{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DJCIDOAKZSJD3H7EICSWL4Z7QU","short_pith_number":"pith:DJCIDOAK","schema_version":"1.0","canonical_sha256":"1a4481b80acc923d9fe440a565f33f850dd0169d611536e5e85cee25e5dc5fdf","source":{"kind":"arxiv","id":"2406.02554","version":1},"attestation_state":"computed","paper":{"title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"eess.AS","authors_text":"Alexander Kaplan, Erin E. Kosloski, Harsh Singh, Matthew Wang, Pamela R. Rollins, Shijian Deng, Siddhi Patel, Sisira Aarukapalli, William T. Doan, Yapeng Tian, Yiyang Nan, Zeke A. Barnett","submitted_at":"2024-03-22T22:52:35Z","abstract_excerpt":"In this article, we introduce a novel problem of audio-visual autism behavior recognition, which includes social behavior recognition, an essential aspect previously omitted in AI-assisted autism screening research. We define the task at hand as one that is audio-visual autism behavior recognition, which uses audio and visual cues, including any speech present in the audio, to recognize autism-related behaviors. To facilitate this new research direction, we collected an audio-visual autism spectrum dataset (AV-ASD), currently the largest video dataset for autism screening using a behavioral ap"},"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":"2406.02554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-22T22:52:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"f705c66a4f89a19189c6d75995fdab88635f2ac6d7448df26ceecfed429706f3","abstract_canon_sha256":"dc1f6aaf423b77fe5e02b21042f08d9ea012debc5a8e9ab7cd65ba089d42a82b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:26.887309Z","signature_b64":"KZIqd2NMNhGPKpgZDIt8kiUYn/6rBmfEcZKX1tjZXbbvnGCNRLy7GBLZ+Alx4C6Nn4o6+0hvQ0Z9L8Va19zCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4481b80acc923d9fe440a565f33f850dd0169d611536e5e85cee25e5dc5fdf","last_reissued_at":"2026-07-05T08:27:26.886874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:26.886874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"eess.AS","authors_text":"Alexander Kaplan, Erin E. Kosloski, Harsh Singh, Matthew Wang, Pamela R. Rollins, Shijian Deng, Siddhi Patel, Sisira Aarukapalli, William T. Doan, Yapeng Tian, Yiyang Nan, Zeke A. Barnett","submitted_at":"2024-03-22T22:52:35Z","abstract_excerpt":"In this article, we introduce a novel problem of audio-visual autism behavior recognition, which includes social behavior recognition, an essential aspect previously omitted in AI-assisted autism screening research. We define the task at hand as one that is audio-visual autism behavior recognition, which uses audio and visual cues, including any speech present in the audio, to recognize autism-related behaviors. To facilitate this new research direction, we collected an audio-visual autism spectrum dataset (AV-ASD), currently the largest video dataset for autism screening using a behavioral ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02554","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/2406.02554/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":"2406.02554","created_at":"2026-07-05T08:27:26.886930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02554v1","created_at":"2026-07-05T08:27:26.886930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02554","created_at":"2026-07-05T08:27:26.886930+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJCIDOAKZSJD","created_at":"2026-07-05T08:27:26.886930+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJCIDOAKZSJD3H7E","created_at":"2026-07-05T08:27:26.886930+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJCIDOAK","created_at":"2026-07-05T08:27:26.886930+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/DJCIDOAKZSJD3H7EICSWL4Z7QU","json":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU.json","graph_json":"https://pith.science/api/pith-number/DJCIDOAKZSJD3H7EICSWL4Z7QU/graph.json","events_json":"https://pith.science/api/pith-number/DJCIDOAKZSJD3H7EICSWL4Z7QU/events.json","paper":"https://pith.science/paper/DJCIDOAK"},"agent_actions":{"view_html":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU","download_json":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU.json","view_paper":"https://pith.science/paper/DJCIDOAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02554&json=true","fetch_graph":"https://pith.science/api/pith-number/DJCIDOAKZSJD3H7EICSWL4Z7QU/graph.json","fetch_events":"https://pith.science/api/pith-number/DJCIDOAKZSJD3H7EICSWL4Z7QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU/action/storage_attestation","attest_author":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU/action/author_attestation","sign_citation":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU/action/citation_signature","submit_replication":"https://pith.science/pith/DJCIDOAKZSJD3H7EICSWL4Z7QU/action/replication_record"}},"created_at":"2026-07-05T08:27:26.886930+00:00","updated_at":"2026-07-05T08:27:26.886930+00:00"}