{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5UUMGBAFWOYT34TXGLCO6NJY7Q","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":"927fe0c2b3a8c0d8453d21d603a6c6a366bb3852ac3fbfd7605aa98ec7d4d48c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T04:13:02Z","title_canon_sha256":"8a5275c6339a59a9d6e0c1c564c642341c9080cc1f8f5318130f67b09e328ca6"},"schema_version":"1.0","source":{"id":"2503.05126","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05126","created_at":"2026-07-05T10:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05126v3","created_at":"2026-07-05T10:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05126","created_at":"2026-07-05T10:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"5UUMGBAFWOYT","created_at":"2026-07-05T10:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"5UUMGBAFWOYT34TX","created_at":"2026-07-05T10:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"5UUMGBAF","created_at":"2026-07-05T10:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:470c9f69ee9a5b0d9fbd6d199e8db4b4a6cd85c9802aad98e506088553d789ed","target":"graph","created_at":"2026-07-05T10:29:36Z","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/2503.05126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task reinforcement learning (MTRL) aims to endow a single agent with the ability to perform well on multiple tasks. Recent works have focused on developing novel sophisticated architectures to improve performance, often resulting in larger models; it is unclear, however, whether the performance gains are a consequence of the architecture design itself or the extra parameters. We argue that gains are mostly due to scale by demonstrating that naively scaling up a simple MTRL baseline to match parameter counts outperforms the more sophisticated architectures, and these gains benefit most fr","authors_text":"Evangelos Chatzaroulas, Isaac Woungang, Jordan Terry, Nariman Farsad, Pablo Samuel Castro, Reginald McLean","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T04:13:02Z","title":"Multi-Task Reinforcement Learning Enables Parameter Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05126","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":"sha256:0f24e2f9345f638ff45e5df2f5aaa1e096de11eaa95f1cfcca1723d363a457ff","target":"record","created_at":"2026-07-05T10:29:36Z","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":"927fe0c2b3a8c0d8453d21d603a6c6a366bb3852ac3fbfd7605aa98ec7d4d48c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T04:13:02Z","title_canon_sha256":"8a5275c6339a59a9d6e0c1c564c642341c9080cc1f8f5318130f67b09e328ca6"},"schema_version":"1.0","source":{"id":"2503.05126","kind":"arxiv","version":3}},"canonical_sha256":"ed28c30405b3b13df27732c4ef3538fc3d43bacc5cdce4f8951ef9a9ad127ae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed28c30405b3b13df27732c4ef3538fc3d43bacc5cdce4f8951ef9a9ad127ae8","first_computed_at":"2026-07-05T10:29:36.484824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:36.484824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4WxAXOG5PH8/zz0KC3H94R2RLBcdBo+aOl5YFgjpGQKcWKgaHpMmvlZrDWEDoTv6087vZerLIl7BGV5+Cl99CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:36.485777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05126","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f24e2f9345f638ff45e5df2f5aaa1e096de11eaa95f1cfcca1723d363a457ff","sha256:470c9f69ee9a5b0d9fbd6d199e8db4b4a6cd85c9802aad98e506088553d789ed"],"state_sha256":"699f5c860d62616c762b22f55613447cbe856785c3b57a24e79c76c853a71ad7"}