{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PC7G3PDYUIDFL4PG54ZVCSYHKC","short_pith_number":"pith:PC7G3PDY","schema_version":"1.0","canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","source":{"kind":"arxiv","id":"2505.14654","version":2},"attestation_state":"computed","paper":{"title":"Beyond Words: Multimodal LLM Knows When to Speak","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen-Ping Yu, Yi-Hsuan Tsai, Yi-Lun Lee, Yi Ouyang, Zhaozheng Yin, Zikai Liao","submitted_at":"2025-05-20T17:42:34Z","abstract_excerpt":"Chatbots via large language models (LLMs) generate fluent responses but often struggle with when to speak, especially for brief, timely listener reactions during ongoing dialogue. We present a multimodal strategy for LLMs, which leverages synchronized video, audio, and text cues to improve conversational timing awareness. The strategy reformulates response timing as a dense response-type prediction task, enabling an agent to decide whether to remain silent, produce a short reaction, or start a full response under streaming constraints. Therefore, we introduce a curated multimodal dataset from "},"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":"2505.14654","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:42:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0f479accce3166f9ce9cedd344772f5293da49b9c928f9474c0d474a6f707e4d","abstract_canon_sha256":"5f94d81c2cc03224f7fc2f93b91773eea8975cf8d088aced01e349be2afb0e8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:14.008112Z","signature_b64":"kpPaE5q+b9D9pzm3bRhgKtrMwuViAtLfhVggUghtHqgGmNtgHexuNvli047wGiBcodFMfx8rmf58q0Xmgx0GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","last_reissued_at":"2026-05-21T01:04:14.007408Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:14.007408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Words: Multimodal LLM Knows When to Speak","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen-Ping Yu, Yi-Hsuan Tsai, Yi-Lun Lee, Yi Ouyang, Zhaozheng Yin, Zikai Liao","submitted_at":"2025-05-20T17:42:34Z","abstract_excerpt":"Chatbots via large language models (LLMs) generate fluent responses but often struggle with when to speak, especially for brief, timely listener reactions during ongoing dialogue. We present a multimodal strategy for LLMs, which leverages synchronized video, audio, and text cues to improve conversational timing awareness. The strategy reformulates response timing as a dense response-type prediction task, enabling an agent to decide whether to remain silent, produce a short reaction, or start a full response under streaming constraints. Therefore, we introduce a curated multimodal dataset from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14654","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/2505.14654/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":"2505.14654","created_at":"2026-05-21T01:04:14.007513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14654v2","created_at":"2026-05-21T01:04:14.007513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14654","created_at":"2026-05-21T01:04:14.007513+00:00"},{"alias_kind":"pith_short_12","alias_value":"PC7G3PDYUIDF","created_at":"2026-05-21T01:04:14.007513+00:00"},{"alias_kind":"pith_short_16","alias_value":"PC7G3PDYUIDFL4PG","created_at":"2026-05-21T01:04:14.007513+00:00"},{"alias_kind":"pith_short_8","alias_value":"PC7G3PDY","created_at":"2026-05-21T01:04:14.007513+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/PC7G3PDYUIDFL4PG54ZVCSYHKC","json":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC.json","graph_json":"https://pith.science/api/pith-number/PC7G3PDYUIDFL4PG54ZVCSYHKC/graph.json","events_json":"https://pith.science/api/pith-number/PC7G3PDYUIDFL4PG54ZVCSYHKC/events.json","paper":"https://pith.science/paper/PC7G3PDY"},"agent_actions":{"view_html":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC","download_json":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC.json","view_paper":"https://pith.science/paper/PC7G3PDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14654&json=true","fetch_graph":"https://pith.science/api/pith-number/PC7G3PDYUIDFL4PG54ZVCSYHKC/graph.json","fetch_events":"https://pith.science/api/pith-number/PC7G3PDYUIDFL4PG54ZVCSYHKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/action/storage_attestation","attest_author":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/action/author_attestation","sign_citation":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/action/citation_signature","submit_replication":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/action/replication_record"}},"created_at":"2026-05-21T01:04:14.007513+00:00","updated_at":"2026-05-21T01:04:14.007513+00:00"}