{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:54Z3ZJEH5V7EE4LB3PLMH6TRAH","short_pith_number":"pith:54Z3ZJEH","schema_version":"1.0","canonical_sha256":"ef33bca487ed7e427161dbd6c3fa7101c36f248561f653cd5bbb6d7385b5dbef","source":{"kind":"arxiv","id":"2410.13206","version":3},"attestation_state":"computed","paper":{"title":"BQA: Body Language Question Answering Dataset for Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hidetaka Kamigaito, Kazuki Hayashi, Miyu Oba, Shintaro Ozaki, Taro Watanabe, Yusuke Sakai","submitted_at":"2024-10-17T04:19:26Z","abstract_excerpt":"A large part of human communication relies on nonverbal cues such as facial expressions, eye contact, and body language. Unlike language or sign language, such nonverbal communication lacks formal rules, requiring complex reasoning based on commonsense understanding. Enabling current Video Large Language Models (VideoLLMs) to accurately interpret body language is a crucial challenge, as human unconscious actions can easily cause the model to misinterpret their intent. To address this, we propose a dataset, BQA, a body language question answering dataset, to validate whether the model can corre"},"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":"2410.13206","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T04:19:26Z","cross_cats_sorted":[],"title_canon_sha256":"35b6b9de51da48b88cc912d2339f9d16aa307a7a62e805b2af70f69fd1eca6d5","abstract_canon_sha256":"3daa88d9c91c481095dc3a929ff7f33fb11e44a5a9819e14233b154bf0ed91ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:36.536127Z","signature_b64":"IBEZ/gERCRH7pQuxYZSAVyO07pY55Zhqd8EC3VTEvarKq+W0eWms6ORfyH8K56iqawMV0RLwk/zWVJbpsyW7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef33bca487ed7e427161dbd6c3fa7101c36f248561f653cd5bbb6d7385b5dbef","last_reissued_at":"2026-07-05T11:55:36.535640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:36.535640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BQA: Body Language Question Answering Dataset for Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hidetaka Kamigaito, Kazuki Hayashi, Miyu Oba, Shintaro Ozaki, Taro Watanabe, Yusuke Sakai","submitted_at":"2024-10-17T04:19:26Z","abstract_excerpt":"A large part of human communication relies on nonverbal cues such as facial expressions, eye contact, and body language. Unlike language or sign language, such nonverbal communication lacks formal rules, requiring complex reasoning based on commonsense understanding. Enabling current Video Large Language Models (VideoLLMs) to accurately interpret body language is a crucial challenge, as human unconscious actions can easily cause the model to misinterpret their intent. To address this, we propose a dataset, BQA, a body language question answering dataset, to validate whether the model can corre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13206","kind":"arxiv","version":3},"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/2410.13206/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":"2410.13206","created_at":"2026-07-05T11:55:36.535699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13206v3","created_at":"2026-07-05T11:55:36.535699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13206","created_at":"2026-07-05T11:55:36.535699+00:00"},{"alias_kind":"pith_short_12","alias_value":"54Z3ZJEH5V7E","created_at":"2026-07-05T11:55:36.535699+00:00"},{"alias_kind":"pith_short_16","alias_value":"54Z3ZJEH5V7EE4LB","created_at":"2026-07-05T11:55:36.535699+00:00"},{"alias_kind":"pith_short_8","alias_value":"54Z3ZJEH","created_at":"2026-07-05T11:55:36.535699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21458","citing_title":"Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH","json":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH.json","graph_json":"https://pith.science/api/pith-number/54Z3ZJEH5V7EE4LB3PLMH6TRAH/graph.json","events_json":"https://pith.science/api/pith-number/54Z3ZJEH5V7EE4LB3PLMH6TRAH/events.json","paper":"https://pith.science/paper/54Z3ZJEH"},"agent_actions":{"view_html":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH","download_json":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH.json","view_paper":"https://pith.science/paper/54Z3ZJEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13206&json=true","fetch_graph":"https://pith.science/api/pith-number/54Z3ZJEH5V7EE4LB3PLMH6TRAH/graph.json","fetch_events":"https://pith.science/api/pith-number/54Z3ZJEH5V7EE4LB3PLMH6TRAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH/action/storage_attestation","attest_author":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH/action/author_attestation","sign_citation":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH/action/citation_signature","submit_replication":"https://pith.science/pith/54Z3ZJEH5V7EE4LB3PLMH6TRAH/action/replication_record"}},"created_at":"2026-07-05T11:55:36.535699+00:00","updated_at":"2026-07-05T11:55:36.535699+00:00"}