{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:34ONMB5U3IEQ3WK4BMDMHDSSP3","short_pith_number":"pith:34ONMB5U","schema_version":"1.0","canonical_sha256":"df1cd607b4da090dd95c0b06c38e527ef1423e93b8421f26b202c6daaaa6193b","source":{"kind":"arxiv","id":"2503.16432","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Casey C. Bennett, Young-Ho Bae","submitted_at":"2025-02-05T23:00:49Z","abstract_excerpt":"This study investigates multimodal turn-taking prediction within human-agent interactions (HAI), particularly focusing on cooperative gaming environments. It comprises both model development and subsequent user study, aiming to refine our understanding and improve conversational dynamics in spoken dialogue systems (SDSs). For the modeling phase, we introduce a novel transformer-based deep learning (DL) model that simultaneously integrates multiple modalities - text, vision, audio, and contextual in-game data to predict turn-taking events in real-time. Our model employs a Crossmodal Transformer"},"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":"2503.16432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-05T23:00:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"76b530f76f42eaedc5aa4cdf3be3bf3ada041594820c1cf682453b992bff42f9","abstract_canon_sha256":"3bed0a3ec9866675776d5ea01c158d4e3bd2114f86c511eb4a4b3900addfcb75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:40.561829Z","signature_b64":"c7Tjq4AcQfBKQPav9g2KUnnpJAUGHEx14id+1kAOI/zkG6iJQWYizgB4xEjewNPMtSS3MePUb+/eZfcvGWY8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df1cd607b4da090dd95c0b06c38e527ef1423e93b8421f26b202c6daaaa6193b","last_reissued_at":"2026-07-05T10:36:40.561172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:40.561172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Casey C. Bennett, Young-Ho Bae","submitted_at":"2025-02-05T23:00:49Z","abstract_excerpt":"This study investigates multimodal turn-taking prediction within human-agent interactions (HAI), particularly focusing on cooperative gaming environments. It comprises both model development and subsequent user study, aiming to refine our understanding and improve conversational dynamics in spoken dialogue systems (SDSs). For the modeling phase, we introduce a novel transformer-based deep learning (DL) model that simultaneously integrates multiple modalities - text, vision, audio, and contextual in-game data to predict turn-taking events in real-time. Our model employs a Crossmodal Transformer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16432","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/2503.16432/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":"2503.16432","created_at":"2026-07-05T10:36:40.561230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16432v1","created_at":"2026-07-05T10:36:40.561230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16432","created_at":"2026-07-05T10:36:40.561230+00:00"},{"alias_kind":"pith_short_12","alias_value":"34ONMB5U3IEQ","created_at":"2026-07-05T10:36:40.561230+00:00"},{"alias_kind":"pith_short_16","alias_value":"34ONMB5U3IEQ3WK4","created_at":"2026-07-05T10:36:40.561230+00:00"},{"alias_kind":"pith_short_8","alias_value":"34ONMB5U","created_at":"2026-07-05T10:36:40.561230+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/34ONMB5U3IEQ3WK4BMDMHDSSP3","json":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3.json","graph_json":"https://pith.science/api/pith-number/34ONMB5U3IEQ3WK4BMDMHDSSP3/graph.json","events_json":"https://pith.science/api/pith-number/34ONMB5U3IEQ3WK4BMDMHDSSP3/events.json","paper":"https://pith.science/paper/34ONMB5U"},"agent_actions":{"view_html":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3","download_json":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3.json","view_paper":"https://pith.science/paper/34ONMB5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16432&json=true","fetch_graph":"https://pith.science/api/pith-number/34ONMB5U3IEQ3WK4BMDMHDSSP3/graph.json","fetch_events":"https://pith.science/api/pith-number/34ONMB5U3IEQ3WK4BMDMHDSSP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3/action/storage_attestation","attest_author":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3/action/author_attestation","sign_citation":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3/action/citation_signature","submit_replication":"https://pith.science/pith/34ONMB5U3IEQ3WK4BMDMHDSSP3/action/replication_record"}},"created_at":"2026-07-05T10:36:40.561230+00:00","updated_at":"2026-07-05T10:36:40.561230+00:00"}