{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QTSIWULW5I6ZLDYADAFJDY3PYT","short_pith_number":"pith:QTSIWULW","schema_version":"1.0","canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","source":{"kind":"arxiv","id":"2607.14675","version":1},"attestation_state":"computed","paper":{"title":"An Intelligent-Cloud Edge Multimodal Interaction System for Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Xiaoqi Li, Zihan Guo","submitted_at":"2026-07-16T07:39:18Z","abstract_excerpt":"Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task planning under limited onboard computing resources. This paper presents a cloud-edge multimodal interaction framework that integrates an enhanced YOLO-based gesture detector with coordinated large language model (LLM) and vision-language model (VLM) agents. The proposed detector, incorporates the Convolutional Block Attention Module (CBAM) into the neck and replaces the baseline bounding-box regression objective with Distance-IoU (DIoU) loss. These modifi"},"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":"2607.14675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-16T07:39:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbb1274f37e76ef35cb6b5db28ea0fe3462afb2e071c8487096cd2a4f3531259","abstract_canon_sha256":"ad9d4a37fcfc086ad3a95c33324326b8b9824d284eec59873eb113fd67d355cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:24.390388Z","signature_b64":"cM8qv50jEYmPo2mfTOoKRYEOofIiIsZHyDD1GVYxAPhJ6GgAW+ASAHVQZbX8LJQkvAgp8lFF0kYS0Ak/h5v7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","last_reissued_at":"2026-07-17T01:21:24.389336Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:24.389336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Intelligent-Cloud Edge Multimodal Interaction System for Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Xiaoqi Li, Zihan Guo","submitted_at":"2026-07-16T07:39:18Z","abstract_excerpt":"Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task planning under limited onboard computing resources. This paper presents a cloud-edge multimodal interaction framework that integrates an enhanced YOLO-based gesture detector with coordinated large language model (LLM) and vision-language model (VLM) agents. The proposed detector, incorporates the Convolutional Block Attention Module (CBAM) into the neck and replaces the baseline bounding-box regression objective with Distance-IoU (DIoU) loss. These modifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14675","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/2607.14675/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":"2607.14675","created_at":"2026-07-17T01:21:24.389777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14675v1","created_at":"2026-07-17T01:21:24.389777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14675","created_at":"2026-07-17T01:21:24.389777+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTSIWULW5I6Z","created_at":"2026-07-17T01:21:24.389777+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTSIWULW5I6ZLDYA","created_at":"2026-07-17T01:21:24.389777+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTSIWULW","created_at":"2026-07-17T01:21:24.389777+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/QTSIWULW5I6ZLDYADAFJDY3PYT","json":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT.json","graph_json":"https://pith.science/api/pith-number/QTSIWULW5I6ZLDYADAFJDY3PYT/graph.json","events_json":"https://pith.science/api/pith-number/QTSIWULW5I6ZLDYADAFJDY3PYT/events.json","paper":"https://pith.science/paper/QTSIWULW"},"agent_actions":{"view_html":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT","download_json":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT.json","view_paper":"https://pith.science/paper/QTSIWULW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14675&json=true","fetch_graph":"https://pith.science/api/pith-number/QTSIWULW5I6ZLDYADAFJDY3PYT/graph.json","fetch_events":"https://pith.science/api/pith-number/QTSIWULW5I6ZLDYADAFJDY3PYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/action/storage_attestation","attest_author":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/action/author_attestation","sign_citation":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/action/citation_signature","submit_replication":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/action/replication_record"}},"created_at":"2026-07-17T01:21:24.389777+00:00","updated_at":"2026-07-17T01:21:24.389777+00:00"}