{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RAIUAFB42WSLLI3ECALS7HSAE6","short_pith_number":"pith:RAIUAFB4","canonical_record":{"source":{"id":"2007.09055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T15:30:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"26b0a9833ca62339d327e11df501820a8d74affa1d8d789254c8e12f30003e6b","abstract_canon_sha256":"fccbe34773f3724a45824afb22303065bf978871b28704751a149caee9a7ca95"},"schema_version":"1.0"},"canonical_sha256":"881140143cd5a4b5a36410172f9e40279c3c0febc060a09b5d49644eb1a6e5c4","source":{"kind":"arxiv","id":"2007.09055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09055","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09055v1","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09055","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"RAIUAFB42WSL","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"RAIUAFB42WSLLI3E","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"RAIUAFB4","created_at":"2026-07-05T01:20:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RAIUAFB42WSLLI3ECALS7HSAE6","target":"record","payload":{"canonical_record":{"source":{"id":"2007.09055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T15:30:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"26b0a9833ca62339d327e11df501820a8d74affa1d8d789254c8e12f30003e6b","abstract_canon_sha256":"fccbe34773f3724a45824afb22303065bf978871b28704751a149caee9a7ca95"},"schema_version":"1.0"},"canonical_sha256":"881140143cd5a4b5a36410172f9e40279c3c0febc060a09b5d49644eb1a6e5c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:06.486674Z","signature_b64":"ZEgEzG1LLUIV69BJa/y0E6kBtXmE16H2Qp7fuGtKzYCAgTmDEcF28syQQTVCOCWcyiz2sloxEF6KrHgPbyLtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"881140143cd5a4b5a36410172f9e40279c3c0febc060a09b5d49644eb1a6e5c4","last_reissued_at":"2026-07-05T01:20:06.486159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:06.486159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.09055","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XSCvA00ZlEIs0bdl+8g/AA/XiL/EKOlY5M6+e6laaDXIJRr/Trm03Gfp1x9vCk4AgjP3bhAntHCDkK0LbHTlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:34:30.442951Z"},"content_sha256":"50bcb7c78b842b3807d34ea6fe5759c67c47764280a5b18f22890fb8aad2d17c","schema_version":"1.0","event_id":"sha256:50bcb7c78b842b3807d34ea6fe5759c67c47764280a5b18f22890fb8aad2d17c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RAIUAFB42WSLLI3ECALS7HSAE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperparameter Selection for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Novikov, Andrea Michi, Caglar Gulcehre, Cosmin Paduraru, Konrad Zolna, Nando de Freitas, Tom Le Paine, Ziyu Wang","submitted_at":"2020-07-17T15:30:38Z","abstract_excerpt":"Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by evaluating policies corresponding to each hyperparameter setting in the environment. This online execution is often infeasible and hence undermines the main aim of offline RL. Therefore, in this work, we focus on \\textit{offline hyperparameter selection}, i.e. methods for choosing the best policy from a set of many policies trained using different hyperparameters,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09055","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/2007.09055/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13J4aVZdznrejKl2BonTDBWXOMgwePQkW3vnM3PKsr9MnW1oCOpN/U7DODMMMQ1ZHNgt8Y7DiH4QVaxq+3YNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:34:30.443875Z"},"content_sha256":"1e8aa81a8d72ffbaba1db76250c727b53139bccbfe8b741785bf1b149a17e7cb","schema_version":"1.0","event_id":"sha256:1e8aa81a8d72ffbaba1db76250c727b53139bccbfe8b741785bf1b149a17e7cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RAIUAFB42WSLLI3ECALS7HSAE6/bundle.json","state_url":"https://pith.science/pith/RAIUAFB42WSLLI3ECALS7HSAE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RAIUAFB42WSLLI3ECALS7HSAE6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T20:34:30Z","links":{"resolver":"https://pith.science/pith/RAIUAFB42WSLLI3ECALS7HSAE6","bundle":"https://pith.science/pith/RAIUAFB42WSLLI3ECALS7HSAE6/bundle.json","state":"https://pith.science/pith/RAIUAFB42WSLLI3ECALS7HSAE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RAIUAFB42WSLLI3ECALS7HSAE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RAIUAFB42WSLLI3ECALS7HSAE6","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":"fccbe34773f3724a45824afb22303065bf978871b28704751a149caee9a7ca95","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T15:30:38Z","title_canon_sha256":"26b0a9833ca62339d327e11df501820a8d74affa1d8d789254c8e12f30003e6b"},"schema_version":"1.0","source":{"id":"2007.09055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09055","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09055v1","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09055","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"RAIUAFB42WSL","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"RAIUAFB42WSLLI3E","created_at":"2026-07-05T01:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"RAIUAFB4","created_at":"2026-07-05T01:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:1e8aa81a8d72ffbaba1db76250c727b53139bccbfe8b741785bf1b149a17e7cb","target":"graph","created_at":"2026-07-05T01:20:06Z","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/2007.09055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by evaluating policies corresponding to each hyperparameter setting in the environment. This online execution is often infeasible and hence undermines the main aim of offline RL. Therefore, in this work, we focus on \\textit{offline hyperparameter selection}, i.e. methods for choosing the best policy from a set of many policies trained using different hyperparameters,","authors_text":"Alexander Novikov, Andrea Michi, Caglar Gulcehre, Cosmin Paduraru, Konrad Zolna, Nando de Freitas, Tom Le Paine, Ziyu Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T15:30:38Z","title":"Hyperparameter Selection for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09055","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":"sha256:50bcb7c78b842b3807d34ea6fe5759c67c47764280a5b18f22890fb8aad2d17c","target":"record","created_at":"2026-07-05T01:20:06Z","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":"fccbe34773f3724a45824afb22303065bf978871b28704751a149caee9a7ca95","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T15:30:38Z","title_canon_sha256":"26b0a9833ca62339d327e11df501820a8d74affa1d8d789254c8e12f30003e6b"},"schema_version":"1.0","source":{"id":"2007.09055","kind":"arxiv","version":1}},"canonical_sha256":"881140143cd5a4b5a36410172f9e40279c3c0febc060a09b5d49644eb1a6e5c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"881140143cd5a4b5a36410172f9e40279c3c0febc060a09b5d49644eb1a6e5c4","first_computed_at":"2026-07-05T01:20:06.486159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:06.486159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZEgEzG1LLUIV69BJa/y0E6kBtXmE16H2Qp7fuGtKzYCAgTmDEcF28syQQTVCOCWcyiz2sloxEF6KrHgPbyLtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:06.486674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.09055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50bcb7c78b842b3807d34ea6fe5759c67c47764280a5b18f22890fb8aad2d17c","sha256:1e8aa81a8d72ffbaba1db76250c727b53139bccbfe8b741785bf1b149a17e7cb"],"state_sha256":"188df68f8a837d8fedde036bfa273a4b6980e04dd75e0c9a7daf33d65f871859"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3bF/07JsGaQX6Rimx/p5pydIODv2w6+g3Hl6slvkka5jc+Sbs+STpXulLbNvEtRsfs43TcXdxhba96CpYNkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:34:30.456682Z","bundle_sha256":"ee70cca4ed08904952acd5b32ae5afc487e3c0fdc3a12b266e5549aa34da59e9"}}