{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WD22VE6UPEMYGT5BBFT36H7U3D","short_pith_number":"pith:WD22VE6U","canonical_record":{"source":{"id":"2603.06009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-06T08:07:08Z","cross_cats_sorted":[],"title_canon_sha256":"e09f892e55d0a02db9406e5a8eedc44d9fd57365c9bed6793948d2746c61b1be","abstract_canon_sha256":"536536c79eec2a3227c44f8850229814ddcafbcc439010f2f4afe7f00bfd5ee2"},"schema_version":"1.0"},"canonical_sha256":"b0f5aa93d47919834fa10967bf1ff4d8c0b50266f4bb6a4bda2618ce8b56af5c","source":{"kind":"arxiv","id":"2603.06009","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.06009","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2603.06009v2","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06009","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"WD22VE6UPEMY","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"WD22VE6UPEMYGT5B","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"WD22VE6U","created_at":"2026-07-21T00:19:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WD22VE6UPEMYGT5BBFT36H7U3D","target":"record","payload":{"canonical_record":{"source":{"id":"2603.06009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-06T08:07:08Z","cross_cats_sorted":[],"title_canon_sha256":"e09f892e55d0a02db9406e5a8eedc44d9fd57365c9bed6793948d2746c61b1be","abstract_canon_sha256":"536536c79eec2a3227c44f8850229814ddcafbcc439010f2f4afe7f00bfd5ee2"},"schema_version":"1.0"},"canonical_sha256":"b0f5aa93d47919834fa10967bf1ff4d8c0b50266f4bb6a4bda2618ce8b56af5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:19:56.449237Z","signature_b64":"yLmTzLqoyAgDq5epwAZuIIr+ldNT2K9h3MTdsxf1kDhk3rAi10l83Y7iq+MxgImBOZbKhL5z82ysN6lRZSnsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f5aa93d47919834fa10967bf1ff4d8c0b50266f4bb6a4bda2618ce8b56af5c","last_reissued_at":"2026-07-21T00:19:56.448256Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:19:56.448256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.06009","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":"2026-07-21T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aEkcn43csTipzyhYjse4OMelKgTAA7xI90O6eJQtjeE1daiSVKQPOX8jlNtbpdoHGWoHbAkeRWsJwYlh/2+nCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:39:38.299907Z"},"content_sha256":"a8c655a4c51bca5fb6b02fac5f41a5aff157059d771d4f5ae70dbf2f142591e2","schema_version":"1.0","event_id":"sha256:a8c655a4c51bca5fb6b02fac5f41a5aff157059d771d4f5ae70dbf2f142591e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WD22VE6UPEMYGT5BBFT36H7U3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Clare Lyle, Jakob Foerster, Khimya Khetarpal, Michael Beukman, Michael Dennis, Will Dabney, Zeyu Zheng","submitted_at":"2026-03-06T08:07:08Z","abstract_excerpt":"An agent's performance stagnating at a suboptimal level is a common problem in deep on-policy RL. Focusing on PPO, we show that plateaus in certain regimes arise not because of known exploration, capacity, or optimisation challenges, but because sample-based estimates of the loss eventually become poor proxies for the true objective over the course of training. Looking deeper, PPO alternates between sampling rollouts from several parallel environments online using the current policy (which we call the \"outer loop\") and performing repeated minibatch SGD steps against this offline dataset (the \""},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06009","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/2603.06009/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":"2026-07-21T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KDCBI/mAu4sp3DcC3c3cev5ZnSZSyJaOBEWWCBy6xmr/YBRnVN0tdkVShKuAhutqFgFVwt3PkN8KC4dlmllsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:39:38.300807Z"},"content_sha256":"107ceec0953c756d12096b49739201900f3b62c8703a57014f9d42dfa65f9722","schema_version":"1.0","event_id":"sha256:107ceec0953c756d12096b49739201900f3b62c8703a57014f9d42dfa65f9722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WD22VE6UPEMYGT5BBFT36H7U3D/bundle.json","state_url":"https://pith.science/pith/WD22VE6UPEMYGT5BBFT36H7U3