{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2HNFH5IF3JSQLG6SNQIQ5H62D6","short_pith_number":"pith:2HNFH5IF","schema_version":"1.0","canonical_sha256":"d1da53f505da65059bd26c110e9fda1fac4e7ea92f21777fa9ff16365360c1af","source":{"kind":"arxiv","id":"2607.13274","version":1},"attestation_state":"computed","paper":{"title":"Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Haseeb Shah, Lingwei Zhu, Martha White","submitted_at":"2026-07-14T21:20:42Z","abstract_excerpt":"Reinforcement learning is increasingly being considered for controlling real-world systems, from fusion plasma and autonomous vehicles to drug discovery and drinking water treatment, where reliability is essential and tuning budgets are limited. Actor-critic algorithms share a set of design decisions, such as how the policy is updated, how it represents the distribution over actions, how its gradient is estimated, and how often it is updated relative to the value estimator. Using a control task derived from a real water treatment plant, we analyze over 33,000 experiments to determine how these"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.13274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-14T21:20:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0459e419feee12ca942ae95a31ff61cc946d87e0f9510383a48adaa2331f326","abstract_canon_sha256":"eee6487b7bfae565861ca14b01917020d43e0c4a39086686caf11b4753fa77b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:06.973451Z","signature_b64":"wS1DB7wEbgsCpeUBbNZbN1nBm/w6mozdpfdg2+5hT4ri9dHGSc9DhuRLcswBep5PQQQXzhaJK721iNXofcMTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1da53f505da65059bd26c110e9fda1fac4e7ea92f21777fa9ff16365360c1af","last_reissued_at":"2026-07-16T00:22:06.972615Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:06.972615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Haseeb Shah, Lingwei Zhu, Martha White","submitted_at":"2026-07-14T21:20:42Z","abstract_excerpt":"Reinforcement learning is increasingly being considered for controlling real-world systems, from fusion plasma and autonomous vehicles to drug discovery and drinking water treatment, where reliability is essential and tuning budgets are limited. Actor-critic algorithms share a set of design decisions, such as how the policy is updated, how it represents the distribution over actions, how its gradient is estimated, and how often it is updated relative to the value estimator. Using a control task derived from a real water treatment plant, we analyze over 33,000 experiments to determine how these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13274","kind":"arxiv","version":1},"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/2607.13274/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.13274","created_at":"2026-07-16T00:22:06.973051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13274v1","created_at":"2026-07-16T00:22:06.973051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13274","created_at":"2026-07-16T00:22:06.973051+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HNFH5IF3JSQ","created_at":"2026-07-16T00:22:06.973051+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HNFH5IF3JSQLG6S","created_at":"2026-07-16T00:22:06.973051+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HNFH5IF","created_at":"2026-07-16T00:22:06.973051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6","json":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6.json","graph_json":"https://pith.science/api/pith-number/2HNFH5IF3JSQLG6SNQIQ5H62D6/graph.json","events_json":"https://pith.science/api/pith-number/2HNFH5IF3JSQLG6SNQIQ5H62D6/events.json","paper":"https://pith.science/paper/2HNFH5IF"},"agent_actions":{"view_html":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6","download_json":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6.json","view_paper":"https://pith.science/paper/2HNFH5IF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13274&json=true","fetch_graph":"https://pith.science/api/pith-number/2HNFH5IF3JSQLG6SNQIQ5H62D6/graph.json","fetch_events":"https://pith.science/api/pith-number/2HNFH5IF3JSQLG6SNQIQ5H62D6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6/action/storage_attestation","attest_author":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6/action/author_attestation","sign_citation":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6/action/citation_signature","submit_replication":"https://pith.science/pith/2HNFH5IF3JSQLG6SNQIQ5H62D6/action/replication_record"}},"created_at":"2026-07-16T00:22:06.973051+00:00","updated_at":"2026-07-16T00:22:06.973051+00:00"}