{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2WLGZDERKDCXBX37UK3PBXMZ5D","short_pith_number":"pith:2WLGZDER","canonical_record":{"source":{"id":"2208.06721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-08-13T20:04:17Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"10c51f00540dc6222969466252c6ecf48520ab1f7a19ef787a054892cc8b2bdd","abstract_canon_sha256":"3c6df4f78c24f2e8849007f2b83084ef4c1a46459021fba667221dd8b6b71a87"},"schema_version":"1.0"},"canonical_sha256":"d5966c8c9150c570df7fa2b6f0dd99e8fc692107ecb9b17786cf80daf85c39ba","source":{"kind":"arxiv","id":"2208.06721","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06721","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06721v2","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06721","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"2WLGZDERKDCX","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"2WLGZDERKDCXBX37","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"2WLGZDER","created_at":"2026-07-05T05:17:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2WLGZDERKDCXBX37UK3PBXMZ5D","target":"record","payload":{"canonical_record":{"source":{"id":"2208.06721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-08-13T20:04:17Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"10c51f00540dc6222969466252c6ecf48520ab1f7a19ef787a054892cc8b2bdd","abstract_canon_sha256":"3c6df4f78c24f2e8849007f2b83084ef4c1a46459021fba667221dd8b6b71a87"},"schema_version":"1.0"},"canonical_sha256":"d5966c8c9150c570df7fa2b6f0dd99e8fc692107ecb9b17786cf80daf85c39ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:12.014257Z","signature_b64":"BVgtkyZchJ3GkmGfsS2sVm1wPYRRLGgwJ70asUND9aO/3gOgkj0GokJO4Dy2rjhc/l6i7Sh9FiwaAdnt7GtTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5966c8c9150c570df7fa2b6f0dd99e8fc692107ecb9b17786cf80daf85c39ba","last_reissued_at":"2026-07-05T05:17:12.013853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:12.013853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.06721","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":"2026-07-05T05:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P3o+jr0F9uxP592c7+55n5BzpLDH/DoRdaswGn46AcS4tHLOPdMMyfun47tlSTjRGKuJz8s0NwkUdaRDi7VgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:54:10.019843Z"},"content_sha256":"16574a5c43fc059b256246a9497c1b9f9f67c4df2ec9e616469752f05ba2625b","schema_version":"1.0","event_id":"sha256:16574a5c43fc059b256246a9497c1b9f9f67c4df2ec9e616469752f05ba2625b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2WLGZDERKDCXBX37UK3PBXMZ5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Ayush Agrawal, Fernando Castaneda, Koushil Sreenath, Shankar Sastry, Tyler Westenbroek","submitted_at":"2022-08-13T20:04:17Z","abstract_excerpt":"Recent advances in the reinforcement learning (RL) literature have enabled roboticists to automatically train complex policies in simulated environments. However, due to the poor sample complexity of these methods, solving RL problems using real-world data remains a challenging problem. This paper introduces a novel cost-shaping method which aims to reduce the number of samples needed to learn a stabilizing controller. The method adds a term involving a Control Lyapunov Function (CLF) -- an `energy-like' function from the model-based control literature -- to typical cost formulations. Theoreti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06721","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/2208.06721/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":"2026-07-05T05:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Fgqny1lyk26lcQoS4sj0qGtT3UTq4lhjghuE1PnWtkh+pKlPGsUj+IKeN4k297futXrR+oChN618RTtrxDwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:54:10.020454Z"},"content_sha256":"25715500e95a419116e6809a292b0b8f9008eebac1a6a34785f5df69de8f185c","schema_version":"1.0","event_id":"sha256:25715500e95a419116e6809a292b0b8f9008eebac1a6a34785f5df69de8f185c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/bundle.json","state_url":"https://pith.science/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/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":"2026-08-10T00:54:10Z","links":{"resolver":"https://pith.science/pith/2WLGZDERKDCXBX37UK3PBXMZ5D","bundle":"https://pith.science/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/bundle.json","state":"https://pith.science/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2WLGZDERKDCXBX37UK3PBXMZ5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2WLGZDERKDCXBX37UK3PBXMZ5D","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":"3c6df4f78c24f2e8849007f2b83084ef4c1a46459021fba667221dd8b6b71a87","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-08-13T20:04:17Z","title_canon_sha256":"10c51f00540dc6222969466252c6ecf48520ab1f7a19ef787a054892cc8b2bdd"},"schema_version":"1.0","source":{"id":"2208.06721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06721","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06721v2","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06721","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"2WLGZDERKDCX","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"2WLGZDERKDCXBX37","created_at":"2026-07-05T05:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"2WLGZDER","created_at":"2026-07-05T05:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:25715500e95a419116e6809a292b0b8f9008eebac1a6a34785f5df69de8f185c","target":"graph","created_at":"2026-07-05T05:17:12Z","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/2208.06721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in the reinforcement learning (RL) literature have enabled roboticists to automatically train complex policies in simulated environments. However, due to the poor sample complexity of these methods, solving RL problems using real-world data remains a challenging problem. This paper introduces a novel cost-shaping method which aims to reduce the number of samples needed to learn a stabilizing controller. The method adds a term involving a Control Lyapunov Function (CLF) -- an `energy-like' function from the model-based control literature -- to typical cost formulations. Theoreti","authors_text":"Ayush Agrawal, Fernando Castaneda, Koushil Sreenath, Shankar Sastry, Tyler Westenbroek","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-08-13T20:04:17Z","title":"Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06721","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":"sha256:16574a5c43fc059b256246a9497c1b9f9f67c4df2ec9e616469752f05ba2625b","target":"record","created_at":"2026-07-05T05:17:12Z","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":"3c6df4f78c24f2e8849007f2b83084ef4c1a46459021fba667221dd8b6b71a87","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-08-13T20:04:17Z","title_canon_sha256":"10c51f00540dc6222969466252c6ecf48520ab1f7a19ef787a054892cc8b2bdd"},"schema_version":"1.0","source":{"id":"2208.06721","kind":"arxiv","version":2}},"canonical_sha256":"d5966c8c9150c570df7fa2b6f0dd99e8fc692107ecb9b17786cf80daf85c39ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5966c8c9150c570df7fa2b6f0dd99e8fc692107ecb9b17786cf80daf85c39ba","first_computed_at":"2026-07-05T05:17:12.013853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:12.013853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BVgtkyZchJ3GkmGfsS2sVm1wPYRRLGgwJ70asUND9aO/3gOgkj0GokJO4Dy2rjhc/l6i7Sh9FiwaAdnt7GtTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:12.014257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16574a5c43fc059b256246a9497c1b9f9f67c4df2ec9e616469752f05ba2625b","sha256:25715500e95a419116e6809a292b0b8f9008eebac1a6a34785f5df69de8f185c"],"state_sha256":"53c9fa73e513cbb38b765fabffd9ab157d04e7b728bbd586352b57b7b56fa694"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IU3RMWjk7qBmLx6HTto1NlZK5WbWxMTaTng3pb45WDWupE633FALLtVD9wtJShxaSJPjmGiafbIjo9EdsiRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:54:10.025604Z","bundle_sha256":"a4168d61f136d9aa9da2c0515ddb0a6f6fae58b7c1572a61b2cc3f811d5876d7"}}