{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LMM63Y4PV5LKJSGWCRRAE4GCAY","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":"ca880c1bdf168582edcb05465252da7854721485cbe4d00ec24406007e9b1c81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T14:03:33Z","title_canon_sha256":"537ca193a78b21f0765ca1edaa0b55bfc8222b2c62721b4ba052e5d92a216d1d"},"schema_version":"1.0","source":{"id":"2302.02788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02788","created_at":"2026-07-05T05:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02788v1","created_at":"2026-07-05T05:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02788","created_at":"2026-07-05T05:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"LMM63Y4PV5LK","created_at":"2026-07-05T05:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"LMM63Y4PV5LKJSGW","created_at":"2026-07-05T05:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"LMM63Y4P","created_at":"2026-07-05T05:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:339a11cd25772136aa908293203c29030fad71e1682dfe391e87c066ded9a384","target":"graph","created_at":"2026-07-05T05:39:06Z","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/2302.02788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making. We provide an easy-to-implement, novel algorithm for imitation learning under a strict data paradigm, in which the agent must learn solely from data collected a priori. This paradigm allows our algorithm to be used for environments in which safety or cost are of critical concern. Our algorithm requires no additional hyper-parameter tuning beyond any standard batch reinforcement learning (RL) algorithm, making it an ideal baseline for such data-strict regimes. Furthermore, we prov","authors_text":"Kamil Ciosek, Lucas Maystre, Matthew Smith, Zhenwen Dai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T14:03:33Z","title":"A Strong Baseline for Batch Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02788","kind":"arxiv","version":1},"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:cb8476126131682351a2dc92895a3177e00656191326f267ccce83ccdb3e80be","target":"record","created_at":"2026-07-05T05:39:06Z","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":"ca880c1bdf168582edcb05465252da7854721485cbe4d00ec24406007e9b1c81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T14:03:33Z","title_canon_sha256":"537ca193a78b21f0765ca1edaa0b55bfc8222b2c62721b4ba052e5d92a216d1d"},"schema_version":"1.0","source":{"id":"2302.02788","kind":"arxiv","version":1}},"canonical_sha256":"5b19ede38faf56a4c8d614620270c2060ddeb9397275be3f407db444e51a37f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b19ede38faf56a4c8d614620270c2060ddeb9397275be3f407db444e51a37f5","first_computed_at":"2026-07-05T05:39:06.717325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:06.717325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1JLen6im76nxKfL5Q4W+rA1wJ0b9ABfRIV6n0FXR+L/bOU80wMttyH+6nNrd7yjWatKcW82wyHAkaxZzlmqjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:06.717692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb8476126131682351a2dc92895a3177e00656191326f267ccce83ccdb3e80be","sha256:339a11cd25772136aa908293203c29030fad71e1682dfe391e87c066ded9a384"],"state_sha256":"a0e89f6aa52716047561202d07f311d12c3abdb6ef619523d49635ae96324542"}