{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YFE5TSVZH4IPEPUZTYSPMOWQBB","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":"33e0a16c29754bbff23e1b7707730ae8c869e519e6f226ff49e8c4a3b800d402","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T17:18:56Z","title_canon_sha256":"5fd953777ae88d99cc1dc41e5fa5be2a8fd8f0b893627c6accb5efe7107cdc59"},"schema_version":"1.0","source":{"id":"2402.08609","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08609","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08609v3","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08609","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"YFE5TSVZH4IP","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"YFE5TSVZH4IPEPUZ","created_at":"2026-07-05T08:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"YFE5TSVZ","created_at":"2026-07-05T08:37:04Z"}],"graph_snapshots":[{"event_id":"sha256:61188582acd92e7967499d3f6adb2baea54c04d8b557b9f91f6e2095df248f45","target":"graph","created_at":"2026-07-05T08:37:04Z","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/2402.08609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a model often hurts its final performance. In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules, and in particular Soft MoEs (Puigcerver et al., 2023), into value-based networks results in more parameter-scalable models, evidenced by substantial performance increases across ","authors_text":"Clare Lyle, Doina Precup, Ghada Sokar, Gintare Karolina Dziugaite, Jakob Foerster, Jesse Farebrother, Johan Obando-Ceron, Pablo Samuel Castro, Timon Willi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T17:18:56Z","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08609","kind":"arxiv","version":3},"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":"sha256:89d0f533d10ff2fe434a3b4b04b4905e05aaa11026c5328456883019fdf5f1f1","target":"record","created_at":"2026-07-05T08:37:04Z","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":"33e0a16c29754bbff23e1b7707730ae8c869e519e6f226ff49e8c4a3b800d402","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T17:18:56Z","title_canon_sha256":"5fd953777ae88d99cc1dc41e5fa5be2a8fd8f0b893627c6accb5efe7107cdc59"},"schema_version":"1.0","source":{"id":"2402.08609","kind":"arxiv","version":3}},"canonical_sha256":"c149d9cab93f10f23e999e24f63ad0085b35c2e67bb291a0a272b4607f96acc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c149d9cab93f10f23e999e24f63ad0085b35c2e67bb291a0a272b4607f96acc1","first_computed_at":"2026-07-05T08:37:04.803009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:04.803009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eNB2KmEKpORilgXFkDrBFliYIprS454d19Fopd7GMKy2vsKuZhk5bYqGr3srHelghWAyYAoXcvIXbmkTJyDUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:04.803527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08609","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89d0f533d10ff2fe434a3b4b04b4905e05aaa11026c5328456883019fdf5f1f1","sha256:61188582acd92e7967499d3f6adb2baea54c04d8b557b9f91f6e2095df248f45"],"state_sha256":"12964e9f6d84e834480d09272f34a30003cec2eaaa16fa42419ca83df56216cb"}