{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MRB45RDTKV7PE4XDDXAUVG5CYB","short_pith_number":"pith:MRB45RDT","canonical_record":{"source":{"id":"2507.13491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T18:59:54Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"ea65685b98c7dbd49084f926d64381a512c18fabb235fda2c950c8c00b2d8347","abstract_canon_sha256":"48f1777e63c6c9688c8bfa820df8e7af18f969912b7c64732dabeb1aad1622b0"},"schema_version":"1.0"},"canonical_sha256":"6443cec473557ef272e31dc14a9ba2c043d9fc8fd2024955bcfabaf7af39b0c5","source":{"kind":"arxiv","id":"2507.13491","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13491","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13491v1","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13491","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_12","alias_value":"MRB45RDTKV7P","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_16","alias_value":"MRB45RDTKV7PE4XD","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_8","alias_value":"MRB45RDT","created_at":"2026-07-05T11:39:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MRB45RDTKV7PE4XDDXAUVG5CYB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T18:59:54Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"ea65685b98c7dbd49084f926d64381a512c18fabb235fda2c950c8c00b2d8347","abstract_canon_sha256":"48f1777e63c6c9688c8bfa820df8e7af18f969912b7c64732dabeb1aad1622b0"},"schema_version":"1.0"},"canonical_sha256":"6443cec473557ef272e31dc14a9ba2c043d9fc8fd2024955bcfabaf7af39b0c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:18.259830Z","signature_b64":"HGcKiijEqd+BmcoI2oZAb825p7nq7bLdf0TRc5FdLKGGfMd3sRGCb9lTVSba3M0z828DRH0+0ZK/92nY9ds6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6443cec473557ef272e31dc14a9ba2c043d9fc8fd2024955bcfabaf7af39b0c5","last_reissued_at":"2026-07-05T11:39:18.259387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:18.259387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13491","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":"2026-07-05T11:39:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APKrQ6JQXTJCRFPsETORbb/8+/2Bpb+QcrAwCK6NSkSdMa58lcWdT2u17Cu9ZPuD3ap3eF0sj/16OP7mRagwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:29:58.521045Z"},"content_sha256":"ae881b677ed4d7bf34f5f189d70277bb4e520f6f0e1720c9a0808ca089b6426b","schema_version":"1.0","event_id":"sha256:ae881b677ed4d7bf34f5f189d70277bb4e520f6f0e1720c9a0808ca089b6426b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MRB45RDTKV7PE4XDDXAUVG5CYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Mesbah, Thomas Banker","submitted_at":"2025-07-17T18:59:54Z","abstract_excerpt":"Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents to improve their performance directly through system interactions, with minimal prior knowledge about the system. Yet, model-free RL has generally relied on agents equipped with deep neural network function approximators, appealing to the networks' expressivity to capture the agent's policy and value function for complex systems. However, neural networks am"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13491","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/2507.13491/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":"2026-07-05T11:39:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIiZW2OX803H90CdkwY9dWaumTMEslUsYV6Dvq1gqeb9+c9QePj/Wq99Y8FqjngvtAPtRq3pebhmqxAO3gqKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:29:58.521427Z"},"content_sha256":"9c9f84c19ddd879b6eb998c11b3533dc9ad15f562963e4eed768c0fb198ba7fb","schema_version":"1.0","event_id":"sha256:9c9f84c19ddd879b6eb998c11b3533dc9ad15f562963e4eed768c0fb198ba7fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/bundle.json","state_url":"https://pith.science/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/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":"2026-08-07T09:29:58Z","links":{"resolver":"https://pith.science/pith/MRB45RDTKV7PE4XDDXAUVG5CYB","bundle":"https://pith.science/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/bundle.json","state":"https://pith.science/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRB45RDTKV7PE4XDDXAUVG5CYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MRB45RDTKV7PE4XDDXAUVG5CYB","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":"48f1777e63c6c9688c8bfa820df8e7af18f969912b7c64732dabeb1aad1622b0","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T18:59:54Z","title_canon_sha256":"ea65685b98c7dbd49084f926d64381a512c18fabb235fda2c950c8c00b2d8347"},"schema_version":"1.0","source":{"id":"2507.13491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13491","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13491v1","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13491","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_12","alias_value":"MRB45RDTKV7P","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_16","alias_value":"MRB45RDTKV7PE4XD","created_at":"2026-07-05T11:39:18Z"},{"alias_kind":"pith_short_8","alias_value":"MRB45RDT","created_at":"2026-07-05T11:39:18Z"}],"graph_snapshots":[{"event_id":"sha256:9c9f84c19ddd879b6eb998c11b3533dc9ad15f562963e4eed768c0fb198ba7fb","target":"graph","created_at":"2026-07-05T11:39:18Z","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/2507.13491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents to improve their performance directly through system interactions, with minimal prior knowledge about the system. Yet, model-free RL has generally relied on agents equipped with deep neural network function approximators, appealing to the networks' expressivity to capture the agent's policy and value function for complex systems. However, neural networks am","authors_text":"Ali Mesbah, Thomas Banker","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T18:59:54Z","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13491","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:ae881b677ed4d7bf34f5f189d70277bb4e520f6f0e1720c9a0808ca089b6426b","target":"record","created_at":"2026-07-05T11:39:18Z","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":"48f1777e63c6c9688c8bfa820df8e7af18f969912b7c64732dabeb1aad1622b0","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T18:59:54Z","title_canon_sha256":"ea65685b98c7dbd49084f926d64381a512c18fabb235fda2c950c8c00b2d8347"},"schema_version":"1.0","source":{"id":"2507.13491","kind":"arxiv","version":1}},"canonical_sha256":"6443cec473557ef272e31dc14a9ba2c043d9fc8fd2024955bcfabaf7af39b0c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6443cec473557ef272e31dc14a9ba2c043d9fc8fd2024955bcfabaf7af39b0c5","first_computed_at":"2026-07-05T11:39:18.259387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:18.259387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HGcKiijEqd+BmcoI2oZAb825p7nq7bLdf0TRc5FdLKGGfMd3sRGCb9lTVSba3M0z828DRH0+0ZK/92nY9ds6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:18.259830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae881b677ed4d7bf34f5f189d70277bb4e520f6f0e1720c9a0808ca089b6426b","sha256:9c9f84c19ddd879b6eb998c11b3533dc9ad15f562963e4eed768c0fb198ba7fb"],"state_sha256":"891e187a5de211ebf5ffa0c4a937bb173302677ebf8185a138fce408603f3fa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyaifLr2CF+wfMjEtYwLCZ2w3CJcT+QCjKQipk9i/rOQJIgm/jzmKG5/L0rClbafXxIO5fHt7vlitDEDYfYPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:29:58.523963Z","bundle_sha256":"90686f8cc328e2e64ef555784fe91bd3f619b68f75223b5d0dcf14cd709dce0e"}}