{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YOOFY5LSQFAEQLR7HQVZJEU5PQ","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":"0dd8e085bff2d8d19833fd44c2c7ede4cc907bfd4b2e4078d8d033d7864cec0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:20:53Z","title_canon_sha256":"3c54e5f19c35ed673a3db1132cea540b3a7d458e04d9ff88725c9b7147252b9c"},"schema_version":"1.0","source":{"id":"2410.09754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09754","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09754v2","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09754","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"YOOFY5LSQFAE","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"YOOFY5LSQFAEQLR7","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"YOOFY5LS","created_at":"2026-07-05T11:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:0c88fcdfcf072462fcbf791c2f8f3ecf52eddc116fbd6cf40374ab7d3eb50301","target":"graph","created_at":"2026-07-05T11:11:35Z","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/2410.09754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating components that induce a simplicity bias, guiding models toward simple and generalizable solutions. However, in deep RL, designing and scaling up networks have been less explored. Motivated by this opportunity, we present SimBa, an architecture designed to scale up parameters in deep RL by injecting a simplicity bias. SimBa consists of three components: ","authors_text":"Donghu Kim, Dongyoon Hwang, Hojoon Lee, Hyunseung Kim, Jaegul Choo, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Peter Stone, Takuma Seno","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:20:53Z","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09754","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":"sha256:6c3c89b49699a3f6e903823642e4641ddbfffc8427adaea154a9771084a9245d","target":"record","created_at":"2026-07-05T11:11:35Z","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":"0dd8e085bff2d8d19833fd44c2c7ede4cc907bfd4b2e4078d8d033d7864cec0a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:20:53Z","title_canon_sha256":"3c54e5f19c35ed673a3db1132cea540b3a7d458e04d9ff88725c9b7147252b9c"},"schema_version":"1.0","source":{"id":"2410.09754","kind":"arxiv","version":2}},"canonical_sha256":"c39c5c75728140482e3f3c2b94929d7c2083680d5532ccb38be1ed908c30c2bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c39c5c75728140482e3f3c2b94929d7c2083680d5532ccb38be1ed908c30c2bd","first_computed_at":"2026-07-05T11:11:35.795597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:35.795597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJK/QLlKXPDOc+hOJw8qV/5DF6C9Y4KGYoDBsDiO1Er9aj/L4ZqLfplTAnl1f9n7Ix6+Hg8aBz9wh/FB1gPgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:35.796089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c3c89b49699a3f6e903823642e4641ddbfffc8427adaea154a9771084a9245d","sha256:0c88fcdfcf072462fcbf791c2f8f3ecf52eddc116fbd6cf40374ab7d3eb50301"],"state_sha256":"5d1cf589f3989ede3c2b8554eddffe05569b21157fb8f75f97c2bf7462f55508"}