{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PV3A3LJUNP6WL3ZIGQ2DOGCCMV","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":"d313dad81784b7dad19fee70d99a45eeda0d031d4795eb94100613be03395769","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T08:59:07Z","title_canon_sha256":"a43790738d2248dcbf71f4185e4d4f8f115c0212c72cd3fb662c513d13a1c448"},"schema_version":"1.0","source":{"id":"2401.14717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14717","created_at":"2026-07-05T07:38:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14717v1","created_at":"2026-07-05T07:38:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14717","created_at":"2026-07-05T07:38:00Z"},{"alias_kind":"pith_short_12","alias_value":"PV3A3LJUNP6W","created_at":"2026-07-05T07:38:00Z"},{"alias_kind":"pith_short_16","alias_value":"PV3A3LJUNP6WL3ZI","created_at":"2026-07-05T07:38:00Z"},{"alias_kind":"pith_short_8","alias_value":"PV3A3LJU","created_at":"2026-07-05T07:38:00Z"}],"graph_snapshots":[{"event_id":"sha256:c0a1578f222ba68be86b57c73ae61d31b7414ca162ce0b8e624a1f25ae680015","target":"graph","created_at":"2026-07-05T07:38:00Z","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/2401.14717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation dataset demonstrate that our approach consistently outperforms the baseline models with single modality. We also develop a novel multi-task instruction fine-tuning strategy to further benefit from LLM-encoded knowledge for understanding the tasks and conversational contexts, leading to additional improvements. Our approach demonstrates the potential of combined","authors_text":"Andreas Stolcke, Anirudh Raju, Aparna Khare, Di He, Jinhan Wang, Long Chen, Minhua Wu, Pranav Dheram, Venkatesh Ravichandran","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T08:59:07Z","title":"Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14717","kind":"arxiv","version":1},"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:b140bfc979bb42ccf44885a520c9c22794fb8c37996c030cddea799f2e5dc68f","target":"record","created_at":"2026-07-05T07:38:00Z","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":"d313dad81784b7dad19fee70d99a45eeda0d031d4795eb94100613be03395769","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T08:59:07Z","title_canon_sha256":"a43790738d2248dcbf71f4185e4d4f8f115c0212c72cd3fb662c513d13a1c448"},"schema_version":"1.0","source":{"id":"2401.14717","kind":"arxiv","version":1}},"canonical_sha256":"7d760dad346bfd65ef28343437184265665c208307485217672a93d459873a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d760dad346bfd65ef28343437184265665c208307485217672a93d459873a1d","first_computed_at":"2026-07-05T07:38:00.909085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:00.909085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UgkPTRet/S99ECFI1IuQKHzqK9ApFlo/hzLGMBT4mTNhVUh+QQfkoUvqFZj1BuJer1HzT27Tx6wGB9RiDC+3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:00.909499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b140bfc979bb42ccf44885a520c9c22794fb8c37996c030cddea799f2e5dc68f","sha256:c0a1578f222ba68be86b57c73ae61d31b7414ca162ce0b8e624a1f25ae680015"],"state_sha256":"f780debe7845b06631492303793cdaf55740a503f61c7bd23d62195cdeac6df9"}