Mallika Mainali, Ximing Wen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T02:26:32Z","title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22093","kind":"arxiv","version":2},"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":"sha256:23ccdb8d552e9313411e7d70b96ae38492d4fdd44ccd7c6d91f801e047176032","target":"record","created_at":"2026-07-05T10:53:16Z","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":"cc537bc74648b782eabc1cb47dbda6bb62d9e90a40a2d69c5025a5e1a653764f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T02:26:32Z","title_canon_sha256":"52a26d33f376d0be7aa8d5346915058d4796fe5f43b0a3212a5b6f3b90dba8f1"},"schema_version":"1.0","source":{"id":"2503.22093","kind":"arxiv","version":2}},"canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a237ae602041d51f012f92597067da625d3f03ccee37657a835f7ebb00abaf02","first_computed_at":"2026-07-05T10:53:16.602732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:16.602732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zSVsvt9ZXJ8uz7HTrL9upXyoyMvsNWFvudV54XNqH34yl4U/urgglAs0QAlYw1FCY1N/xEzAL+Luu0uv6zuqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:16.603171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22093","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23ccdb8d552e9313411e7d70b96ae38492d4fdd44ccd7c6d91f801e047176032","sha256:a51197e3f9d16962f792af15b1fc87bf0b41c8d35d4018f50fdc8897488c1beb"],"state_sha256":"19501ec49dd6529f9fb974c943bb2f59ff67ea24f8981194776ffb5584a82210"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Y1rJPN6jhCU37G0Or0e6gu88sJRPnHxvuwN5UlDo/EZGpFA+WqHkg2PBpjMTwfu/TlSsaXKdrowmG9t8v2XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:23:23.887049Z","bundle_sha256":"c64f0fbe5bafd4717ee2e1b55545523afac5658ea97bedb1f0439815931297dd"}}