{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7UNGNVKSTXADLJWFMXPKYVXKQA","short_pith_number":"pith:7UNGNVKS","canonical_record":{"source":{"id":"2509.00215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-29T19:55:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1e41ef6912b403dc5350831f86437a5409beff63c87921f53704bf32a79bb11b","abstract_canon_sha256":"f2fec9a588fc3b25590ac70a195e229655445ed927c402d365c4aec8ea8a65ce"},"schema_version":"1.0"},"canonical_sha256":"fd1a66d5529dc035a6c565deac56ea8007f11102690eddd95e80c3c9ce37eca2","source":{"kind":"arxiv","id":"2509.00215","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00215","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00215v2","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00215","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"7UNGNVKSTXAD","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"7UNGNVKSTXADLJWF","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"7UNGNVKS","created_at":"2026-07-05T12:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7UNGNVKSTXADLJWFMXPKYVXKQA","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-29T19:55:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1e41ef6912b403dc5350831f86437a5409beff63c87921f53704bf32a79bb11b","abstract_canon_sha256":"f2fec9a588fc3b25590ac70a195e229655445ed927c402d365c4aec8ea8a65ce"},"schema_version":"1.0"},"canonical_sha256":"fd1a66d5529dc035a6c565deac56ea8007f11102690eddd95e80c3c9ce37eca2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:40.420762Z","signature_b64":"bI8okOuGiDgPkETWkcEr72dpKhMjNV+nV+8wOIASU7y0f+t6RTews+wiul6C677wbTgNxe3tuZ3wGWMlknJFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1a66d5529dc035a6c565deac56ea8007f11102690eddd95e80c3c9ce37eca2","last_reissued_at":"2026-07-05T12:04:40.420001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:40.420001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00215","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+KTS1Qxt1DMk4SW0WbGp8oA7K1b3R/6PQt96gIZL4soiL9T8aJu4kr4iPQ0jPvbsXmxgcViUiRpg+Lv/7CoUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:17:31.139657Z"},"content_sha256":"47ac1917ca4fd24dd8f211efe493f05c584973a87f7cab5997ba632ce80917e7","schema_version":"1.0","event_id":"sha256:47ac1917ca4fd24dd8f211efe493f05c584973a87f7cab5997ba632ce80917e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7UNGNVKSTXADLJWFMXPKYVXKQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First Order Model-Based RL through Decoupled Backpropagation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Elliot Chane-Sane, Joseph Amigo, Ludovic Righetti, Nicolas Mansard, Rooholla Khorrambakht","submitted_at":"2025-08-29T19:55:25Z","abstract_excerpt":"There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to derivative-free methods, accessing simulator gradients is often impractical due to their implementation cost or unavailability. Model-based RL (MBRL) can approximate these gradients via learned dynamics models, but the solver efficiency suffers from compounding prediction errors during training rollouts, which can degrade policy performance. We propose an approach that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00215","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/2509.00215/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":"2026-07-05T12:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e8y4RvEnhimtesUphfcSwE1GqPjOtZwfkm4bu4OSkECM0yHURBxbVXbek4AOOTYto50IbsNl2odFJkK0EpwOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:17:31.140034Z"},"content_sha256":"84490a810bcb5f8c12770246d5b7e84c7fc8daa6c8ef1ce3905b981897c644b4","schema_version":"1.0","event_id":"sha256:84490a810bcb5f8c12770246d5b7e84c7fc8daa6c8ef1ce3905b981897c644b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/bundle.json","state_url":"https://pith.science/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/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":"2026-08-06T02:17:31Z","links":{"resolver":"https://pith.science/pith/7UNGNVKSTXADLJWFMXPKYVXKQA","bundle":"https://pith.science/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/bundle.json","state":"https://pith.science/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UNGNVKSTXADLJWFMXPKYVXKQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7UNGNVKSTXADLJWFMXPKYVXKQA","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":"f2fec9a588fc3b25590ac70a195e229655445ed927c402d365c4aec8ea8a65ce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-29T19:55:25Z","title_canon_sha256":"1e41ef6912b403dc5350831f86437a5409beff63c87921f53704bf32a79bb11b"},"schema_version":"1.0","source":{"id":"2509.00215","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00215","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00215v2","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00215","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"7UNGNVKSTXAD","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"7UNGNVKSTXADLJWF","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"7UNGNVKS","created_at":"2026-07-05T12:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:84490a810bcb5f8c12770246d5b7e84c7fc8daa6c8ef1ce3905b981897c644b4","target":"graph","created_at":"2026-07-05T12:04:40Z","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/2509.00215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to derivative-free methods, accessing simulator gradients is often impractical due to their implementation cost or unavailability. Model-based RL (MBRL) can approximate these gradients via learned dynamics models, but the solver efficiency suffers from compounding prediction errors during training rollouts, which can degrade policy performance. We propose an approach that ","authors_text":"Elliot Chane-Sane, Joseph Amigo, Ludovic Righetti, Nicolas Mansard, Rooholla Khorrambakht","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-29T19:55:25Z","title":"First Order Model-Based RL through Decoupled Backpropagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00215","kind":"arxiv","version":2},"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":"sha256:47ac1917ca4fd24dd8f211efe493f05c584973a87f7cab5997ba632ce80917e7","target":"record","created_at":"2026-07-05T12:04:40Z","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":"f2fec9a588fc3b25590ac70a195e229655445ed927c402d365c4aec8ea8a65ce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-29T19:55:25Z","title_canon_sha256":"1e41ef6912b403dc5350831f86437a5409beff63c87921f53704bf32a79bb11b"},"schema_version":"1.0","source":{"id":"2509.00215","kind":"arxiv","version":2}},"canonical_sha256":"fd1a66d5529dc035a6c565deac56ea8007f11102690eddd95e80c3c9ce37eca2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1a66d5529dc035a6c565deac56ea8007f11102690eddd95e80c3c9ce37eca2","first_computed_at":"2026-07-05T12:04:40.420001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:40.420001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bI8okOuGiDgPkETWkcEr72dpKhMjNV+nV+8wOIASU7y0f+t6RTews+wiul6C677wbTgNxe3tuZ3wGWMlknJFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:40.420762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00215","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47ac1917ca4fd24dd8f211efe493f05c584973a87f7cab5997ba632ce80917e7","sha256:84490a810bcb5f8c12770246d5b7e84c7fc8daa6c8ef1ce3905b981897c644b4"],"state_sha256":"5a6f6f671aeddeec08a167f9a3fe63716337cde7f910e41602d8b4754579bfb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1HbBhTv77jR7JWWNOnOvPrYwCReuS1g2HKXzyu5SF4o7LpybfosI3pDSA1trliPYjA7RHC6btIGO4S2sVmEmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:17:31.143442Z","bundle_sha256":"b63ec55bc685c906e25a004dad4d7217501143e7d33d52eb26d819e62068a695"}}