{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VWV5WRQPDIXEFI4V2KZZTUU44T","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":"95879412fcc3c8ffa139d9926d9db3f60d2c67212d8d2067aa5d824baf85c5b5","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T17:57:06Z","title_canon_sha256":"c2ed634e68e8583712d0c6300f118e58d17968a81281cfd7cf1f29a3dbc3ce9c"},"schema_version":"1.0","source":{"id":"1906.01624","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01624","created_at":"2026-07-05T00:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01624v3","created_at":"2026-07-05T00:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01624","created_at":"2026-07-05T00:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"VWV5WRQPDIXE","created_at":"2026-07-05T00:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"VWV5WRQPDIXEFI4V","created_at":"2026-07-05T00:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"VWV5WRQP","created_at":"2026-07-05T00:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:be74d4cf0ee2ac6170cabb390bf2d82bcd65d3cbd0f2b475a884cfe513fb860b","target":"graph","created_at":"2026-07-05T00:21:22Z","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/1906.01624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment. However, comparing models in a real-world environment for the purposes of early stopping or hyperparameter tuning is costly and often practically infeasible. This leads us to examine off-policy policy evaluation (OPE) in such settings. We focus on OPE for value-based methods, which are of particular interest in deep RL, with applications like robotics, where","authors_text":"Alex Irpan, Chris Harris, Julian Ibarz, Kanishka Rao, Konstantinos Bousmalis, Sergey Levine","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T17:57:06Z","title":"Off-Policy Evaluation via Off-Policy Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01624","kind":"arxiv","version":3},"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:f6717f1f0a419535cfaefe8d02b6e43c9b65a8b96396390d2e4091c6bdd47508","target":"record","created_at":"2026-07-05T00:21:22Z","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":"95879412fcc3c8ffa139d9926d9db3f60d2c67212d8d2067aa5d824baf85c5b5","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T17:57:06Z","title_canon_sha256":"c2ed634e68e8583712d0c6300f118e58d17968a81281cfd7cf1f29a3dbc3ce9c"},"schema_version":"1.0","source":{"id":"1906.01624","kind":"arxiv","version":3}},"canonical_sha256":"adabdb460f1a2e42a395d2b399d29ce4c519b0b5edb836b0bba4b75e57d332eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adabdb460f1a2e42a395d2b399d29ce4c519b0b5edb836b0bba4b75e57d332eb","first_computed_at":"2026-07-05T00:21:22.994938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:22.994938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zBd4TYMfpc6L1F+4gL6yFx8QrrHrYBkpu6rMK4law05HvHhPYXwwIxqcnxGP/vA+ZNEGFjREgk6c0k0rKqVOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:22.995407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01624","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6717f1f0a419535cfaefe8d02b6e43c9b65a8b96396390d2e4091c6bdd47508","sha256:be74d4cf0ee2ac6170cabb390bf2d82bcd65d3cbd0f2b475a884cfe513fb860b"],"state_sha256":"382b5240a1f7bd4e45911de316afe17828401a49166e29de89b85b7da81c8985"}