{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GPJMLUMFNICYT2AUGC4JAZWHDX","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":"19f223d149443846ba6ad63d81237049d0f14903e5a642793cb09c4c5e664bce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:47Z","title_canon_sha256":"d977af2bbc6b06f092680fb67f0707a8a916ec31eb612eaa7d93a9aae5c51f32"},"schema_version":"1.0","source":{"id":"2502.04327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04327","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04327v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04327","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"GPJMLUMFNICY","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"GPJMLUMFNICYT2AU","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"GPJMLUMF","created_at":"2026-07-05T11:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:4d787562da6de72d83823147fa71b2f27d89a3e501777e4a8fe46443377567ed","target":"graph","created_at":"2026-07-05T11:42:53Z","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/2502.04327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling data and compute is critical to the success of modern ML. However, scaling demands predictability: we want methods to not only perform well with more compute or data, but also have their performance be predictable from small-scale runs, without running the large-scale experiment. In this paper, we show that value-based off-policy RL methods are predictable despite community lore regarding their pathological behavior. First, we show that data and compute requirements to attain a given performance level lie on a Pareto frontier, controlled by the updates-to-data (UTD) ratio. By estimatin","authors_text":"Aviral Kumar, Charlie Snell, Michal Nauman, Oleh Rybkin, Pieter Abbeel, Preston Fu, Sergey Levine","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:47Z","title":"Value-Based Deep RL Scales Predictably"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04327","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":"sha256:79865ac21acedfd6922ad700499047e33cfac598e29fb9e58ec915dc3bd1769f","target":"record","created_at":"2026-07-05T11:42:53Z","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":"19f223d149443846ba6ad63d81237049d0f14903e5a642793cb09c4c5e664bce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:47Z","title_canon_sha256":"d977af2bbc6b06f092680fb67f0707a8a916ec31eb612eaa7d93a9aae5c51f32"},"schema_version":"1.0","source":{"id":"2502.04327","kind":"arxiv","version":2}},"canonical_sha256":"33d2c5d1856a0589e81430b89066c71dc1e56ac171098ebd9c15d10eb5f9063c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33d2c5d1856a0589e81430b89066c71dc1e56ac171098ebd9c15d10eb5f9063c","first_computed_at":"2026-07-05T11:42:53.295261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:53.295261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7do2eS4ZL2PlO9/6GkqBr94qMHy83gTj7AdQvy1knx0e67uMB4RW3rgxNyq5Wvz5HQFXN9/VQLT0+uSPmRMCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:53.295702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79865ac21acedfd6922ad700499047e33cfac598e29fb9e58ec915dc3bd1769f","sha256:4d787562da6de72d83823147fa71b2f27d89a3e501777e4a8fe46443377567ed"],"state_sha256":"0f26ac9f6fce0f27dc54f956e0bbeb0c658f50ad5edafbdb7db3348dcc66f7a0"}