{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SB7R64KOKBAUEI4UNV64ME6BNT","short_pith_number":"pith:SB7R64KO","schema_version":"1.0","canonical_sha256":"907f1f714e50414223946d7dc613c16cc36bbdf52f1a72b5f5a61c4b97e937f0","source":{"kind":"arxiv","id":"2306.09537","version":1},"attestation_state":"computed","paper":{"title":"QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Aleksei Petrenko, Artem Molchanov, Gaurav S. Sukhatme, James A. Preiss, Rahul Krupani, Sumeet Batra, Tao Chen, Tushar Kumar, Zhaojing Yang, Zhehui Huang","submitted_at":"2023-06-15T22:46:20Z","abstract_excerpt":"Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for q"},"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":"2306.09537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-15T22:46:20Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"fee1fbb19b626fbcdbcd081500a2245601b7ff0a01f197c3ee84cc23d65c1629","abstract_canon_sha256":"6d1ff438cc903fa725c3b4dd832321f99f8d867e8fff400a78f2b98245d25382"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:20.921741Z","signature_b64":"ZVmt6iONZxpI73E0cqjCJuYHb6MZsAJXIPuj8edu9pZMPx34IB3OrBu2MAEp9vcDejhU849S4dGQk9XrW6P/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907f1f714e50414223946d7dc613c16cc36bbdf52f1a72b5f5a61c4b97e937f0","last_reissued_at":"2026-07-05T06:21:20.921333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:20.921333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Aleksei Petrenko, Artem Molchanov, Gaurav S. Sukhatme, James A. Preiss, Rahul Krupani, Sumeet Batra, Tao Chen, Tushar Kumar, Zhaojing Yang, Zhehui Huang","submitted_at":"2023-06-15T22:46:20Z","abstract_excerpt":"Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09537","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/2306.09537/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":"2306.09537","created_at":"2026-07-05T06:21:20.921387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09537v1","created_at":"2026-07-05T06:21:20.921387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09537","created_at":"2026-07-05T06:21:20.921387+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB7R64KOKBAU","created_at":"2026-07-05T06:21:20.921387+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB7R64KOKBAUEI4U","created_at":"2026-07-05T06:21:20.921387+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB7R64KO","created_at":"2026-07-05T06:21:20.921387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11489","citing_title":"Steering Multirobot Behavior via Closed-Loop Affine Activation Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01478","citing_title":"Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT","json":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT.json","graph_json":"https://pith.science/api/pith-number/SB7R64KOKBAUEI4UNV64ME6BNT/graph.json","events_json":"https://pith.science/api/pith-number/SB7R64KOKBAUEI4UNV64ME6BNT/events.json","paper":"https://pith.science/paper/SB7R64KO"},"agent_actions":{"view_html":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT","download_json":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT.json","view_paper":"https://pith.science/paper/SB7R64KO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09537&json=true","fetch_graph":"https://pith.science/api/pith-number/SB7R64KOKBAUEI4UNV64ME6BNT/graph.json","fetch_events":"https://pith.science/api/pith-number/SB7R64KOKBAUEI4UNV64ME6BNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT/action/storage_attestation","attest_author":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT/action/author_attestation","sign_citation":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT/action/citation_signature","submit_replication":"https://pith.science/pith/SB7R64KOKBAUEI4UNV64ME6BNT/action/replication_record"}},"created_at":"2026-07-05T06:21:20.921387+00:00","updated_at":"2026-07-05T06:21:20.921387+00:00"}