{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PC7G3PDYUIDFL4PG54ZVCSYHKC","short_pith_number":"pith:PC7G3PDY","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"},"canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","source":{"kind":"arxiv","id":"2505.14654","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PC7G3PDYUIDFL4PG54ZVCSYHKC","target":"record","payload":{"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"},"canonical_sha256":"78be6dbc78a20655f1e6ef33514b0750ac44264818623a23db69dc3e91be2ab5","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"},"source_kind":"arxiv","source_id":"2505.14654","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y29a/I4VaKCy4lnl/AACPXhZZWJcNKKDmYy1whGIZytbXxAOQHaIAD6+klIxdQ1AM8zwdp4hMM2AW0a5ikpnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:52:39.076009Z"},"content_sha256":"5114922af845607d5691e9d49465bcddba56b21a3107e4335ed0db7ddf494921","schema_version":"1.0","event_id":"sha256:5114922af845607d5691e9d49465bcddba56b21a3107e4335ed0db7ddf494921"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PC7G3PDYUIDFL4PG54ZVCSYHKC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n37AZrN69VagBe078WmZTCfMVt1TwMwwT3qABmbaORgEHf12YfHC6z+SBaGxLFhVB7jVny+Xdo4F0LCc298BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:52:39.076512Z"},"content_sha256":"ef8942b4360b40b420b8af4997f9c7eee2d191a00b87ae9f961ca9b34b6b2fd8","schema_version":"1.0","event_id":"sha256:ef8942b4360b40b420b8af4997f9c7eee2d191a00b87ae9f961ca9b34b6b2fd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/bundle.json","state_url":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T01:52:39Z","links":{"resolver":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC","bundle":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/bundle.json","state":"https://pith.science/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PC7G3PDYUIDFL4PG54ZVCSYHKC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pSHyFt8bodfaC8ITb0+Y5QGZOZiJL+OnZaEnT3cImjYJN+zrKl4OQucoueb9zJ8IjUEV1JMMGSKCsSsvY/HVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:52:39.079957Z","bundle_sha256":"ade6e4522e875e8d25afc0606d4f3622544a872ef97ab5d87dd8bdcccc21fcc8"}}