{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VA4Y7V4PFUACVAOAPUSWDD7B25","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":"735bb2cc758db04db3d0682322595dc27eb3476a343dd302e97cc7154a65a747","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T06:38:53Z","title_canon_sha256":"401b1d678a9a05a577be57e0fd7b1f7d56658be518e1d9155a6918acff41378e"},"schema_version":"1.0","source":{"id":"2301.13442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13442","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13442v2","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13442","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"VA4Y7V4PFUAC","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"VA4Y7V4PFUACVAOA","created_at":"2026-07-05T05:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"VA4Y7V4P","created_at":"2026-07-05T05:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:090d6551e5448be79e356f33a2b5b7677bda5dcb61927db296401e2fc55e9ef3","target":"graph","created_at":"2026-07-05T05:43:19Z","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/2301.13442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that, in generative modeling, cross-entropy loss improves smoothly with model size and training compute, following a power law plus constant scaling law. One challenge in extending these results to reinforcement learning is that the main performance objective of interest, mean episode return, need not vary smoothly. To overcome this, we introduce *intrinsic performance*, a monotonic function of the return defined as the minimum compute required to achieve the given return across a family of models of different sizes. We find that, across a range of environments, intrinsic","authors_text":"Jacob Hilton, Jie Tang, John Schulman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T06:38:53Z","title":"Scaling laws for single-agent reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13442","kind":"arxiv","version":2},"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:cf0374fa4594fa37a4685c3bc78356aa826407fdd085e2e29565a255aabb8b76","target":"record","created_at":"2026-07-05T05:43:19Z","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":"735bb2cc758db04db3d0682322595dc27eb3476a343dd302e97cc7154a65a747","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T06:38:53Z","title_canon_sha256":"401b1d678a9a05a577be57e0fd7b1f7d56658be518e1d9155a6918acff41378e"},"schema_version":"1.0","source":{"id":"2301.13442","kind":"arxiv","version":2}},"canonical_sha256":"a8398fd78f2d002a81c07d25618fe1d76818797372b66fda54aa9ca73cb8427c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8398fd78f2d002a81c07d25618fe1d76818797372b66fda54aa9ca73cb8427c","first_computed_at":"2026-07-05T05:43:19.429207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:19.429207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t02eHzcx4YwQnF0pDtIubLN3aftDhu/cFf2MYnodnVK6ZhcWbJAKyyI6Lb5PYitG1xWARgRPhYrdAt3R14C5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:19.429686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf0374fa4594fa37a4685c3bc78356aa826407fdd085e2e29565a255aabb8b76","sha256:090d6551e5448be79e356f33a2b5b7677bda5dcb61927db296401e2fc55e9ef3"],"state_sha256":"242c373b9fa884a1f9a3171cb0be191ab529552aaf4de9d8b7b405cfba979daa"}