{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4HIZSWHCPHGGQAGXVBGCEZPJZS","short_pith_number":"pith:4HIZSWHC","canonical_record":{"source":{"id":"2310.17805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T22:40:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d7f822bd7717afbae966c180fff725c568c1cadce95547a9b9ec98d8b306416","abstract_canon_sha256":"2d2c3cf86ff59ee60ee1344527c711ebe7e9fb8b5e139b320e906113b327e023"},"schema_version":"1.0"},"canonical_sha256":"e1d19958e279cc6800d7a84c2265e9cc8f772fbd2aab3625a6f7b1ac992bef6e","source":{"kind":"arxiv","id":"2310.17805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17805","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17805v1","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17805","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"4HIZSWHCPHGG","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"4HIZSWHCPHGGQAGX","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"4HIZSWHC","created_at":"2026-07-05T07:05:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4HIZSWHCPHGGQAGXVBGCEZPJZS","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T22:40:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d7f822bd7717afbae966c180fff725c568c1cadce95547a9b9ec98d8b306416","abstract_canon_sha256":"2d2c3cf86ff59ee60ee1344527c711ebe7e9fb8b5e139b320e906113b327e023"},"schema_version":"1.0"},"canonical_sha256":"e1d19958e279cc6800d7a84c2265e9cc8f772fbd2aab3625a6f7b1ac992bef6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:53.004433Z","signature_b64":"aoGybvEF7uQ8by/o4Cs3PoF6nRTilcjedy2iuVIVoAqDIygTu/d6j/yCrzaUNJOiZ/MEkTvcKDFRdS/RGehZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d19958e279cc6800d7a84c2265e9cc8f772fbd2aab3625a6f7b1ac992bef6e","last_reissued_at":"2026-07-05T07:05:53.004047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:53.004047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17805","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJyS1/iCAmHKoqr9LMPBqX1ZobKTow2gNbyhtgM8fNdL1ykDJ4J+UGqLCZMq0nU/k0EiA2YSqhdmmVXatw/EDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:49:49.500512Z"},"content_sha256":"2647325fe673160d7e2b55850e87548759da3cdc3db5135dacc7634009800049","schema_version":"1.0","event_id":"sha256:2647325fe673160d7e2b55850e87548759da3cdc3db5135dacc7634009800049"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4HIZSWHCPHGGQAGXVBGCEZPJZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akarsh Kumar, John P. Dickerson, Joseph Suarez, Ryan Sullivan, Shengyi Huang","submitted_at":"2023-10-26T22:40:30Z","abstract_excerpt":"Most reinforcement learning methods rely heavily on dense, well-normalized environment rewards. DreamerV3 recently introduced a model-based method with a number of tricks that mitigate these limitations, achieving state-of-the-art on a wide range of benchmarks with a single set of hyperparameters. This result sparked discussion about the generality of the tricks, since they appear to be applicable to other reinforcement learning algorithms. Our work applies DreamerV3's tricks to PPO and is the first such empirical study outside of the original work. Surprisingly, we find that the tricks presen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17805","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/2310.17805/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":"2026-07-05T07:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fC4Po1ll65SlX9EQB7BDBvFJK7IqOzfVXSB9n1SUKYDrpw1rIxJkzoeMb/c30q8Cx4/IOtkBLVde8XgVd/MJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:49:49.501149Z"},"content_sha256":"c595b52fe4dbeda53681382597c49f92b5c238c389a6689235625cffdbaff601","schema_version":"1.0","event_id":"sha256:c595b52fe4dbeda53681382597c49f92b5c238c389a6689235625cffdbaff601"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/bundle.json","state_url":"https://pith.science/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/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":"2026-07-07T07:49:49Z","links":{"resolver":"https://pith.science/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS","bundle":"https://pith.science/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/bundle.json","state":"https://pith.science/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HIZSWHCPHGGQAGXVBGCEZPJZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4HIZSWHCPHGGQAGXVBGCEZPJZS","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":"2d2c3cf86ff59ee60ee1344527c711ebe7e9fb8b5e139b320e906113b327e023","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T22:40:30Z","title_canon_sha256":"1d7f822bd7717afbae966c180fff725c568c1cadce95547a9b9ec98d8b306416"},"schema_version":"1.0","source":{"id":"2310.17805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17805","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17805v1","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17805","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"4HIZSWHCPHGG","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"4HIZSWHCPHGGQAGX","created_at":"2026-07-05T07:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"4HIZSWHC","created_at":"2026-07-05T07:05:53Z"}],"graph_snapshots":[{"event_id":"sha256:c595b52fe4dbeda53681382597c49f92b5c238c389a6689235625cffdbaff601","target":"graph","created_at":"2026-07-05T07:05:53Z","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/2310.17805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most reinforcement learning methods rely heavily on dense, well-normalized environment rewards. DreamerV3 recently introduced a model-based method with a number of tricks that mitigate these limitations, achieving state-of-the-art on a wide range of benchmarks with a single set of hyperparameters. This result sparked discussion about the generality of the tricks, since they appear to be applicable to other reinforcement learning algorithms. Our work applies DreamerV3's tricks to PPO and is the first such empirical study outside of the original work. Surprisingly, we find that the tricks presen","authors_text":"Akarsh Kumar, John P. Dickerson, Joseph Suarez, Ryan Sullivan, Shengyi Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T22:40:30Z","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17805","kind":"arxiv","version":1},"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":"sha256:2647325fe673160d7e2b55850e87548759da3cdc3db5135dacc7634009800049","target":"record","created_at":"2026-07-05T07:05:53Z","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":"2d2c3cf86ff59ee60ee1344527c711ebe7e9fb8b5e139b320e906113b327e023","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T22:40:30Z","title_canon_sha256":"1d7f822bd7717afbae966c180fff725c568c1cadce95547a9b9ec98d8b306416"},"schema_version":"1.0","source":{"id":"2310.17805","kind":"arxiv","version":1}},"canonical_sha256":"e1d19958e279cc6800d7a84c2265e9cc8f772fbd2aab3625a6f7b1ac992bef6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d19958e279cc6800d7a84c2265e9cc8f772fbd2aab3625a6f7b1ac992bef6e","first_computed_at":"2026-07-05T07:05:53.004047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:53.004047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aoGybvEF7uQ8by/o4Cs3PoF6nRTilcjedy2iuVIVoAqDIygTu/d6j/yCrzaUNJOiZ/MEkTvcKDFRdS/RGehZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:53.004433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2647325fe673160d7e2b55850e87548759da3cdc3db5135dacc7634009800049","sha256:c595b52fe4dbeda53681382597c49f92b5c238c389a6689235625cffdbaff601"],"state_sha256":"6f600d6173f01d59ab72c1488894b8123773283bdd05b142dec18fefc5f75fca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2MIrVMkUM10XAYGAredItet4/EPYz6zulDjMkA/zHOP7HLJbnbkwp/3ngbE9vmY8PRR0QvIdUnc6fKZirLeFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:49:49.504239Z","bundle_sha256":"472f84742615fd5c8f5835f457fcbc6804afa20dd954c206aa2551d24d2047e8"}}