{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2HYFFQLAHCC5B6QY3HZKQAJNIP","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":"76f1a2dd25285eea70484df8554934f9c6c5185eef7f876a00ded6cd8a4cc6e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:45:57Z","title_canon_sha256":"ff0e153bcec440ed9aed48ae8a245b5be81b47910e1b62e590a703d9d6034679"},"schema_version":"1.0","source":{"id":"2602.05999","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.05999","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2602.05999v4","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05999","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"2HYFFQLAHCC5","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"2HYFFQLAHCC5B6QY","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"2HYFFQLA","created_at":"2026-07-03T01:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:4d0dd7ad4d1622470886d7ee1ddb53c9881e37411b51c1222a88de3905982fa1","target":"graph","created_at":"2026-07-03T01:17:17Z","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/2602.05999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a language to answer these questions formally. Empirically, deep RL policies are often parameterized as neural networks with static architectures, conflating the amount of compute and the number of parameters. In this paper, we formalize compute bounded policies and prove that policies which use more compute can solve problems and generalize to longer-horizon tasks","authors_text":"Alicja Ziarko, Benjamin Eysenbach, Micha{\\l} Bortkiewicz, Raj Ghugare","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:45:57Z","title":"On the Role of Computation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05999","kind":"arxiv","version":4},"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":"sha256:7a1e399eda3da8c1871e72d32affc1a772299844abe3ef75b5dad60fb899a4f8","target":"record","created_at":"2026-07-03T01:17:17Z","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":"76f1a2dd25285eea70484df8554934f9c6c5185eef7f876a00ded6cd8a4cc6e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:45:57Z","title_canon_sha256":"ff0e153bcec440ed9aed48ae8a245b5be81b47910e1b62e590a703d9d6034679"},"schema_version":"1.0","source":{"id":"2602.05999","kind":"arxiv","version":4}},"canonical_sha256":"d1f052c1603885d0fa18d9f2a8012d43f2346d663b1635a1c8552ab6a2242abb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1f052c1603885d0fa18d9f2a8012d43f2346d663b1635a1c8552ab6a2242abb","first_computed_at":"2026-07-03T01:17:17.288915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:17.288915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5GiOT1lmCd1LnCX4JYkTK8OslQP87KZ3WYUO4jbTP7nWx/SuUCtkrSG7BjkVkmtbgxIBkHVg8PgkHFWmv/oyCw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:17.289368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.05999","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a1e399eda3da8c1871e72d32affc1a772299844abe3ef75b5dad60fb899a4f8","sha256:4d0dd7ad4d1622470886d7ee1ddb53c9881e37411b51c1222a88de3905982fa1"],"state_sha256":"47c5b1ef9506286f53d804e33a20d12057eb9c3e187555e9a5693b498848a87f"}