{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QTSIWULW5I6ZLDYADAFJDY3PYT","short_pith_number":"pith:QTSIWULW","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"},"canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","source":{"kind":"arxiv","id":"2607.14675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14675","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14675v1","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14675","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"QTSIWULW5I6Z","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"QTSIWULW5I6ZLDYA","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"QTSIWULW","created_at":"2026-07-17T01:21:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QTSIWULW5I6ZLDYADAFJDY3PYT","target":"record","payload":{"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"},"canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","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"},"source_kind":"arxiv","source_id":"2607.14675","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T01:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JPKvW0jE6lNX281AGNPU8ZRBBlYNaeUrLBG0owoRL6GFpsfV1uiz20SMMMWYeEBcn39uOU+E4wE3ncjQDb6zAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:49:32.134157Z"},"content_sha256":"fa245a152741e4b9f6ef5d27e77ddfad3497de34a8ebce637114f7903a2677bf","schema_version":"1.0","event_id":"sha256:fa245a152741e4b9f6ef5d27e77ddfad3497de34a8ebce637114f7903a2677bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QTSIWULW5I6ZLDYADAFJDY3PYT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T01:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPggA4mVoSVtlErhKjqWpgHNLt7yLe3JX4HDNeb17grm08vY5E4jN/0YiDra+gi+WHojeGn+soFvyyidZRc6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:49:32.134768Z"},"content_sha256":"fa9d8bfbd9377cfde3152e5a441c77879edcd59a7a0c2bdfaa96590393794453","schema_version":"1.0","event_id":"sha256:fa9d8bfbd9377cfde3152e5a441c77879edcd59a7a0c2bdfaa96590393794453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/bundle.json","state_url":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/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":"2026-08-04T11:49:32Z","links":{"resolver":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT","bundle":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/bundle.json","state":"https://pith.science/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTSIWULW5I6ZLDYADAFJDY3PYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QTSIWULW5I6ZLDYADAFJDY3PYT","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":"ad9d4a37fcfc086ad3a95c33324326b8b9824d284eec59873eb113fd67d355cd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-16T07:39:18Z","title_canon_sha256":"fbb1274f37e76ef35cb6b5db28ea0fe3462afb2e071c8487096cd2a4f3531259"},"schema_version":"1.0","source":{"id":"2607.14675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14675","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14675v1","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14675","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"QTSIWULW5I6Z","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"QTSIWULW5I6ZLDYA","created_at":"2026-07-17T01:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"QTSIWULW","created_at":"2026-07-17T01:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:fa9d8bfbd9377cfde3152e5a441c77879edcd59a7a0c2bdfaa96590393794453","target":"graph","created_at":"2026-07-17T01:21:24Z","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/2607.14675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xiaoqi Li, Zihan Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-16T07:39:18Z","title":"An Intelligent-Cloud Edge Multimodal Interaction System for Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14675","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:fa245a152741e4b9f6ef5d27e77ddfad3497de34a8ebce637114f7903a2677bf","target":"record","created_at":"2026-07-17T01:21:24Z","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":"ad9d4a37fcfc086ad3a95c33324326b8b9824d284eec59873eb113fd67d355cd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-16T07:39:18Z","title_canon_sha256":"fbb1274f37e76ef35cb6b5db28ea0fe3462afb2e071c8487096cd2a4f3531259"},"schema_version":"1.0","source":{"id":"2607.14675","kind":"arxiv","version":1}},"canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84e48b5176ea3d958f00180a91e36fc4c6ae3e80edbbbe837a4a93c99fcfae9d","first_computed_at":"2026-07-17T01:21:24.389336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:24.389336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cM8qv50jEYmPo2mfTOoKRYEOofIiIsZHyDD1GVYxAPhJ6GgAW+ASAHVQZbX8LJQkvAgp8lFF0kYS0Ak/h5v7Ag==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:24.390388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa245a152741e4b9f6ef5d27e77ddfad3497de34a8ebce637114f7903a2677bf","sha256:fa9d8bfbd9377cfde3152e5a441c77879edcd59a7a0c2bdfaa96590393794453"],"state_sha256":"7783f3267a8a63248cb1c66bdc2214f3758d1c875074d558217aa04a52a9d9a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCtvdeu4RWcpSw5dTdnTWcxLPiAp4XzvwKSl6Yl6r53EdJscUXz2kaqZxF5oilMkvsvQIlkHmkBib5LX2ER1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:49:32.138510Z","bundle_sha256":"c069ea27dab2cd88827871d7af9c07bea1dfbe44e8c3f9bbff7af9ad9887d51a"}}