{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6SH3EZWMAWBT3ODQEXMG4ACQT6","short_pith_number":"pith:6SH3EZWM","schema_version":"1.0","canonical_sha256":"f48fb266cc05833db87025d86e00509fb7bceec177d43da6986ca40a0077a477","source":{"kind":"arxiv","id":"2404.02887","version":2},"attestation_state":"computed","paper":{"title":"Learning Deployable Locomotion Control via Differentiable Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Clemens Schwarke, Ignat Georgiev, Jean-Pierre Sleiman, Jesus Tordesillas, Joshua Bagajo, Marco Hutter, Victor Klemm","submitted_at":"2024-04-03T17:42:22Z","abstract_excerpt":"Differentiable simulators promise to improve sample efficiency in robot learning by providing analytic gradients of the system dynamics. Yet, their application to contact-rich tasks like locomotion is complicated by the inherently non-smooth nature of contact, impeding effective gradient-based optimization. Existing works thus often rely on soft contact models that provide smooth gradients but lack physical accuracy, constraining results to simulation. To address this limitation, we propose a differentiable contact model designed to provide informative gradients while maintaining high physical"},"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":"2404.02887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-03T17:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"77afc2c7336dba17816a90c00970457c93f33c71db30b6701424f5d244e520fd","abstract_canon_sha256":"d9d698873ca9fdc3e98db830a9d0c714a151ec8f791e93ca806da84eaeb6e6d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:51.957521Z","signature_b64":"YbxEwSwrRWqdZ3T7KI02e5ggG+8vQWlGV1yBcPuEJUc28h/JCGXWyvrb64Il2P5RNqiKbNsu/WtbkJNJBdqgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48fb266cc05833db87025d86e00509fb7bceec177d43da6986ca40a0077a477","last_reissued_at":"2026-07-05T11:59:51.957036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:51.957036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deployable Locomotion Control via Differentiable Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Clemens Schwarke, Ignat Georgiev, Jean-Pierre Sleiman, Jesus Tordesillas, Joshua Bagajo, Marco Hutter, Victor Klemm","submitted_at":"2024-04-03T17:42:22Z","abstract_excerpt":"Differentiable simulators promise to improve sample efficiency in robot learning by providing analytic gradients of the system dynamics. Yet, their application to contact-rich tasks like locomotion is complicated by the inherently non-smooth nature of contact, impeding effective gradient-based optimization. Existing works thus often rely on soft contact models that provide smooth gradients but lack physical accuracy, constraining results to simulation. To address this limitation, we propose a differentiable contact model designed to provide informative gradients while maintaining high physical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02887","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/2404.02887/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":"2404.02887","created_at":"2026-07-05T11:59:51.957094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02887v2","created_at":"2026-07-05T11:59:51.957094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02887","created_at":"2026-07-05T11:59:51.957094+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SH3EZWMAWBT","created_at":"2026-07-05T11:59:51.957094+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SH3EZWMAWBT3ODQ","created_at":"2026-07-05T11:59:51.957094+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SH3EZWM","created_at":"2026-07-05T11:59:51.957094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26478","citing_title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18161","citing_title":"Does \"Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6","json":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6.json","graph_json":"https://pith.science/api/pith-number/6SH3EZWMAWBT3ODQEXMG4ACQT6/graph.json","events_json":"https://pith.science/api/pith-number/6SH3EZWMAWBT3ODQEXMG4ACQT6/events.json","paper":"https://pith.science/paper/6SH3EZWM"},"agent_actions":{"view_html":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6","download_json":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6.json","view_paper":"https://pith.science/paper/6SH3EZWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02887&json=true","fetch_graph":"https://pith.science/api/pith-number/6SH3EZWMAWBT3ODQEXMG4ACQT6/graph.json","fetch_events":"https://pith.science/api/pith-number/6SH3EZWMAWBT3ODQEXMG4ACQT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6/action/storage_attestation","attest_author":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6/action/author_attestation","sign_citation":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6/action/citation_signature","submit_replication":"https://pith.science/pith/6SH3EZWMAWBT3ODQEXMG4ACQT6/action/replication_record"}},"created_at":"2026-07-05T11:59:51.957094+00:00","updated_at":"2026-07-05T11:59:51.957094+00:00"}