{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YFE5TSVZH4IPEPUZTYSPMOWQBB","short_pith_number":"pith:YFE5TSVZ","canonical_record":{"source":{"id":"2402.08609","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T17:18:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fd953777ae88d99cc1dc41e5fa5be2a8fd8f0b893627c6accb5efe7107cdc59","abstract_canon_sha256":"33e0a16c29754bbff23e1b7707730ae8c869e519e6f226ff49e8c4a3b800d402"},"schema_version":"1.0"},"canonical_sha256":"c149d9cab93f10f23e999e24f63ad0085b35c2e67bb291a0a272b4607f96acc1","source":{"kind":"arxiv","id":"2402.08609","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YFE5TSVZH4IPEPUZTYSPMOWQBB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08609","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T17:18:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fd953777ae88d99cc1dc41e5fa5be2a8fd8f0b893627c6accb5efe7107cdc59","abstract_canon_sha256":"33e0a16c29754bbff23e1b7707730ae8c869e519e6f226ff49e8c4a3b800d402"},"schema_version":"1.0"},"canonical_sha256":"c149d9cab93f10f23e999e24f63ad0085b35c2e67bb291a0a272b4607f96acc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:04.803527Z","signature_b64":"eNB2KmEKpORilgXFkDrBFliYIprS454d19Fopd7GMKy2vsKuZhk5bYqGr3srHelghWAyYAoXcvIXbmkTJyDUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c149d9cab93f10f23e999e24f63ad0085b35c2e67bb291a0a272b4607f96acc1","last_reissued_at":"2026-07-05T08:37:04.803009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:04.803009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08609","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvounKt/5muMYizWr40TXdo4jqCg+swJi3/mZ3jAA61bM0mzhlgLxpdMH3f7iRfobzzWkV6w8U////2aqL3qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:48:46.569708Z"},"content_sha256":"89d0f533d10ff2fe434a3b4b04b4905e05aaa11026c5328456883019fdf5f1f1","schema_version":"1.0","event_id":"sha256:89d0f533d10ff2fe434a3b4b04b4905e05aaa11026c5328456883019fdf5f1f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YFE5TSVZH4IPEPUZTYSPMOWQBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clare Lyle, Doina Precup, Ghada Sokar, Gintare Karolina Dziugaite, Jakob Foerster, Jesse Farebrother, Johan Obando-Ceron, Pablo Samuel Castro, Timon Willi","submitted_at":"2024-02-13T17:18:56Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08609","kind":"arxiv","version":3},"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/2402.08609/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":"2026-07-05T08:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRctzKbuql/a08AoVgEFIhhEH71++Gpk/HLYfHYuov+ocI99XKVRqrb2kKLrNShnl4RF5p5QXl9AWcnm61i/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:48:46.570200Z"},"content_sha256":"61188582acd92e7967499d3f6adb2baea54c04d8b557b9f91f6e2095df248f45","schema_version":"1.0","event_id":"sha256:61188582acd92e7967499d3f6adb2baea54c04d8b557b9f91f6e2095df248f45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/bundle.json","state_url":"https://pith.science/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/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":"2026-08-06T07:48:46Z","links":{"resolver":"https://pith.science/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB","bundle":"https://pith.science/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/bundle.json","state":"https://pith.science/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFE5TSVZH4IPEPUZTYSPMOWQBB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BvQtVo+BEljTKt3rQ6DqIIz7B9MDCP+mvVoSi8f66TKUlEb+WQNe3toNvpkFT3tz1RzX1tXBrYMmH7PuLDHWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:48:46.573440Z","bundle_sha256":"c5b4dbac975aa50693aebfb4a38d0bd2ea2c48d3c4722b2c3c2c83d1c58b22d6"}}