{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KMUXNCI4AGMBRVUKX56YGD4H4J","short_pith_number":"pith:KMUXNCI4","schema_version":"1.0","canonical_sha256":"532976891c019818d68abf7d830f87e243119c3ab38a1a2d24cc0ab7e06a8274","source":{"kind":"arxiv","id":"1910.00935","version":3},"attestation_state":"computed","paper":{"title":"DiffTaichi: Differentiable Programming for Physical Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fr\\'edo Durand, Jonathan Ragan-Kelley, Luke Anderson, Nathan Carr, Qi Sun, Tzu-Mao Li, Yuanming Hu","submitted_at":"2019-10-01T05:00:26Z","abstract_excerpt":"We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Based on an imperative programming language, DiffTaichi generates gradients of simulation steps using source code transformations that preserve arithmetic intensity and parallelism. A light-weight tape is used to record the whole simulation program structure and replay the gradient kernels in a reversed order, for end-to-end backpropagation. We demonstrate the performance and productivity of our language in gradient-based learning and optimization tasks on"},"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":"1910.00935","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-01T05:00:26Z","cross_cats_sorted":["cs.GR","physics.comp-ph","stat.ML"],"title_canon_sha256":"94f0e83815d1e027efe9463c51bd96c70adf9691f4ada0ea77b95ab10723a487","abstract_canon_sha256":"34868e41a0ed480e1b5c5532da8e3c093bc43a9aa1e313f06fb03a885bb4843a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:44.742152Z","signature_b64":"OBDdSqXJiVgG6hpvre33xizB42dMMxGRrnsVQKNiAc5nQgNWB21HdTK5JrHmb5IdOioi5GtrSVDppJ8DdMyzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"532976891c019818d68abf7d830f87e243119c3ab38a1a2d24cc0ab7e06a8274","last_reissued_at":"2026-07-05T00:40:44.741658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:44.741658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffTaichi: Differentiable Programming for Physical Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fr\\'edo Durand, Jonathan Ragan-Kelley, Luke Anderson, Nathan Carr, Qi Sun, Tzu-Mao Li, Yuanming Hu","submitted_at":"2019-10-01T05:00:26Z","abstract_excerpt":"We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Based on an imperative programming language, DiffTaichi generates gradients of simulation steps using source code transformations that preserve arithmetic intensity and parallelism. A light-weight tape is used to record the whole simulation program structure and replay the gradient kernels in a reversed order, for end-to-end backpropagation. We demonstrate the performance and productivity of our language in gradient-based learning and optimization tasks on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00935","kind":"arxiv","version":3},"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/1910.00935/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":"1910.00935","created_at":"2026-07-05T00:40:44.741715+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.00935v3","created_at":"2026-07-05T00:40:44.741715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00935","created_at":"2026-07-05T00:40:44.741715+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMUXNCI4AGMB","created_at":"2026-07-05T00:40:44.741715+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMUXNCI4AGMBRVUK","created_at":"2026-07-05T00:40:44.741715+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMUXNCI4","created_at":"2026-07-05T00:40:44.741715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10596","citing_title":"Embedding Hybrid Systems into Continuous Latent Vector Fields","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07681","citing_title":"Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model","ref_index":8,"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":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05328","citing_title":"The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03210","citing_title":"Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03288","citing_title":"Neural Control: Adjoint Learning Through Equilibrium Constraints","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06779","citing_title":"Exploring the Boundaries of Differentiable Radiation Transport and Detector Simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31481","citing_title":"Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23458","citing_title":"A matrix-free, differentiable PyTorch solver for phase-field fracture: Formulation, benchmarks, and inverse analysis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16478","citing_title":"Fast and Reliable Gradients for Deformables Across Frictional Contact Regimes","ref_index":13,"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":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21138","citing_title":"Safety-Critical Control for Smoothed Implicit Contact Dynamics","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16988","citing_title":"PhysMorph-GS: Render-Guided Volumetric Morphing with Differentiable Physics","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14297","citing_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12654","citing_title":"COSMIC: Concurrent Optimization of Structure, Material, and Integrated Control for robotic systems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09196","citing_title":"RigidFormer: Learning Rigid Dynamics using Transformers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03288","citing_title":"Neural Control: Adjoint Learning Through Equilibrium Constraints","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06779","citing_title":"Exploring the Boundaries of Differentiable Radiation Transport and Detector Simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06896","citing_title":"VertAX: a differentiable vertex model for learning epithelial tissue mechanics","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19062","citing_title":"Differentiable Satellite Constellation Configuration via Relaxed Coverage and Revisit Objectives","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J","json":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J.json","graph_json":"https://pith.science/api/pith-number/KMUXNCI4AGMBRVUKX56YGD4H4J/graph.json","events_json":"https://pith.science/api/pith-number/KMUXNCI4AGMBRVUKX56YGD4H4J/events.json","paper":"https://pith.science/paper/KMUXNCI4"},"agent_actions":{"view_html":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J","download_json":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J.json","view_paper":"https://pith.science/paper/KMUXNCI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.00935&json=true","fetch_graph":"https://pith.science/api/pith-number/KMUXNCI4AGMBRVUKX56YGD4H4J/graph.json","fetch_events":"https://pith.science/api/pith-number/KMUXNCI4AGMBRVUKX56YGD4H4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J/action/storage_attestation","attest_author":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J/action/author_attestation","sign_citation":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J/action/citation_signature","submit_replication":"https://pith.science/pith/KMUXNCI4AGMBRVUKX56YGD4H4J/action/replication_record"}},"created_at":"2026-07-05T00:40:44.741715+00:00","updated_at":"2026-07-05T00:40:44.741715+00:00"}