{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XVUEMXAUQVQC4NG53CRMIHYLMC","short_pith_number":"pith:XVUEMXAU","schema_version":"1.0","canonical_sha256":"bd68465c1485602e34ddd8a2c41f0b60b42805af7b2e83d7632d1f4412306005","source":{"kind":"arxiv","id":"2606.31158","version":1},"attestation_state":"computed","paper":{"title":"LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ranjan Dasgupta, Snehasis Banerjee","submitted_at":"2026-06-30T05:35:26Z","abstract_excerpt":"The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid, pre-programmed commands that limit the robot's expressiveness and adaptability. This paper introduces a novel framework that leverages the reasoning capabilities of Large Language Models (LLMs) to synthesize complex robotic actions from a rich tapestry of multimodal human inputs: natural speech, hand gestures, and music/sound beats. Our system architecture integrates a speech transcription model, a gesture recognition module, and a signal proce"},"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":"2606.31158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T05:35:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ef008c57e9c481a3a91bd4d322786ac6231df35ac970c092c815e4b17f4e555","abstract_canon_sha256":"4ece7d4181172e049ef73d657bfc15294023eff3724193cc7448c37885ff165e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:30.818416Z","signature_b64":"VlaViPC23ijhDAQc3CKhCtTbGw+1CkfmBbJsUwmqLp1FrYUKFitPoNm/LfDDYP2sJsAcuGrurL651seYzeCNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd68465c1485602e34ddd8a2c41f0b60b42805af7b2e83d7632d1f4412306005","last_reissued_at":"2026-07-01T01:17:30.817839Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:30.817839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ranjan Dasgupta, Snehasis Banerjee","submitted_at":"2026-06-30T05:35:26Z","abstract_excerpt":"The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid, pre-programmed commands that limit the robot's expressiveness and adaptability. This paper introduces a novel framework that leverages the reasoning capabilities of Large Language Models (LLMs) to synthesize complex robotic actions from a rich tapestry of multimodal human inputs: natural speech, hand gestures, and music/sound beats. Our system architecture integrates a speech transcription model, a gesture recognition module, and a signal proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31158","kind":"arxiv","version":1},"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/2606.31158/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":"2606.31158","created_at":"2026-07-01T01:17:30.817925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31158v1","created_at":"2026-07-01T01:17:30.817925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31158","created_at":"2026-07-01T01:17:30.817925+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVUEMXAUQVQC","created_at":"2026-07-01T01:17:30.817925+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVUEMXAUQVQC4NG5","created_at":"2026-07-01T01:17:30.817925+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVUEMXAU","created_at":"2026-07-01T01:17:30.817925+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/XVUEMXAUQVQC4NG53CRMIHYLMC","json":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC.json","graph_json":"https://pith.science/api/pith-number/XVUEMXAUQVQC4NG53CRMIHYLMC/graph.json","events_json":"https://pith.science/api/pith-number/XVUEMXAUQVQC4NG53CRMIHYLMC/events.json","paper":"https://pith.science/paper/XVUEMXAU"},"agent_actions":{"view_html":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC","download_json":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC.json","view_paper":"https://pith.science/paper/XVUEMXAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31158&json=true","fetch_graph":"https://pith.science/api/pith-number/XVUEMXAUQVQC4NG53CRMIHYLMC/graph.json","fetch_events":"https://pith.science/api/pith-number/XVUEMXAUQVQC4NG53CRMIHYLMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC/action/storage_attestation","attest_author":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC/action/author_attestation","sign_citation":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC/action/citation_signature","submit_replication":"https://pith.science/pith/XVUEMXAUQVQC4NG53CRMIHYLMC/action/replication_record"}},"created_at":"2026-07-01T01:17:30.817925+00:00","updated_at":"2026-07-01T01:17:30.817925+00:00"}