{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIUNZ6IDF3WGPJVN3CVONPC7AR","short_pith_number":"pith:SIUNZ6ID","schema_version":"1.0","canonical_sha256":"9228dcf9032eec67a6add8aae6bc5f04673574ea84dd4f2edd669e86fde88b56","source":{"kind":"arxiv","id":"2408.11347","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ken Fukuda, Kensho Hara, Shusaku Egami, Takanori Ugai","submitted_at":"2024-08-21T05:27:55Z","abstract_excerpt":"We used a 3D simulator to create artificial video data with standardized annotations, aiming to aid in the development of Embodied AI. Our question answering (QA) dataset measures the extent to which a robot can understand human behavior and the environment in a home setting. Preliminary experiments suggest our dataset is useful in measuring AI's comprehension of daily life. \\end{abstract}"},"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":"2408.11347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T05:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"f0932680ef9911fddefbdff8b475b09f2a5cdcd7bcff00fe85d15fffb82ec596","abstract_canon_sha256":"2a2744727549a42b5bbc86515084aa81308c7aa61271c0cdbaadf3ef753f4a9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:50.417091Z","signature_b64":"qaGTirykddKzyeEnurTYUgmLDDhZTNgvVRje7RRmaMjz5TW8wii1S/M0IdNdbqBVn7TmxjTiCo/q8vNy8TOGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9228dcf9032eec67a6add8aae6bc5f04673574ea84dd4f2edd669e86fde88b56","last_reissued_at":"2026-07-05T09:07:50.416553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:50.416553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ken Fukuda, Kensho Hara, Shusaku Egami, Takanori Ugai","submitted_at":"2024-08-21T05:27:55Z","abstract_excerpt":"We used a 3D simulator to create artificial video data with standardized annotations, aiming to aid in the development of Embodied AI. Our question answering (QA) dataset measures the extent to which a robot can understand human behavior and the environment in a home setting. Preliminary experiments suggest our dataset is useful in measuring AI's comprehension of daily life. \\end{abstract}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11347","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/2408.11347/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":"2408.11347","created_at":"2026-07-05T09:07:50.416610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11347v2","created_at":"2026-07-05T09:07:50.416610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11347","created_at":"2026-07-05T09:07:50.416610+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIUNZ6IDF3WG","created_at":"2026-07-05T09:07:50.416610+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIUNZ6IDF3WGPJVN","created_at":"2026-07-05T09:07:50.416610+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIUNZ6ID","created_at":"2026-07-05T09:07:50.416610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24346","citing_title":"VUDG: A Dataset for Video Understanding Domain Generalization","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR","json":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR.json","graph_json":"https://pith.science/api/pith-number/SIUNZ6IDF3WGPJVN3CVONPC7AR/graph.json","events_json":"https://pith.science/api/pith-number/SIUNZ6IDF3WGPJVN3CVONPC7AR/events.json","paper":"https://pith.science/paper/SIUNZ6ID"},"agent_actions":{"view_html":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR","download_json":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR.json","view_paper":"https://pith.science/paper/SIUNZ6ID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11347&json=true","fetch_graph":"https://pith.science/api/pith-number/SIUNZ6IDF3WGPJVN3CVONPC7AR/graph.json","fetch_events":"https://pith.science/api/pith-number/SIUNZ6IDF3WGPJVN3CVONPC7AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR/action/storage_attestation","attest_author":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR/action/author_attestation","sign_citation":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR/action/citation_signature","submit_replication":"https://pith.science/pith/SIUNZ6IDF3WGPJVN3CVONPC7AR/action/replication_record"}},"created_at":"2026-07-05T09:07:50.416610+00:00","updated_at":"2026-07-05T09:07:50.416610+00:00"}