{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4CDN42IQMHDBE5N7I7QFQBDG4I","short_pith_number":"pith:4CDN42IQ","canonical_record":{"source":{"id":"2204.07137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T17:46:26Z","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"title_canon_sha256":"4cbf1c389c5c42c49cc1ee219873cf9138ae27e355a85f1a270def374a41cebb","abstract_canon_sha256":"5c5f0606fced8323ecbeef9f3e7e22d9ca75765a00fcce0999ce95928e16c477"},"schema_version":"1.0"},"canonical_sha256":"e086de691061c61275bf47e0580466e228abd966925be73383ba841bd1066923","source":{"kind":"arxiv","id":"2204.07137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07137","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07137v1","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07137","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"4CDN42IQMHDB","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"4CDN42IQMHDBE5N7","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"4CDN42IQ","created_at":"2026-07-05T04:14:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4CDN42IQMHDBE5N7I7QFQBDG4I","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T17:46:26Z","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"title_canon_sha256":"4cbf1c389c5c42c49cc1ee219873cf9138ae27e355a85f1a270def374a41cebb","abstract_canon_sha256":"5c5f0606fced8323ecbeef9f3e7e22d9ca75765a00fcce0999ce95928e16c477"},"schema_version":"1.0"},"canonical_sha256":"e086de691061c61275bf47e0580466e228abd966925be73383ba841bd1066923","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:49.935998Z","signature_b64":"m5L9ibme+yvdnkzdxmN3npPQMsN5mRtMMChY1ygPp+eU0HQh/xms4UYGibMjqqKVent5n+j6sgtTknuvzvgcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e086de691061c61275bf47e0580466e228abd966925be73383ba841bd1066923","last_reissued_at":"2026-07-05T04:14:49.935497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:49.935497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07137","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+s/nFL+17Zc6uphmDm+aXTLDBm2UgfmiHz/+zQndeVwpJShrYfHufDtP0ZiSo5uzX5N+PdoOEcDU0phoM6VEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:45:25.335690Z"},"content_sha256":"184dbf402467746fdea70bc265bf3122ba8c87f64d81ea368d0a6fda549e1c95","schema_version":"1.0","event_id":"sha256:184dbf402467746fdea70bc265bf3122ba8c87f64d81ea368d0a6fda549e1c95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4CDN42IQMHDBE5N7I7QFQBDG4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerated Policy Learning with Parallel Differentiable Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.RO"],"primary_cat":"cs.LG","authors_text":"Animesh Garg, Fabio Ramos, Jie Xu, Miles Macklin, Viktor Makoviychuk, Wojciech Matusik, Yashraj Narang","submitted_at":"2022-04-14T17:46:26Z","abstract_excerpt":"Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent problems such as local minima and exploding/vanishing numerical gradients prevent these methods from being generally applied to control tasks with complex contact-rich dynamics, such as humanoid locomotion in classical RL benchmarks. In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07137","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/2204.07137/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8FKtXZG2RdCdJzpADfKCvHdOorn0L6TNWw9R1HBV2hksXR/73UvyebmFvBBTP2x5W3/3bWaGUOxBFc+989fRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:45:25.336266Z"},"content_sha256":"2cbcbf1a7572ec83aecb440686e457431b77bba562860da2f33fd1ffaf7a93c4","schema_version":"1.0","event_id":"sha256:2cbcbf1a7572ec83aecb440686e457431b77bba562860da2f33fd1ffaf7a93c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/bundle.json","state_url":"https://pith.science/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T08:45:25Z","links":{"resolver":"https://pith.science/pith/4CDN42IQMHDBE5N7I7QFQBDG4I","bundle":"https://pith.science/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/bundle.json","state":"https://pith.science/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CDN42IQMHDBE5N7I7QFQBDG4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4CDN42IQMHDBE5N7I7QFQBDG4I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5c5f0606fced8323ecbeef9f3e7e22d9ca75765a00fcce0999ce95928e16c477","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T17:46:26Z","title_canon_sha256":"4cbf1c389c5c42c49cc1ee219873cf9138ae27e355a85f1a270def374a41cebb"},"schema_version":"1.0","source":{"id":"2204.07137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07137","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07137v1","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07137","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"4CDN42IQMHDB","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"4CDN42IQMHDBE5N7","created_at":"2026-07-05T04:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"4CDN42IQ","created_at":"2026-07-05T04:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:2cbcbf1a7572ec83aecb440686e457431b77bba562860da2f33fd1ffaf7a93c4","target":"graph","created_at":"2026-07-05T04:14:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.07137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent problems such as local minima and exploding/vanishing numerical gradients prevent these methods from being generally applied to control tasks with complex contact-rich dynamics, such as humanoid locomotion in classical RL benchmarks. In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effecti","authors_text":"Animesh Garg, Fabio Ramos, Jie Xu, Miles Macklin, Viktor Makoviychuk, Wojciech Matusik, Yashraj Narang","cross_cats":["cs.AI","cs.GR","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T17:46:26Z","title":"Accelerated Policy Learning with Parallel Differentiable Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07137","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:184dbf402467746fdea70bc265bf3122ba8c87f64d81ea368d0a6fda549e1c95","target":"record","created_at":"2026-07-05T04:14:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5c5f0606fced8323ecbeef9f3e7e22d9ca75765a00fcce0999ce95928e16c477","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T17:46:26Z","title_canon_sha256":"4cbf1c389c5c42c49cc1ee219873cf9138ae27e355a85f1a270def374a41cebb"},"schema_version":"1.0","source":{"id":"2204.07137","kind":"arxiv","version":1}},"canonical_sha256":"e086de691061c61275bf47e0580466e228abd966925be73383ba841bd1066923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e086de691061c61275bf47e0580466e228abd966925be73383ba841bd1066923","first_computed_at":"2026-07-05T04:14:49.935497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:49.935497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m5L9ibme+yvdnkzdxmN3npPQMsN5mRtMMChY1ygPp+eU0HQh/xms4UYGibMjqqKVent5n+j6sgtTknuvzvgcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:49.935998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:184dbf402467746fdea70bc265bf3122ba8c87f64d81ea368d0a6fda549e1c95","sha256:2cbcbf1a7572ec83aecb440686e457431b77bba562860da2f33fd1ffaf7a93c4"],"state_sha256":"ae5e36a82fd07695a8710946967d739352459cfa386387c45c790ef457dfb413"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W4M544vEzqYhyA42jgcFwyOG5C9lX64AiDvCLnQOeH/852d7C0wXpm8QVx7cbfEV0dAl5vMVAJzLecOTStrLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:45:25.341283Z","bundle_sha256":"9ea2c47d776726443b4a4007a686a64b311c35ab71e9990029720b54900c82e6"}}