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WD22VE6UPEMYGT5BBFT36H7U3D/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":"2026-08-03T17:39:38Z","links":{"resolver":"https://pith.science/pith/WD22VE6UPEMYGT5BBFT36H7U3D","bundle":"https://pith.science/pith/WD22VE6UPEMYGT5BBFT36H7U3D/bundle.json","state":"https://pith.science/pith/WD22VE6UPEMYGT5BBFT36H7U3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WD22VE6UPEMYGT5BBFT36H7U3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WD22VE6UPEMYGT5BBFT36H7U3D","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":"536536c79eec2a3227c44f8850229814ddcafbcc439010f2f4afe7f00bfd5ee2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-06T08:07:08Z","title_canon_sha256":"e09f892e55d0a02db9406e5a8eedc44d9fd57365c9bed6793948d2746c61b1be"},"schema_version":"1.0","source":{"id":"2603.06009","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.06009","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2603.06009v2","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06009","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"WD22VE6UPEMY","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"WD22VE6UPEMYGT5B","created_at":"2026-07-21T00:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"WD22VE6U","created_at":"2026-07-21T00:19:56Z"}],"graph_snapshots":[{"event_id":"sha256:107ceec0953c756d12096b49739201900f3b62c8703a57014f9d42dfa65f9722","target":"graph","created_at":"2026-07-21T00:19:56Z","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/2603.06009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An agent's performance stagnating at a suboptimal level is a common problem in deep on-policy RL. Focusing on PPO, we show that plateaus in certain regimes arise not because of known exploration, capacity, or optimisation challenges, but because sample-based estimates of the loss eventually become poor proxies for the true objective over the course of training. Looking deeper, PPO alternates between sampling rollouts from several parallel environments online using the current policy (which we call the \"outer loop\") and performing repeated minibatch SGD steps against this offline dataset (the \"","authors_text":"Clare Lyle, Jakob Foerster, Khimya Khetarpal, Michael Beukman, Michael Dennis, Will Dabney, Zeyu Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-06T08:07:08Z","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06009","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:a8c655a4c51bca5fb6b02fac5f41a5aff157059d771d4f5ae70dbf2f142591e2","target":"record","created_at":"2026-07-21T00:19:56Z","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":"536536c79eec2a3227c44f8850229814ddcafbcc439010f2f4afe7f00bfd5ee2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-06T08:07:08Z","title_canon_sha256":"e09f892e55d0a02db9406e5a8eedc44d9fd57365c9bed6793948d2746c61b1be"},"schema_version":"1.0","source":{"id":"2603.06009","kind":"arxiv","version":2}},"canonical_sha256":"b0f5aa93d47919834fa10967bf1ff4d8c0b50266f4bb6a4bda2618ce8b56af5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f5aa93d47919834fa10967bf1ff4d8c0b50266f4bb6a4bda2618ce8b56af5c","first_computed_at":"2026-07-21T00:19:56.448256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:19:56.448256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yLmTzLqoyAgDq5epwAZuIIr+ldNT2K9h3MTdsxf1kDhk3rAi10l83Y7iq+MxgImBOZbKhL5z82ysN6lRZSnsAA==","signature_status":"signed_v1","signed_at":"2026-07-21T00:19:56.449237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.06009","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8c655a4c51bca5fb6b02fac5f41a5aff157059d771d4f5ae70dbf2f142591e2","sha256:107ceec0953c756d12096b49739201900f3b62c8703a57014f9d42dfa65f9722"],"state_sha256":"41da856591e59a3a6fe482a6761f0015a54af0c155af0cfd5f272457cf3dec14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4lf9ap/hnRncgkL3vjqXYmcnBw8smKhlhSmT4gaeo/ES82hAWuyXNyqknGtzhBOgVUqp/kQoZpeEptbG6qrQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:39:38.308400Z","bundle_sha256":"2490e4a9efde174d69be04a1264a19c9de2481dfdb68f5871c6142e2377ac04b"}}