{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GIP4CPP2KPSLL7D2SPX3ZOSIBH","short_pith_number":"pith:GIP4CPP2","schema_version":"1.0","canonical_sha256":"321fc13dfa53e4b5fc7a93efbcba4809cfe37df29ee28c45dde7509df030fd39","source":{"kind":"arxiv","id":"2605.27556","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Reinforcement Learning Training Using Simulation Surrogate Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David J. Eckman, Mohammadmahdi Ghasemloo, Yaxian Li","submitted_at":"2026-05-26T18:23:42Z","abstract_excerpt":"High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of cheaper surrogate models that approximate the simulation model's input-output relationship. In parallel, reinforcement learning (RL) has emerged as a powerful framework for making online decisions in stochastic environments, with increasing attention being given to the use of simulation models as training environments for RL models. We investigate a class of surrogate models suitable for accelerating RL training in settings where the reward struc"},"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":"2605.27556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T18:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c996e59f3040727bfd2d16bcaab653a12db836c02a33bce7065fc03421c4405","abstract_canon_sha256":"89cf8ad589da87a3a615b48ead7bab4022e64b34689405c4825a7333f8f386d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:15.759577Z","signature_b64":"YbrtvaTIf31tG3oal3VmSXeimo0+LxpyuyuPX42azMBljzWDPPoBNhM6nWxf2Fsf5Ws9LsBaPddQ9MI2WWu2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"321fc13dfa53e4b5fc7a93efbcba4809cfe37df29ee28c45dde7509df030fd39","last_reissued_at":"2026-05-28T01:04:15.758925Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:15.758925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Reinforcement Learning Training Using Simulation Surrogate Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David J. Eckman, Mohammadmahdi Ghasemloo, Yaxian Li","submitted_at":"2026-05-26T18:23:42Z","abstract_excerpt":"High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of cheaper surrogate models that approximate the simulation model's input-output relationship. In parallel, reinforcement learning (RL) has emerged as a powerful framework for making online decisions in stochastic environments, with increasing attention being given to the use of simulation models as training environments for RL models. We investigate a class of surrogate models suitable for accelerating RL training in settings where the reward struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27556","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/2605.27556/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":"2605.27556","created_at":"2026-05-28T01:04:15.759024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27556v1","created_at":"2026-05-28T01:04:15.759024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27556","created_at":"2026-05-28T01:04:15.759024+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIP4CPP2KPSL","created_at":"2026-05-28T01:04:15.759024+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIP4CPP2KPSLL7D2","created_at":"2026-05-28T01:04:15.759024+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIP4CPP2","created_at":"2026-05-28T01:04:15.759024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH","json":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH.json","graph_json":"https://pith.science/api/pith-number/GIP4CPP2KPSLL7D2SPX3ZOSIBH/graph.json","events_json":"https://pith.science/api/pith-number/GIP4CPP2KPSLL7D2SPX3ZOSIBH/events.json","paper":"https://pith.science/paper/GIP4CPP2"},"agent_actions":{"view_html":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH","download_json":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH.json","view_paper":"https://pith.science/paper/GIP4CPP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27556&json=true","fetch_graph":"https://pith.science/api/pith-number/GIP4CPP2KPSLL7D2SPX3ZOSIBH/graph.json","fetch_events":"https://pith.science/api/pith-number/GIP4CPP2KPSLL7D2SPX3ZOSIBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH/action/storage_attestation","attest_author":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH/action/author_attestation","sign_citation":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH/action/citation_signature","submit_replication":"https://pith.science/pith/GIP4CPP2KPSLL7D2SPX3ZOSIBH/action/replication_record"}},"created_at":"2026-05-28T01:04:15.759024+00:00","updated_at":"2026-05-28T01:04:15.759024+00:00"}