{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UQOYGOA2IKEVBGKZMEUHSTA2T3","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":"df098b60ac5770e930055f6718a2cedad302916cccb336cec7d7414972e5d1c4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T14:00:03Z","title_canon_sha256":"899dd60df41a93e4c28eed0baf6b7efdacd282b1ca4ee410175147b690f37d71"},"schema_version":"1.0","source":{"id":"2506.01016","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01016","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01016v3","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01016","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"UQOYGOA2IKEV","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"UQOYGOA2IKEVBGKZ","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"UQOYGOA2","created_at":"2026-07-05T11:53:47Z"}],"graph_snapshots":[{"event_id":"sha256:b8ff4ead7d3d6acd8cb9c80e35438f6964c764fa97f6538ef095b7c7f0517b28","target":"graph","created_at":"2026-07-05T11:53:47Z","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/2506.01016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, smaller actors result in performance degradation and overfit critics. Our analyses suggest poor data co","authors_text":"Dhruv Sreenivas, Olya Mastikhina, Pablo Samuel Castro","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T14:00:03Z","title":"Optimistic critics can empower small actors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01016","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":"sha256:542252816082067a198feb83d9777b7abcf530510d7cef11a24247e9fe72c6e7","target":"record","created_at":"2026-07-05T11:53:47Z","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":"df098b60ac5770e930055f6718a2cedad302916cccb336cec7d7414972e5d1c4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T14:00:03Z","title_canon_sha256":"899dd60df41a93e4c28eed0baf6b7efdacd282b1ca4ee410175147b690f37d71"},"schema_version":"1.0","source":{"id":"2506.01016","kind":"arxiv","version":3}},"canonical_sha256":"a41d83381a42895099596128794c1a9ef896f85b9e335da41b55ab17ab19cb53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a41d83381a42895099596128794c1a9ef896f85b9e335da41b55ab17ab19cb53","first_computed_at":"2026-07-05T11:53:47.333879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:47.333879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NolLlQbj+gw3+gdgvRCCcmnEhrrZ1aB7/HTaCgySB0rZWDzjUIkgNqWS8daCEwjmDC0cDwFTWKxXhMZGgy9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:47.334436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01016","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:542252816082067a198feb83d9777b7abcf530510d7cef11a24247e9fe72c6e7","sha256:b8ff4ead7d3d6acd8cb9c80e35438f6964c764fa97f6538ef095b7c7f0517b28"],"state_sha256":"703ed43e492026b2e0f8c00159361ed1bdc7388302d55034fdcd4a646860bc96"}