{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VA4Y7V4PFUACVAOAPUSWDD7B25","short_pith_number":"pith:VA4Y7V4P","canonical_record":{"source":{"id":"2301.13442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T06:38:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"401b1d678a9a05a577be57e0fd7b1f7d56658be518e1d9155a6918acff41378e","abstract_canon_sha256":"735bb2cc758db04db3d0682322595dc27eb3476a343dd302e97cc7154a65a747"},"schema_version":"1.0"},"canonical_sha256":"a8398fd78f2d002a81c07d25618fe1d76818797372b66fda54aa9ca73cb8427c","source":{"kind":"arxiv","id":"2301.13442","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VA4Y7V4PFUACVAOAPUSWDD7B25","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T06:38:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"401b1d678a9a05a577be57e0fd7b1f7d56658be518e1d9155a6918acff41378e","abstract_canon_sha256":"735bb2cc758db04db3d0682322595dc27eb3476a343dd302e97cc7154a65a747"},"schema_version":"1.0"},"canonical_sha256":"a8398fd78f2d002a81c07d25618fe1d76818797372b66fda54aa9ca73cb8427c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:19.429686Z","signature_b64":"t02eHzcx4YwQnF0pDtIubLN3aftDhu/cFf2MYnodnVK6ZhcWbJAKyyI6Lb5PYitG1xWARgRPhYrdAt3R14C5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8398fd78f2d002a81c07d25618fe1d76818797372b66fda54aa9ca73cb8427c","last_reissued_at":"2026-07-05T05:43:19.429207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:19.429207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13442","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Se1Omf78oUpu3+DdRG/m8rOQTQmaQ1IOBWZ2Pq74MZOp3Yyxta2r2zgzlFElftQGppB+gaj/STvD2mfiiLRiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:12:36.567099Z"},"content_sha256":"cf0374fa4594fa37a4685c3bc78356aa826407fdd085e2e29565a255aabb8b76","schema_version":"1.0","event_id":"sha256:cf0374fa4594fa37a4685c3bc78356aa826407fdd085e2e29565a255aabb8b76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VA4Y7V4PFUACVAOAPUSWDD7B25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling laws for single-agent reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Hilton, Jie Tang, John Schulman","submitted_at":"2023-01-31T06:38:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13442","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/2301.13442/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:43:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2uzSJY/a89DTTgyoqtZSixekX0tGFBldLjpA0FzSNTgEJJZfXwdApoLEv7SvXC+Yd6RVpJtrPEFQQCjfivrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:12:36.567610Z"},"content_sha256":"090d6551e5448be79e356f33a2b5b7677bda5dcb61927db296401e2fc55e9ef3","schema_version":"1.0","event_id":"sha256:090d6551e5448be79e356f33a2b5b7677bda5dcb61927db296401e2fc55e9ef3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/bundle.json","state_url":"https://pith.science/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:12:36Z","links":{"resolver":"https://pith.science/pith/VA4Y7V4PFUACVAOAPUSWDD7B25","bundle":"https://pith.science/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/bundle.json","state":"https://pith.science/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VA4Y7V4PFUACVAOAPUSWDD7B25/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDYPH+ZpqJtUgrzOSUpooVK+znc2KWIN8J0jJ/uV5NggAgRi71EsaMAKPpEOXqadZho3kZg7I8FaVVMZg8iWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:12:36.571327Z","bundle_sha256":"57d996a6d75ea83350004100ac9fcf20c4a031a062b9c16e51e9483eb4090673"}}