{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QKO3I3MI7B6RC6KJY75OLXFRD7","short_pith_number":"pith:QKO3I3MI","schema_version":"1.0","canonical_sha256":"829db46d88f87d117949c7fae5dcb11ffe5e4ab52f54feaf3b7be7cb2ce8022d","source":{"kind":"arxiv","id":"2311.18206","version":3},"attestation_state":"computed","paper":{"title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haruka Kiyohara, Kazuhide Nakata, Ken Kobayashi, Kosuke Kawakami, Ren Kishimoto, Yuta Saito","submitted_at":"2023-11-30T02:56:43Z","abstract_excerpt":"This paper introduces SCOPE-RL, a comprehensive open-source Python software designed for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection (OPS). Unlike most existing libraries that focus solely on either policy learning or evaluation, SCOPE-RL seamlessly integrates these two key aspects, facilitating flexible and complete implementations of both offline RL and OPE processes. SCOPE-RL put particular emphasis on its OPE modules, offering a range of OPE estimators and robust evaluation-of-OPE protocols. This approach enables more in-depth and reliable OPE co"},"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":"2311.18206","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T02:56:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac23556c5d1935b741d812be02ea21c8bd0dda8eacc7f496d8f0f60c78e85f7f","abstract_canon_sha256":"95ac30721e57af871e11d0022d1a84054970d1df46051dd7d7415b6840f794bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:06.383898Z","signature_b64":"8EQ2qpGv5WexIrN3u1K5XLI4WKMw9lGDFqPSQpP5V4w4SwtRdA2vBBxMmpQO1SE4Yjo/Vms0fCMsOM+B4IPgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"829db46d88f87d117949c7fae5dcb11ffe5e4ab52f54feaf3b7be7cb2ce8022d","last_reissued_at":"2026-07-05T07:54:06.383369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:06.383369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haruka Kiyohara, Kazuhide Nakata, Ken Kobayashi, Kosuke Kawakami, Ren Kishimoto, Yuta Saito","submitted_at":"2023-11-30T02:56:43Z","abstract_excerpt":"This paper introduces SCOPE-RL, a comprehensive open-source Python software designed for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection (OPS). Unlike most existing libraries that focus solely on either policy learning or evaluation, SCOPE-RL seamlessly integrates these two key aspects, facilitating flexible and complete implementations of both offline RL and OPE processes. SCOPE-RL put particular emphasis on its OPE modules, offering a range of OPE estimators and robust evaluation-of-OPE protocols. This approach enables more in-depth and reliable OPE co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18206","kind":"arxiv","version":3},"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/2311.18206/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":"2311.18206","created_at":"2026-07-05T07:54:06.383428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18206v3","created_at":"2026-07-05T07:54:06.383428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18206","created_at":"2026-07-05T07:54:06.383428+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKO3I3MI7B6R","created_at":"2026-07-05T07:54:06.383428+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKO3I3MI7B6RC6KJ","created_at":"2026-07-05T07:54:06.383428+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKO3I3MI","created_at":"2026-07-05T07:54:06.383428+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/QKO3I3MI7B6RC6KJY75OLXFRD7","json":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7.json","graph_json":"https://pith.science/api/pith-number/QKO3I3MI7B6RC6KJY75OLXFRD7/graph.json","events_json":"https://pith.science/api/pith-number/QKO3I3MI7B6RC6KJY75OLXFRD7/events.json","paper":"https://pith.science/paper/QKO3I3MI"},"agent_actions":{"view_html":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7","download_json":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7.json","view_paper":"https://pith.science/paper/QKO3I3MI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18206&json=true","fetch_graph":"https://pith.science/api/pith-number/QKO3I3MI7B6RC6KJY75OLXFRD7/graph.json","fetch_events":"https://pith.science/api/pith-number/QKO3I3MI7B6RC6KJY75OLXFRD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7/action/storage_attestation","attest_author":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7/action/author_attestation","sign_citation":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7/action/citation_signature","submit_replication":"https://pith.science/pith/QKO3I3MI7B6RC6KJY75OLXFRD7/action/replication_record"}},"created_at":"2026-07-05T07:54:06.383428+00:00","updated_at":"2026-07-05T07:54:06.383428+00:00"}