{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7CML3HRAHXWGQWZ4YLFAIAKYY4","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":"abc44779fc44bdb318f580e8f39cfd3d170cc735a89be3b848296f10c4c9b6e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T22:55:34Z","title_canon_sha256":"e96e8d20475a4f0f0564ca09d8dbeef4d63472dc031f15edf36b0edeb7a43bc4"},"schema_version":"1.0","source":{"id":"2305.03870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03870","created_at":"2026-07-05T06:08:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03870v2","created_at":"2026-07-05T06:08:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03870","created_at":"2026-07-05T06:08:38Z"},{"alias_kind":"pith_short_12","alias_value":"7CML3HRAHXWG","created_at":"2026-07-05T06:08:38Z"},{"alias_kind":"pith_short_16","alias_value":"7CML3HRAHXWGQWZ4","created_at":"2026-07-05T06:08:38Z"},{"alias_kind":"pith_short_8","alias_value":"7CML3HRA","created_at":"2026-07-05T06:08:38Z"}],"graph_snapshots":[{"event_id":"sha256:392a51aa21c3da32a038487886552a55250ca3d259ab580cb1535f170c0c88b9","target":"graph","created_at":"2026-07-05T06:08:38Z","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/2305.03870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard approaches to sequential decision-making exploit an agent's ability to continually interact with its environment and improve its control policy. However, due to safety, ethical, and practicality constraints, this type of trial-and-error experimentation is often infeasible in many real-world domains such as healthcare and robotics. Instead, control policies in these domains are typically trained offline from previously logged data or in a growing-batch manner. In this setting a fixed policy is deployed to the environment and used to gather an entire batch of new data before being aggre","authors_text":"Abram L. Friesen, Bobak Shahriari, Matt W. Hoffman, Nando de Freitas, Patrick Emedom-Nnamdi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T22:55:34Z","title":"Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03870","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":"sha256:825b09b1e9e8b593fb97c735e555de9935df759086c927698c4fa5efbf4b2a57","target":"record","created_at":"2026-07-05T06:08:38Z","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":"abc44779fc44bdb318f580e8f39cfd3d170cc735a89be3b848296f10c4c9b6e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T22:55:34Z","title_canon_sha256":"e96e8d20475a4f0f0564ca09d8dbeef4d63472dc031f15edf36b0edeb7a43bc4"},"schema_version":"1.0","source":{"id":"2305.03870","kind":"arxiv","version":2}},"canonical_sha256":"f898bd9e203dec685b3cc2ca040158c71aec732a2da3b04dcd6ed74108aa25c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f898bd9e203dec685b3cc2ca040158c71aec732a2da3b04dcd6ed74108aa25c4","first_computed_at":"2026-07-05T06:08:38.832398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:38.832398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZOoo21oqc9kz7vdrBXcxsqs74Qsh5C7wfMn0Ewb5BUUzMMB0nVjbnp7GgS+Bo2hjHicU7WuBcY/UuBwXFQxsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:38.832792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:825b09b1e9e8b593fb97c735e555de9935df759086c927698c4fa5efbf4b2a57","sha256:392a51aa21c3da32a038487886552a55250ca3d259ab580cb1535f170c0c88b9"],"state_sha256":"d9aabaff8a1f4971746917c7f2e17d6db2ff142efbdb2ca61343dcdeee67aa9d"}