{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MYESUJJZSH4YVDZCLJINXCMAMO","short_pith_number":"pith:MYESUJJZ","canonical_record":{"source":{"id":"2410.16821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-22T08:48:48Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"d250bb4465636cac4e9d36c2c8503300333c3e608a92c60d66c70e1025f15111","abstract_canon_sha256":"4013d91e501d0d63def77db406b478127e62300d6e6f5329f0c8c708eb9d8bd2"},"schema_version":"1.0"},"canonical_sha256":"66092a253991f98a8f225a50db89806389478d09ee217cd84e4771d4e57bd49d","source":{"kind":"arxiv","id":"2410.16821","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16821","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16821v2","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16821","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"MYESUJJZSH4Y","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_16","alias_value":"MYESUJJZSH4YVDZC","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_8","alias_value":"MYESUJJZ","created_at":"2026-07-05T09:25:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MYESUJJZSH4YVDZCLJINXCMAMO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-22T08:48:48Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"d250bb4465636cac4e9d36c2c8503300333c3e608a92c60d66c70e1025f15111","abstract_canon_sha256":"4013d91e501d0d63def77db406b478127e62300d6e6f5329f0c8c708eb9d8bd2"},"schema_version":"1.0"},"canonical_sha256":"66092a253991f98a8f225a50db89806389478d09ee217cd84e4771d4e57bd49d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:02.831722Z","signature_b64":"XopT8gcOD697HNdGCCobCRDuemsNAdir7ou5kPdErzaCOpF4et/ZRwAZNnjw7y0CtaFhBak9LMZKXqeNlRItAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66092a253991f98a8f225a50db89806389478d09ee217cd84e4771d4e57bd49d","last_reissued_at":"2026-07-05T09:25:02.831220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:02.831220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16821","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":"2026-07-05T09:25:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INoaQHZXKt1xGwIwunN54nDxHMa3P2VMQVRs4oPL993JAYZf7lrANARoz33pduvgz8jWSOO5UI+8VKDHOYk5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:34:51.756960Z"},"content_sha256":"cbe54c92a49c5d1d656c3d62ba494c0e2debdad301fc9aec8446b798b06a5ed8","schema_version":"1.0","event_id":"sha256:cbe54c92a49c5d1d656c3d62ba494c0e2debdad301fc9aec8446b798b06a5ed8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MYESUJJZSH4YVDZCLJINXCMAMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guiding Reinforcement Learning with Incomplete System Dynamics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jingliang Duan, Lixian Zhang, Michael G. Forbes, Nathan P. Lawrence, Philip D. Loewen, R. Bhushan Gopaluni, Shuyuan Wang","submitted_at":"2024-10-22T08:48:48Z","abstract_excerpt":"Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several challenges, such as poor sample efficiency, generalization, and the need for well-designed reward functions to guide learning effectively. On the other hand, controllers based on complete system dynamics do not require data. This paper addresses the intermediate situation where there is not enough model information for complete controller design, but there is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16821","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/2410.16821/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":"2026-07-05T09:25:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1Zltzt3uYk94KhqPIpc8HP+k4lGynJtl0zQt+Wlmm5a+5FzwOBVXauj8hf/1iyfSxem5qq3CNbwy91n67o8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:34:51.757461Z"},"content_sha256":"3396d5ff8b07a06b00f7134a6b15cf1fe0728967d190a340dfb72775c27cba6d","schema_version":"1.0","event_id":"sha256:3396d5ff8b07a06b00f7134a6b15cf1fe0728967d190a340dfb72775c27cba6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYESUJJZSH4YVDZCLJINXCMAMO/bundle.json","state_url":"https://pith.science/pith/MYESUJJZSH4YVDZCLJINXCMAMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYESUJJZSH4YVDZCLJINXCMAMO/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":"2026-08-19T23:34:51Z","links":{"resolver":"https://pith.science/pith/MYESUJJZSH4YVDZCLJINXCMAMO","bundle":"https://pith.science/pith/MYESUJJZSH4YVDZCLJINXCMAMO/bundle.json","state":"https://pith.science/pith/MYESUJJZSH4YVDZCLJINXCMAMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYESUJJZSH4YVDZCLJINXCMAMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MYESUJJZSH4YVDZCLJINXCMAMO","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":"4013d91e501d0d63def77db406b478127e62300d6e6f5329f0c8c708eb9d8bd2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-22T08:48:48Z","title_canon_sha256":"d250bb4465636cac4e9d36c2c8503300333c3e608a92c60d66c70e1025f15111"},"schema_version":"1.0","source":{"id":"2410.16821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16821","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16821v2","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16821","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"MYESUJJZSH4Y","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_16","alias_value":"MYESUJJZSH4YVDZC","created_at":"2026-07-05T09:25:02Z"},{"alias_kind":"pith_short_8","alias_value":"MYESUJJZ","created_at":"2026-07-05T09:25:02Z"}],"graph_snapshots":[{"event_id":"sha256:3396d5ff8b07a06b00f7134a6b15cf1fe0728967d190a340dfb72775c27cba6d","target":"graph","created_at":"2026-07-05T09:25:02Z","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/2410.16821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several challenges, such as poor sample efficiency, generalization, and the need for well-designed reward functions to guide learning effectively. On the other hand, controllers based on complete system dynamics do not require data. This paper addresses the intermediate situation where there is not enough model information for complete controller design, but there is ","authors_text":"Jingliang Duan, Lixian Zhang, Michael G. Forbes, Nathan P. Lawrence, Philip D. Loewen, R. Bhushan Gopaluni, Shuyuan Wang","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-22T08:48:48Z","title":"Guiding Reinforcement Learning with Incomplete System Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16821","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:cbe54c92a49c5d1d656c3d62ba494c0e2debdad301fc9aec8446b798b06a5ed8","target":"record","created_at":"2026-07-05T09:25:02Z","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":"4013d91e501d0d63def77db406b478127e62300d6e6f5329f0c8c708eb9d8bd2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-22T08:48:48Z","title_canon_sha256":"d250bb4465636cac4e9d36c2c8503300333c3e608a92c60d66c70e1025f15111"},"schema_version":"1.0","source":{"id":"2410.16821","kind":"arxiv","version":2}},"canonical_sha256":"66092a253991f98a8f225a50db89806389478d09ee217cd84e4771d4e57bd49d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66092a253991f98a8f225a50db89806389478d09ee217cd84e4771d4e57bd49d","first_computed_at":"2026-07-05T09:25:02.831220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:02.831220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XopT8gcOD697HNdGCCobCRDuemsNAdir7ou5kPdErzaCOpF4et/ZRwAZNnjw7y0CtaFhBak9LMZKXqeNlRItAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:02.831722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbe54c92a49c5d1d656c3d62ba494c0e2debdad301fc9aec8446b798b06a5ed8","sha256:3396d5ff8b07a06b00f7134a6b15cf1fe0728967d190a340dfb72775c27cba6d"],"state_sha256":"23888e437a26f0877ec4538283be84f63d731aeb38da695e4ef271095a80fc88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LPnRAeEOGGFIe54/3Yj8/yiZmJ7KGhsSFWQk/txLAcjUBVEs/Ee2WPIQwrF7WRba5kHDh98OL7BU6R1IQoCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:34:51.761245Z","bundle_sha256":"90c2e0f8cce14a0aa406b712e63f8e88fb870babd91aaf1388a8c7b4cfbf12ae"}}