{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ARNGBKZVA7SWC4B7QSJHFSE3O7","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":"d7bea07310535f620dd27a58d4e24d9f3fb372b6eb278b6fb1288da2beeea5ef","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T02:52:02Z","title_canon_sha256":"0232e1cb297a05444a7e6b47bdaec32a85374b4b4fcf34fab65e5c3e0cc6228b"},"schema_version":"1.0","source":{"id":"2305.12063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12063","created_at":"2026-07-05T06:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12063v1","created_at":"2026-07-05T06:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12063","created_at":"2026-07-05T06:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"ARNGBKZVA7SW","created_at":"2026-07-05T06:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"ARNGBKZVA7SWC4B7","created_at":"2026-07-05T06:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"ARNGBKZV","created_at":"2026-07-05T06:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:7d15f264d37c7fe3f1d7544008aa2145a120bcb0fc120aee5eeb3848692ece05","target":"graph","created_at":"2026-07-05T06:12:06Z","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/2305.12063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The adoption of multimodal interactions by Voice Assistants (VAs) is growing rapidly to enhance human-computer interactions. Smartwatches have now incorporated trigger-less methods of invoking VAs, such as Raise To Speak (RTS), where the user raises their watch and speaks to VAs without an explicit trigger. Current state-of-the-art RTS systems rely on heuristics and engineered Finite State Machines to fuse gesture and audio data for multimodal decision-making. However, these methods have limitations, including limited adaptability, scalability, and induced human biases. In this work, we propos","authors_text":"Ed Yanosik, Karan Sawnhey, Sai Srujana Buddi, Saravana Rathinam, Saurabh Adya, Tashweena Heeramun, Utkarsh Oggy Sarawgi","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T02:52:02Z","title":"Efficient Multimodal Neural Networks for Trigger-less Voice Assistants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12063","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":"sha256:0ae6db64cc5e216ea7c9d1511035682b5dba73170e60f74aa565c89f30b346e0","target":"record","created_at":"2026-07-05T06:12:06Z","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":"d7bea07310535f620dd27a58d4e24d9f3fb372b6eb278b6fb1288da2beeea5ef","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T02:52:02Z","title_canon_sha256":"0232e1cb297a05444a7e6b47bdaec32a85374b4b4fcf34fab65e5c3e0cc6228b"},"schema_version":"1.0","source":{"id":"2305.12063","kind":"arxiv","version":1}},"canonical_sha256":"045a60ab3507e561703f849272c89b77d2a2a22716edd6e0f668d27785129112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"045a60ab3507e561703f849272c89b77d2a2a22716edd6e0f668d27785129112","first_computed_at":"2026-07-05T06:12:06.115492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:06.115492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GRfTxXmw/4tiUTGo9C6Z8n3rStwoS+CJ/WEZwsbkK11g7reHGTiRM1UQk0gqjuSEyLbsq6eNx0V65+hBY/CSCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:06.115826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ae6db64cc5e216ea7c9d1511035682b5dba73170e60f74aa565c89f30b346e0","sha256:7d15f264d37c7fe3f1d7544008aa2145a120bcb0fc120aee5eeb3848692ece05"],"state_sha256":"75ebb712d613fbf045562f5cabfc55956f8efa97402fa3340f32b597fb1b3230"}