{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7O5YBC7HEXH4VM3A6UDOOPXVQU","short_pith_number":"pith:7O5YBC7H","canonical_record":{"source":{"id":"2606.21525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T15:22:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ec5d128a4c18d1ff5b07a353e29391942b4b7814d679f3143eba563cba9d296","abstract_canon_sha256":"1030dd9d3a4d3e2caed47ea939b30c204763e45952a62039151d24667309311e"},"schema_version":"1.0"},"canonical_sha256":"fbbb808be725cfcab360f506e73ef5851c58b6282e66c06723b7270a64467793","source":{"kind":"arxiv","id":"2606.21525","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21525","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21525v1","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21525","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"7O5YBC7HEXH4","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"7O5YBC7HEXH4VM3A","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"7O5YBC7H","created_at":"2026-06-23T01:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7O5YBC7HEXH4VM3A6UDOOPXVQU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T15:22:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ec5d128a4c18d1ff5b07a353e29391942b4b7814d679f3143eba563cba9d296","abstract_canon_sha256":"1030dd9d3a4d3e2caed47ea939b30c204763e45952a62039151d24667309311e"},"schema_version":"1.0"},"canonical_sha256":"fbbb808be725cfcab360f506e73ef5851c58b6282e66c06723b7270a64467793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:13.465871Z","signature_b64":"7oKXbcaSg85fuad5Fi3RivuOyel4Gw115doG6CAU7ZAL4cas/zOOR7fvg3DA8sfmYmtRDUMFeLZNcdBqcB7vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbbb808be725cfcab360f506e73ef5851c58b6282e66c06723b7270a64467793","last_reissued_at":"2026-06-23T01:13:13.465405Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:13.465405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21525","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":"2026-06-23T01:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+1zIXd0U2vvmXiWuoM4rBT5/BwLXSIf02BDHJQ0upLjF55eHyuUBwVbbtC++TLYofYsHUg33FlLhNoEZq78Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:36:31.114997Z"},"content_sha256":"d10460b10eca531fe5ff56b701325f74ed9b4c294c2cd62c08b7f665352fb4e1","schema_version":"1.0","event_id":"sha256:d10460b10eca531fe5ff56b701325f74ed9b4c294c2cd62c08b7f665352fb4e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7O5YBC7HEXH4VM3A6UDOOPXVQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yueci Deng","submitted_at":"2026-06-19T15:22:51Z","abstract_excerpt":"Model-free reinforcement learning algorithms such as Proximal Policy Optimization (PPO) treat the environment as a black box, estimating policy gradients from sampled rewards; this process demands millions of interactions and relies on high-variance advantage estimates. When environment dynamics are differentiable, the return is an end-to-end differentiable function of the policy parameters, enabling exact gradient computation via backpropagation through simulation. We term this approach Analytic Policy Gradients (APG) and evaluate it against PPO on four continuous control tasks of increasing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21525","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/2606.21525/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":"2026-06-23T01:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUCqxN+gNXZaeNCs+4bqSErYLB6m9GMjy2kXiMxr4CtqW4b+zYvG040Y0PS1IwUGmX29nrHo1B5Llits2Of7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:36:31.115386Z"},"content_sha256":"5c36d73b18fcd78ea8b742f549995d81387fca0c5bfc76274faf86a85b4264be","schema_version":"1.0","event_id":"sha256:5c36d73b18fcd78ea8b742f549995d81387fca0c5bfc76274faf86a85b4264be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/bundle.json","state_url":"https://pith.science/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/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":"2026-07-07T11:36:31Z","links":{"resolver":"https://pith.science/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU","bundle":"https://pith.science/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/bundle.json","state":"https://pith.science/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7O5YBC7HEXH4VM3A6UDOOPXVQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7O5YBC7HEXH4VM3A6UDOOPXVQU","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":"1030dd9d3a4d3e2caed47ea939b30c204763e45952a62039151d24667309311e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T15:22:51Z","title_canon_sha256":"1ec5d128a4c18d1ff5b07a353e29391942b4b7814d679f3143eba563cba9d296"},"schema_version":"1.0","source":{"id":"2606.21525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21525","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21525v1","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21525","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"7O5YBC7HEXH4","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"7O5YBC7HEXH4VM3A","created_at":"2026-06-23T01:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"7O5YBC7H","created_at":"2026-06-23T01:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:5c36d73b18fcd78ea8b742f549995d81387fca0c5bfc76274faf86a85b4264be","target":"graph","created_at":"2026-06-23T01:13:13Z","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/2606.21525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning algorithms such as Proximal Policy Optimization (PPO) treat the environment as a black box, estimating policy gradients from sampled rewards; this process demands millions of interactions and relies on high-variance advantage estimates. When environment dynamics are differentiable, the return is an end-to-end differentiable function of the policy parameters, enabling exact gradient computation via backpropagation through simulation. We term this approach Analytic Policy Gradients (APG) and evaluate it against PPO on four continuous control tasks of increasing ","authors_text":"Yueci Deng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T15:22:51Z","title":"Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21525","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:d10460b10eca531fe5ff56b701325f74ed9b4c294c2cd62c08b7f665352fb4e1","target":"record","created_at":"2026-06-23T01:13:13Z","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":"1030dd9d3a4d3e2caed47ea939b30c204763e45952a62039151d24667309311e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T15:22:51Z","title_canon_sha256":"1ec5d128a4c18d1ff5b07a353e29391942b4b7814d679f3143eba563cba9d296"},"schema_version":"1.0","source":{"id":"2606.21525","kind":"arxiv","version":1}},"canonical_sha256":"fbbb808be725cfcab360f506e73ef5851c58b6282e66c06723b7270a64467793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbbb808be725cfcab360f506e73ef5851c58b6282e66c06723b7270a64467793","first_computed_at":"2026-06-23T01:13:13.465405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:13.465405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7oKXbcaSg85fuad5Fi3RivuOyel4Gw115doG6CAU7ZAL4cas/zOOR7fvg3DA8sfmYmtRDUMFeLZNcdBqcB7vBQ==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:13.465871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d10460b10eca531fe5ff56b701325f74ed9b4c294c2cd62c08b7f665352fb4e1","sha256:5c36d73b18fcd78ea8b742f549995d81387fca0c5bfc76274faf86a85b4264be"],"state_sha256":"6aaaa8071d5a9a76eda00a457ae2fcdcadecca5681c107d4f7fdcb09b65ecb67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMaAwV2BoNQUMmU/zU3zFhqGBAWFuXPdNYBcChf9VOJi1vtXdvjnCMyM2pvpbRE5NHe8jIUuKXb1nwfq62iSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:36:31.117288Z","bundle_sha256":"06005785f9f06c85a51da36427d449a9a5c0cddbfe196fca1472d28bb30e9680"}}