{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UH5DOWPIYFBL7HRPZ75EBDF7HW","short_pith_number":"pith:UH5DOWPI","schema_version":"1.0","canonical_sha256":"a1fa3759e8c142bf9e2fcffa408cbf3daf47fd625b5e6720a085cdb541b7ee90","source":{"kind":"arxiv","id":"2106.13358","version":2},"attestation_state":"computed","paper":{"title":"Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alejandro Ribeiro, Brian M. Sadler, Fernando Gama, Tianlong Chen, Ting-Kuei Hu, Wenqing Zheng, Zhangyang Wang","submitted_at":"2021-06-24T23:57:21Z","abstract_excerpt":"In this paper, we present a perception-action-communication loop design using Vision-based Graph Aggregation and Inference (VGAI). This multi-agent decentralized learning-to-control framework maps raw visual observations to agent actions, aided by local communication among neighboring agents. Our framework is implemented by a cascade of a convolutional and a graph neural network (CNN / GNN), addressing agent-level visual perception and feature learning, as well as swarm-level communication, local information aggregation and agent action inference, respectively. By jointly training the CNN and "},"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":"2106.13358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-24T23:57:21Z","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SP","eess.SY"],"title_canon_sha256":"987b30c43b7023d32761eff16847a2aa9bc2b237bb78e8b0eaef1dd5cba60362","abstract_canon_sha256":"c8fc4367a08c6f6c1c3c1ff5f0b058182bcb10ad48ffaa18c9f37ebbdf539a6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:17.467878Z","signature_b64":"MKZfeZNez4s/jjQDwAf2X0xIJLG6B0CjhJoEdXZ2rczgQ3WrZZUNp/06OqD7BHSmAFvWe5aUKQlOQAF/PPNqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1fa3759e8c142bf9e2fcffa408cbf3daf47fd625b5e6720a085cdb541b7ee90","last_reissued_at":"2026-07-05T03:29:17.467481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:17.467481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alejandro Ribeiro, Brian M. Sadler, Fernando Gama, Tianlong Chen, Ting-Kuei Hu, Wenqing Zheng, Zhangyang Wang","submitted_at":"2021-06-24T23:57:21Z","abstract_excerpt":"In this paper, we present a perception-action-communication loop design using Vision-based Graph Aggregation and Inference (VGAI). This multi-agent decentralized learning-to-control framework maps raw visual observations to agent actions, aided by local communication among neighboring agents. Our framework is implemented by a cascade of a convolutional and a graph neural network (CNN / GNN), addressing agent-level visual perception and feature learning, as well as swarm-level communication, local information aggregation and agent action inference, respectively. By jointly training the CNN and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13358","kind":"arxiv","version":2},"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/2106.13358/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":"2106.13358","created_at":"2026-07-05T03:29:17.467538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13358v2","created_at":"2026-07-05T03:29:17.467538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13358","created_at":"2026-07-05T03:29:17.467538+00:00"},{"alias_kind":"pith_short_12","alias_value":"UH5DOWPIYFBL","created_at":"2026-07-05T03:29:17.467538+00:00"},{"alias_kind":"pith_short_16","alias_value":"UH5DOWPIYFBL7HRP","created_at":"2026-07-05T03:29:17.467538+00:00"},{"alias_kind":"pith_short_8","alias_value":"UH5DOWPI","created_at":"2026-07-05T03:29:17.467538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21839","citing_title":"GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW","json":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW.json","graph_json":"https://pith.science/api/pith-number/UH5DOWPIYFBL7HRPZ75EBDF7HW/graph.json","events_json":"https://pith.science/api/pith-number/UH5DOWPIYFBL7HRPZ75EBDF7HW/events.json","paper":"https://pith.science/paper/UH5DOWPI"},"agent_actions":{"view_html":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW","download_json":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW.json","view_paper":"https://pith.science/paper/UH5DOWPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13358&json=true","fetch_graph":"https://pith.science/api/pith-number/UH5DOWPIYFBL7HRPZ75EBDF7HW/graph.json","fetch_events":"https://pith.science/api/pith-number/UH5DOWPIYFBL7HRPZ75EBDF7HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW/action/storage_attestation","attest_author":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW/action/author_attestation","sign_citation":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW/action/citation_signature","submit_replication":"https://pith.science/pith/UH5DOWPIYFBL7HRPZ75EBDF7HW/action/replication_record"}},"created_at":"2026-07-05T03:29:17.467538+00:00","updated_at":"2026-07-05T03:29:17.467538+00:00"}