{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FLY3QCTIIY7ZGJCJQD4FXYLBLZ","short_pith_number":"pith:FLY3QCTI","schema_version":"1.0","canonical_sha256":"2af1b80a68463f93244980f85be1615e439357423bb80b5ef4036df7c78e7f3b","source":{"kind":"arxiv","id":"2607.01736","version":1},"attestation_state":"computed","paper":{"title":"Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Nikolai Smolyanskiy","submitted_at":"2026-07-02T05:46:03Z","abstract_excerpt":"We study how to predict the downstream closed-loop performance of a learned latent world model from validation-time diagnostics alone. Choosing the right checkpoint from a world-model training run is difficult: validation loss and multi-step prediction RMSE keep improving long after closed-loop performance has collapsed. We present a suite of structural validation-time diagnostics drawn from optimal-control theory and apply them to Gymnasium's LunarLander v3, which features shaped rewards. We train an RSSM [5, 4] world model on it and treat per checkpoint CEM-MPC return as the oracle for close"},"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":"2607.01736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T05:46:03Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"2a08e15f3a65b406c19d59e547cd272bc7eebd36ad28ca357dba0cc0e16f7957","abstract_canon_sha256":"7fcd316d4035b444b4417a4c6708dda55257e1354c632aba0cf66490bfc4f1e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:28.155425Z","signature_b64":"6e6ZopzQlHPuh0VPKN0uFOhbgmZ4vCfvOfVrEKawhsj/0xBJvFBsmJi+vR9ilB4El5axYWsnqlg7dc3fue17Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2af1b80a68463f93244980f85be1615e439357423bb80b5ef4036df7c78e7f3b","last_reissued_at":"2026-07-03T01:17:28.155001Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:28.155001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Nikolai Smolyanskiy","submitted_at":"2026-07-02T05:46:03Z","abstract_excerpt":"We study how to predict the downstream closed-loop performance of a learned latent world model from validation-time diagnostics alone. Choosing the right checkpoint from a world-model training run is difficult: validation loss and multi-step prediction RMSE keep improving long after closed-loop performance has collapsed. We present a suite of structural validation-time diagnostics drawn from optimal-control theory and apply them to Gymnasium's LunarLander v3, which features shaped rewards. We train an RSSM [5, 4] world model on it and treat per checkpoint CEM-MPC return as the oracle for close"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01736","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/2607.01736/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":"2607.01736","created_at":"2026-07-03T01:17:28.155072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01736v1","created_at":"2026-07-03T01:17:28.155072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01736","created_at":"2026-07-03T01:17:28.155072+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLY3QCTIIY7Z","created_at":"2026-07-03T01:17:28.155072+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLY3QCTIIY7ZGJCJ","created_at":"2026-07-03T01:17:28.155072+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLY3QCTI","created_at":"2026-07-03T01:17:28.155072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07265","citing_title":"Metric Non-Collapse in Learned World Models for Control: Approximation Theory, Finite-Sample Geometric Guarantees, and Deterministic Planning Transfer","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ","json":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ.json","graph_json":"https://pith.science/api/pith-number/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/graph.json","events_json":"https://pith.science/api/pith-number/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/events.json","paper":"https://pith.science/paper/FLY3QCTI"},"agent_actions":{"view_html":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ","download_json":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ.json","view_paper":"https://pith.science/paper/FLY3QCTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01736&json=true","fetch_graph":"https://pith.science/api/pith-number/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/action/storage_attestation","attest_author":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/action/author_attestation","sign_citation":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/action/citation_signature","submit_replication":"https://pith.science/pith/FLY3QCTIIY7ZGJCJQD4FXYLBLZ/action/replication_record"}},"created_at":"2026-07-03T01:17:28.155072+00:00","updated_at":"2026-07-03T01:17:28.155072+00:00"}