{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PC7G3PDYUIDFL4PG54ZVCSYHKC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5f94d81c2cc03224f7fc2f93b91773eea8975cf8d088aced01e349be2afb0e8b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:42:34Z","title_canon_sha256":"0f479accce3166f9ce9cedd344772f5293da49b9c928f9474c0d474a6f707e4d"},"schema_version":"1.0","source":{"id":"2505.14654","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14654","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14654v2","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14654","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"PC7G3PDYUIDF","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"PC7G3PDYUIDFL4PG","created_at":"2026-05-21T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"PC7G3PDY","created_at":"2026-05-21T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:ef8942b4360b40b420b8af4997f9c7eee2d191a00b87ae9f961ca9b34b6b2fd8","target":"graph","created_at":"2026-05-21T01:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.14654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chen-Ping Yu, Yi-Hsuan Tsai, Yi-Lun Lee, Yi Ouyang, Zhaozheng Yin, Zikai Liao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:42:34Z","title":"Beyond Words: Multimodal LLM Knows When to Speak"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14654","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5114922af845607d5691e9d49465bcddba56b21a3107e4335ed0db7ddf494921","target":"record","created_at":"2026-05-21T01:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5f94d81c2cc03224f7fc2f93b91773eea8975cf8d088aced01e349be2afb0e8b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:42:34Z","title_canon_sha256":"0f479accce3166f9ce9cedd344772f5293da49b9c928f9474c0d474a6f707e4d"},"schema_version":"1.0","source":{"id":"2505.14654","kind":"arxiv","version":2}},"canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","first_computed_at":"2026-05-21T01:04:14.007408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:14.007408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpPaE5q+b9D9pzm3bRhgKtrMwuViAtLfhVggUghtHqgGmNtgHexuNvli047wGiBcodFMfx8rmf58q0Xmgx0GCg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:14.008112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14654","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5114922af845607d5691e9d49465bcddba56b21a3107e4335ed0db7ddf494921","sha256:ef8942b4360b40b420b8af4997f9c7eee2d191a00b87ae9f961ca9b34b6b2fd8"],"state_sha256":"c7979651c1e82d60ae73db51fc478748b931dfd3e28c7ec5afc2e4c6762f97a0"}