{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B2GPPUQW4OI2IJEESTGSW5CM2Y","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":"5bd9d3ba8b6a5c86ae9306d56041af20857aef4d6d950e2caafbb8269a0047ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T15:13:17Z","title_canon_sha256":"7b4ec6de55587974f48a383d82130299ee9d5887b633c2004e474e1b284d4af1"},"schema_version":"1.0","source":{"id":"2410.08896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08896","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08896v2","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08896","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"B2GPPUQW4OI2","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"B2GPPUQW4OI2IJEE","created_at":"2026-07-05T10:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"B2GPPUQW","created_at":"2026-07-05T10:43:40Z"}],"graph_snapshots":[{"event_id":"sha256:880d6c43ab52bd9b4c309f27b4bbbb51c534825e230d66d9d2e586c37d0017f4","target":"graph","created_at":"2026-07-05T10:43:40Z","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/2410.08896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient steps for every new sample. While such high update-to-data (UTD) ratios have shown strong empirical performance, they also introduce instability to the training process. Previous approaches need to rely on periodic neural network parameter resets to address this instability, but restarting the training process is infeasible in many real-world applications and r","authors_text":"Amir-massoud Farahmand, Claas A Voelcker, Eric Eaton, Igor Gilitschenski, Marcel Hussing","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T15:13:17Z","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08896","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":"sha256:4ae71151633fa08f2f6efa7d65d92563b031773930da19c840c3ac22e6f8c304","target":"record","created_at":"2026-07-05T10:43:40Z","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":"5bd9d3ba8b6a5c86ae9306d56041af20857aef4d6d950e2caafbb8269a0047ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T15:13:17Z","title_canon_sha256":"7b4ec6de55587974f48a383d82130299ee9d5887b633c2004e474e1b284d4af1"},"schema_version":"1.0","source":{"id":"2410.08896","kind":"arxiv","version":2}},"canonical_sha256":"0e8cf7d216e391a4248494cd2b744cd632c772353f234c11231a8833a763bc0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e8cf7d216e391a4248494cd2b744cd632c772353f234c11231a8833a763bc0a","first_computed_at":"2026-07-05T10:43:40.117508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:40.117508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6gZV1tIxNvn1DR5+lrhQOl+8gpa8xOh0C+RB/XKr6df/B1SZtIIwLHhzim5rBt/6Z2JFDA89oJDzaskvN6fhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:40.117962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ae71151633fa08f2f6efa7d65d92563b031773930da19c840c3ac22e6f8c304","sha256:880d6c43ab52bd9b4c309f27b4bbbb51c534825e230d66d9d2e586c37d0017f4"],"state_sha256":"0e39ab06f5ba8d67733cfe639096ea29c35ede20c757883f283dfae9a6b6f8b8"}