{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UB7IOQKKQLYQNERR2FXYZH4NQ4","short_pith_number":"pith:UB7IOQKK","canonical_record":{"source":{"id":"2503.22152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T05:10:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ba0f4207be9b02146895bf968684255d2ad64e765766c267f4260686d609fee","abstract_canon_sha256":"85ca40beb66440e91a269afcc278f9f15d320118b67bbeaa9206fcdd932c82df"},"schema_version":"1.0"},"canonical_sha256":"a07e87414a82f1069231d16f8c9f8d87217832655f4cc06ad4ff1ad26fe35534","source":{"kind":"arxiv","id":"2503.22152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22152","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22152v1","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22152","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"UB7IOQKKQLYQ","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"UB7IOQKKQLYQNERR","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"UB7IOQKK","created_at":"2026-07-05T10:40:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UB7IOQKKQLYQNERR2FXYZH4NQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T05:10:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ba0f4207be9b02146895bf968684255d2ad64e765766c267f4260686d609fee","abstract_canon_sha256":"85ca40beb66440e91a269afcc278f9f15d320118b67bbeaa9206fcdd932c82df"},"schema_version":"1.0"},"canonical_sha256":"a07e87414a82f1069231d16f8c9f8d87217832655f4cc06ad4ff1ad26fe35534","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:48.416405Z","signature_b64":"Oni8nR8s7g7fBRXAnOAdiN/aOzoXBj7F35SIsEi4ZBxb0Dx8r8Tu6johaS3YSzmhwWHdlCr7GCp1Q6KNl0ppCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a07e87414a82f1069231d16f8c9f8d87217832655f4cc06ad4ff1ad26fe35534","last_reissued_at":"2026-07-05T10:40:48.415931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:48.415931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22152","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10B19g1Tu9gdhkqf+sn4JgSIIfmAEmJ9qDzzcPN8okfKCjllVqge8/G9EWbgf0Cw1SsNAP7nCI8bbdWrSuNsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T22:21:43.460688Z"},"content_sha256":"99fe268d0e447e6c7e6711623d2f87cd11aaf16b150ddefa45d45a57fdffbfdf","schema_version":"1.0","event_id":"sha256:99fe268d0e447e6c7e6711623d2f87cd11aaf16b150ddefa45d45a57fdffbfdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UB7IOQKKQLYQNERR2FXYZH4NQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Asli Celikyilmaz, Brett D. Roads, Karl Ridgeway, Michael L. Iuzzolino, Vijay Veerabadran, Yuxuan Li","submitted_at":"2025-03-28T05:10:59Z","abstract_excerpt":"We introduce EgoToM, a new video question-answering benchmark that extends Theory-of-Mind (ToM) evaluation to egocentric domains. Using a causal ToM model, we generate multi-choice video QA instances for the Ego4D dataset to benchmark the ability to predict a camera wearer's goals, beliefs, and next actions. We study the performance of both humans and state of the art multimodal large language models (MLLMs) on these three interconnected inference problems. Our evaluation shows that MLLMs achieve close to human-level accuracy on inferring goals from egocentric videos. However, MLLMs (including"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22152","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/2503.22152/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":"2026-07-05T10:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIvHVB69pA8QJW4V5+Su5sZ0dJG7RG8FFBNTSvGNVGCCijMPIMgWLvV/u4J7xCaSN2MqtU9dEmqPhuUMlykADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T22:21:43.461064Z"},"content_sha256":"30d39f3ed8e05a5717aaf07eb01f2fa178b84cb2dc6f397292a6904a0df2a4ed","schema_version":"1.0","event_id":"sha256:30d39f3ed8e05a5717aaf07eb01f2fa178b84cb2dc6f397292a6904a0df2a4ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/bundle.json","state_url":"https://pith.science/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/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":"2026-07-14T22:21:43Z","links":{"resolver":"https://pith.science/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4","bundle":"https://pith.science/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/bundle.json","state":"https://pith.science/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UB7IOQKKQLYQNERR2FXYZH4NQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UB7IOQKKQLYQNERR2FXYZH4NQ4","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":"85ca40beb66440e91a269afcc278f9f15d320118b67bbeaa9206fcdd932c82df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T05:10:59Z","title_canon_sha256":"8ba0f4207be9b02146895bf968684255d2ad64e765766c267f4260686d609fee"},"schema_version":"1.0","source":{"id":"2503.22152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22152","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22152v1","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22152","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"UB7IOQKKQLYQ","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"UB7IOQKKQLYQNERR","created_at":"2026-07-05T10:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"UB7IOQKK","created_at":"2026-07-05T10:40:48Z"}],"graph_snapshots":[{"event_id":"sha256:30d39f3ed8e05a5717aaf07eb01f2fa178b84cb2dc6f397292a6904a0df2a4ed","target":"graph","created_at":"2026-07-05T10:40:48Z","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/2503.22152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce EgoToM, a new video question-answering benchmark that extends Theory-of-Mind (ToM) evaluation to egocentric domains. Using a causal ToM model, we generate multi-choice video QA instances for the Ego4D dataset to benchmark the ability to predict a camera wearer's goals, beliefs, and next actions. We study the performance of both humans and state of the art multimodal large language models (MLLMs) on these three interconnected inference problems. Our evaluation shows that MLLMs achieve close to human-level accuracy on inferring goals from egocentric videos. However, MLLMs (including","authors_text":"Asli Celikyilmaz, Brett D. Roads, Karl Ridgeway, Michael L. Iuzzolino, Vijay Veerabadran, Yuxuan Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T05:10:59Z","title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22152","kind":"arxiv","version":1},"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":"sha256:99fe268d0e447e6c7e6711623d2f87cd11aaf16b150ddefa45d45a57fdffbfdf","target":"record","created_at":"2026-07-05T10:40:48Z","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":"85ca40beb66440e91a269afcc278f9f15d320118b67bbeaa9206fcdd932c82df","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T05:10:59Z","title_canon_sha256":"8ba0f4207be9b02146895bf968684255d2ad64e765766c267f4260686d609fee"},"schema_version":"1.0","source":{"id":"2503.22152","kind":"arxiv","version":1}},"canonical_sha256":"a07e87414a82f1069231d16f8c9f8d87217832655f4cc06ad4ff1ad26fe35534","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a07e87414a82f1069231d16f8c9f8d87217832655f4cc06ad4ff1ad26fe35534","first_computed_at":"2026-07-05T10:40:48.415931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:48.415931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oni8nR8s7g7fBRXAnOAdiN/aOzoXBj7F35SIsEi4ZBxb0Dx8r8Tu6johaS3YSzmhwWHdlCr7GCp1Q6KNl0ppCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:48.416405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99fe268d0e447e6c7e6711623d2f87cd11aaf16b150ddefa45d45a57fdffbfdf","sha256:30d39f3ed8e05a5717aaf07eb01f2fa178b84cb2dc6f397292a6904a0df2a4ed"],"state_sha256":"038285992e77d6c7a7d5a56b8f360b6d2dab1d840369659294e211a19d53ed22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Q9efnEcTpDMVmYbS5DUDLlxGmhCQrXXuxPuEVMfW7zGnkJzCC+bh80/Gq1vif0XyytqfjrgeLA4HwWWr/MjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T22:21:43.465064Z","bundle_sha256":"f11b475f377ef28cf2ba86692e9047b0d735154c40a08f560341243da4d87900"}}