{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JUUD7DMF3XAZWSVYWNOD47IXGY","short_pith_number":"pith:JUUD7DMF","schema_version":"1.0","canonical_sha256":"4d283f8d85ddc19b4ab8b35c3e7d17360b5a6a76984b683b184b320ab89c001e","source":{"kind":"arxiv","id":"2504.01086","version":2},"attestation_state":"computed","paper":{"title":"MPCritic: A plug-and-play MPC architecture for reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Mesbah, Nathan P. Lawrence, Thomas Banker","submitted_at":"2025-04-01T18:07:07Z","abstract_excerpt":"The reinforcement learning (RL) and model predictive control (MPC) communities have developed vast ecosystems of theoretical approaches and computational tools for solving optimal control problems. Given their conceptual similarities but differing strengths, there has been increasing interest in synergizing RL and MPC. However, existing approaches tend to be limited for various reasons, including computational cost of MPC in an RL algorithm and software hurdles towards seamless integration of MPC and RL tools. These challenges often result in the use of \"simple\" MPC schemes or RL algorithms, n"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.01086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T18:07:07Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"839f2600bd3c9182da1ea54005d0434c6a1c48f6d4e883f50f0578ed348868a8","abstract_canon_sha256":"2b54871097381fcadbf908402fc1ed23f0f8464bdec5de47c2e270d68fd47ade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:14.620665Z","signature_b64":"J1bI12/7LLwrbzv9SAWZ/bbTL84NafL1cdeBQBf3RLp7JFi3u3OuiBvXpQhqGhU7VxFi6K4DXDLS4IgucwusBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d283f8d85ddc19b4ab8b35c3e7d17360b5a6a76984b683b184b320ab89c001e","last_reissued_at":"2026-07-05T12:04:14.620034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:14.620034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPCritic: A plug-and-play MPC architecture for reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Mesbah, Nathan P. Lawrence, Thomas Banker","submitted_at":"2025-04-01T18:07:07Z","abstract_excerpt":"The reinforcement learning (RL) and model predictive control (MPC) communities have developed vast ecosystems of theoretical approaches and computational tools for solving optimal control problems. Given their conceptual similarities but differing strengths, there has been increasing interest in synergizing RL and MPC. However, existing approaches tend to be limited for various reasons, including computational cost of MPC in an RL algorithm and software hurdles towards seamless integration of MPC and RL tools. These challenges often result in the use of \"simple\" MPC schemes or RL algorithms, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01086","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/2504.01086/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.01086","created_at":"2026-07-05T12:04:14.620144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01086v2","created_at":"2026-07-05T12:04:14.620144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01086","created_at":"2026-07-05T12:04:14.620144+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUUD7DMF3XAZ","created_at":"2026-07-05T12:04:14.620144+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUUD7DMF3XAZWSVY","created_at":"2026-07-05T12:04:14.620144+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUUD7DMF","created_at":"2026-07-05T12:04:14.620144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13491","citing_title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","ref_index":102,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY","json":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY.json","graph_json":"https://pith.science/api/pith-number/JUUD7DMF3XAZWSVYWNOD47IXGY/graph.json","events_json":"https://pith.science/api/pith-number/JUUD7DMF3XAZWSVYWNOD47IXGY/events.json","paper":"https://pith.science/paper/JUUD7DMF"},"agent_actions":{"view_html":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY","download_json":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY.json","view_paper":"https://pith.science/paper/JUUD7DMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01086&json=true","fetch_graph":"https://pith.science/api/pith-number/JUUD7DMF3XAZWSVYWNOD47IXGY/graph.json","fetch_events":"https://pith.science/api/pith-number/JUUD7DMF3XAZWSVYWNOD47IXGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY/action/storage_attestation","attest_author":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY/action/author_attestation","sign_citation":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY/action/citation_signature","submit_replication":"https://pith.science/pith/JUUD7DMF3XAZWSVYWNOD47IXGY/action/replication_record"}},"created_at":"2026-07-05T12:04:14.620144+00:00","updated_at":"2026-07-05T12:04:14.620144+00:00"}