{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NFYDEDVICDUTJ3APSHFGBBI6AC","short_pith_number":"pith:NFYDEDVI","schema_version":"1.0","canonical_sha256":"6970320ea810e934ec0f91ca60851e00a083112a37f2e1066428d06b0f3053b8","source":{"kind":"arxiv","id":"2106.13281","version":1},"attestation_state":"computed","paper":{"title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Anton Raichuk, C. Daniel Freeman, Erik Frey, Igor Mordatch, Olivier Bachem, Sertan Girgin","submitted_at":"2021-06-24T19:09:12Z","abstract_excerpt":"We present Brax, an open source library for rigid body simulation with a focus on performance and parallelism on accelerators, written in JAX. We present results on a suite of tasks inspired by the existing reinforcement learning literature, but remade in our engine. Additionally, we provide reimplementations of PPO, SAC, ES, and direct policy optimization in JAX that compile alongside our environments, allowing the learning algorithm and the environment processing to occur on the same device, and to scale seamlessly on accelerators. Finally, we include notebooks that facilitate training of pe"},"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":"2106.13281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-06-24T19:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7649156f722501771f0fdeadb18f2c9b8a789b9d3c969da81df211bd4cb78f9a","abstract_canon_sha256":"8caf075f9b1855de1ffe72682446bc1a10e50de06d7706affa5329782fa1d6f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:17.814819Z","signature_b64":"Ueey+JqZURIacE2iQcqmmjUQbe3A/j7rRqEAMqR09pXRKRV+VwXmRtd2As3DSDA6sFIJShQvcAetRZBpMrf/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6970320ea810e934ec0f91ca60851e00a083112a37f2e1066428d06b0f3053b8","last_reissued_at":"2026-07-05T02:52:17.814394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:17.814394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Anton Raichuk, C. Daniel Freeman, Erik Frey, Igor Mordatch, Olivier Bachem, Sertan Girgin","submitted_at":"2021-06-24T19:09:12Z","abstract_excerpt":"We present Brax, an open source library for rigid body simulation with a focus on performance and parallelism on accelerators, written in JAX. We present results on a suite of tasks inspired by the existing reinforcement learning literature, but remade in our engine. Additionally, we provide reimplementations of PPO, SAC, ES, and direct policy optimization in JAX that compile alongside our environments, allowing the learning algorithm and the environment processing to occur on the same device, and to scale seamlessly on accelerators. Finally, we include notebooks that facilitate training of pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13281","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/2106.13281/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":"2106.13281","created_at":"2026-07-05T02:52:17.814451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13281v1","created_at":"2026-07-05T02:52:17.814451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13281","created_at":"2026-07-05T02:52:17.814451+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFYDEDVICDUT","created_at":"2026-07-05T02:52:17.814451+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFYDEDVICDUTJ3AP","created_at":"2026-07-05T02:52:17.814451+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFYDEDVI","created_at":"2026-07-05T02:52:17.814451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":34,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":250,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26341","citing_title":"Scaling Nonlinear Optimization: Many Problems One GPU","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22447","citing_title":"A Differentiable Atari VCS:A Complex, Fully Known Ground Truth for Explainable AI","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21525","citing_title":"Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06094","citing_title":"Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00442","citing_title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04749","citing_title":"COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24922","citing_title":"MuJoCoUni:Persistent Batched Runtime Primitives for MuJoCo","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31700","citing_title":"Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03288","citing_title":"Neural Control: Adjoint Learning Through Equilibrium Constraints","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14911","citing_title":"Chrono-Gymnasium: An Open-Source, Gymnasium-Compatible Distributed Simulation Framework","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29201","citing_title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30313","citing_title":"UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31120","citing_title":"SWIM: Single-Instance Whole-Body Imitation for swiMming","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14009","citing_title":"GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12633","citing_title":"Real-to-Sim for Highly Cluttered Environments via Physics-Consistent Inter-Object Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12145","citing_title":"Automatic Generation of High-Performance RL Environments","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19503","citing_title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20576","citing_title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19503","citing_title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14297","citing_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21456","citing_title":"Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC","json":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC.json","graph_json":"https://pith.science/api/pith-number/NFYDEDVICDUTJ3APSHFGBBI6AC/graph.json","events_json":"https://pith.science/api/pith-number/NFYDEDVICDUTJ3APSHFGBBI6AC/events.json","paper":"https://pith.science/paper/NFYDEDVI"},"agent_actions":{"view_html":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC","download_json":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC.json","view_paper":"https://pith.science/paper/NFYDEDVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13281&json=true","fetch_graph":"https://pith.science/api/pith-number/NFYDEDVICDUTJ3APSHFGBBI6AC/graph.json","fetch_events":"https://pith.science/api/pith-number/NFYDEDVICDUTJ3APSHFGBBI6AC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC/action/storage_attestation","attest_author":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC/action/author_attestation","sign_citation":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC/action/citation_signature","submit_replication":"https://pith.science/pith/NFYDEDVICDUTJ3APSHFGBBI6AC/action/replication_record"}},"created_at":"2026-07-05T02:52:17.814451+00:00","updated_at":"2026-07-05T02:52:17.814451+00:00"}