{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5XLXRYXRBBU654EAUTV62SWFCO","short_pith_number":"pith:5XLXRYXR","canonical_record":{"source":{"id":"2211.02016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T17:32:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e83948eed98087ee0bda851088c8c34f44a88dddf4128effaa3ba717bf85cd2f","abstract_canon_sha256":"16e9050db52af0bc0378a79f2c96b890b0e6d541b9efd7cdb1048c3b7bb79bed"},"schema_version":"1.0"},"canonical_sha256":"edd778e2f10869eef080a4ebed4ac513b18f926f4af00593c9eaf2db448e48b1","source":{"kind":"arxiv","id":"2211.02016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02016","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02016v1","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02016","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"5XLXRYXRBBU6","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"5XLXRYXRBBU654EA","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"5XLXRYXR","created_at":"2026-07-05T05:13:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5XLXRYXRBBU654EAUTV62SWFCO","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T17:32:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e83948eed98087ee0bda851088c8c34f44a88dddf4128effaa3ba717bf85cd2f","abstract_canon_sha256":"16e9050db52af0bc0378a79f2c96b890b0e6d541b9efd7cdb1048c3b7bb79bed"},"schema_version":"1.0"},"canonical_sha256":"edd778e2f10869eef080a4ebed4ac513b18f926f4af00593c9eaf2db448e48b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:02.550649Z","signature_b64":"h8yfxvA2P/ngzaNStp3qalUry0042l7RHk9giuOhPPwtNBMyHzrtLSvLjjv5yJ2jn8GMeYowyKoi2YPXm2xvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd778e2f10869eef080a4ebed4ac513b18f926f4af00593c9eaf2db448e48b1","last_reissued_at":"2026-07-05T05:13:02.550306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:02.550306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02016","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":"2026-07-05T05:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8DQBAg3C/Fp2/gMuhOfxjmzo+MXxFAbT8/tEOC8BK81SbpV0KSWl3F+j2HPBRS+C/Fx6U7Xxebn5aHiOJjuQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T14:22:30.033087Z"},"content_sha256":"354db8d659eaf0351b0c20d6a7adfbd0b3612e9cbb47d013284347cbb1635841","schema_version":"1.0","event_id":"sha256:354db8d659eaf0351b0c20d6a7adfbd0b3612e9cbb47d013284347cbb1635841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5XLXRYXRBBU654EAUTV62SWFCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Emma Brunskill, George Tucker, Jonathan N. Lee, Ofir Nachum","submitted_at":"2022-11-03T17:32:34Z","abstract_excerpt":"In offline reinforcement learning (RL), a learner leverages prior logged data to learn a good policy without interacting with the environment. A major challenge in applying such methods in practice is the lack of both theoretically principled and practical tools for model selection and evaluation. To address this, we study the problem of model selection in offline RL with value function approximation. The learner is given a nested sequence of model classes to minimize squared Bellman error and must select among these to achieve a balance between approximation and estimation error of the classe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02016","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/2211.02016/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":"2026-07-05T05:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xA9r5lvn+4M0Q1dJtfAhMEPcXn+A1ioOWk1MLyixVNoMhBRi8KbSGFIq5nM8voiJ223RT+ThiEfs6f6n6tzaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T14:22:30.033474Z"},"content_sha256":"a2fecbe32ce140f6a545a69802def36c721f6c994ab406be65248bdf461a0494","schema_version":"1.0","event_id":"sha256:a2fecbe32ce140f6a545a69802def36c721f6c994ab406be65248bdf461a0494"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XLXRYXRBBU654EAUTV62SWFCO/bundle.json","state_url":"https://pith.science/pith/5XLXRYXRBBU654EAUTV62SWFCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XLXRYXRBBU654EAUTV62SWFCO/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":"2026-07-17T14:22:30Z","links":{"resolver":"https://pith.science/pith/5XLXRYXRBBU654EAUTV62SWFCO","bundle":"https://pith.science/pith/5XLXRYXRBBU654EAUTV62SWFCO/bundle.json","state":"https://pith.science/pith/5XLXRYXRBBU654EAUTV62SWFCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XLXRYXRBBU654EAUTV62SWFCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5XLXRYXRBBU654EAUTV62SWFCO","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":"16e9050db52af0bc0378a79f2c96b890b0e6d541b9efd7cdb1048c3b7bb79bed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T17:32:34Z","title_canon_sha256":"e83948eed98087ee0bda851088c8c34f44a88dddf4128effaa3ba717bf85cd2f"},"schema_version":"1.0","source":{"id":"2211.02016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02016","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02016v1","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02016","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"5XLXRYXRBBU6","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"5XLXRYXRBBU654EA","created_at":"2026-07-05T05:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"5XLXRYXR","created_at":"2026-07-05T05:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:a2fecbe32ce140f6a545a69802def36c721f6c994ab406be65248bdf461a0494","target":"graph","created_at":"2026-07-05T05:13:02Z","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/2211.02016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL), a learner leverages prior logged data to learn a good policy without interacting with the environment. A major challenge in applying such methods in practice is the lack of both theoretically principled and practical tools for model selection and evaluation. To address this, we study the problem of model selection in offline RL with value function approximation. The learner is given a nested sequence of model classes to minimize squared Bellman error and must select among these to achieve a balance between approximation and estimation error of the classe","authors_text":"Bo Dai, Emma Brunskill, George Tucker, Jonathan N. Lee, Ofir Nachum","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T17:32:34Z","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02016","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":"sha256:354db8d659eaf0351b0c20d6a7adfbd0b3612e9cbb47d013284347cbb1635841","target":"record","created_at":"2026-07-05T05:13:02Z","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":"16e9050db52af0bc0378a79f2c96b890b0e6d541b9efd7cdb1048c3b7bb79bed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T17:32:34Z","title_canon_sha256":"e83948eed98087ee0bda851088c8c34f44a88dddf4128effaa3ba717bf85cd2f"},"schema_version":"1.0","source":{"id":"2211.02016","kind":"arxiv","version":1}},"canonical_sha256":"edd778e2f10869eef080a4ebed4ac513b18f926f4af00593c9eaf2db448e48b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd778e2f10869eef080a4ebed4ac513b18f926f4af00593c9eaf2db448e48b1","first_computed_at":"2026-07-05T05:13:02.550306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:02.550306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h8yfxvA2P/ngzaNStp3qalUry0042l7RHk9giuOhPPwtNBMyHzrtLSvLjjv5yJ2jn8GMeYowyKoi2YPXm2xvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:02.550649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:354db8d659eaf0351b0c20d6a7adfbd0b3612e9cbb47d013284347cbb1635841","sha256:a2fecbe32ce140f6a545a69802def36c721f6c994ab406be65248bdf461a0494"],"state_sha256":"22b3ae689a5045cf2190879b19114b44f52f96449412f6fe8d52b69a43080e29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFvj3QZOEJCAtkKr3Q2/Cc3WYEK68dnjzx8WlrSy7gn9yvCgfjAQk7MST6W2wf9RDtGPeyCXOQl8G/1InL5zAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T14:22:30.035825Z","bundle_sha256":"f5323f06b0fc9a2479c708d2faecafc49e0b1d3e28023b970cc05c2014d1d740"}}