{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZK7QOUIWVUMCWAIW5MJGBIM7TQ","short_pith_number":"pith:ZK7QOUIW","canonical_record":{"source":{"id":"2110.14020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T20:50:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed22ca5e47f6fc55a16b702f61118ef3493f8694c5338cac3bde8832b41518ed","abstract_canon_sha256":"cc3a77daeeb4c91464641ef211b05db6303ab4dfcde6789df3c2ef04b40484f4"},"schema_version":"1.0"},"canonical_sha256":"cabf075116ad182b0116eb1260a19f9c2b16b1b7b699d59b60a256f9abf529f7","source":{"kind":"arxiv","id":"2110.14020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14020","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14020v1","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14020","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZK7QOUIWVUMC","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZK7QOUIWVUMCWAIW","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZK7QOUIW","created_at":"2026-07-05T03:26:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZK7QOUIWVUMCWAIW5MJGBIM7TQ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T20:50:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed22ca5e47f6fc55a16b702f61118ef3493f8694c5338cac3bde8832b41518ed","abstract_canon_sha256":"cc3a77daeeb4c91464641ef211b05db6303ab4dfcde6789df3c2ef04b40484f4"},"schema_version":"1.0"},"canonical_sha256":"cabf075116ad182b0116eb1260a19f9c2b16b1b7b699d59b60a256f9abf529f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:22.928364Z","signature_b64":"RRgOKSuaIoWp4ZizYwrj5BY/usv6BBaMlkcCbVdqAhgLF09d/Y4w+JvKMuZ5Jbm4lvTjFr550QB33Kxuf3x3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabf075116ad182b0116eb1260a19f9c2b16b1b7b699d59b60a256f9abf529f7","last_reissued_at":"2026-07-05T03:26:22.927932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:22.927932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14020","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":"2026-07-05T03:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uVIU4DWTg9VYVLoEEtHPzNEn+Jh7b0AqQYgWeAC5u0s08AfdJn2aTGbKZFRPJwDZEDsLsgP4/IB0e1749LpEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:25:39.082191Z"},"content_sha256":"a4ccceca2a93ee5951ed8b95f5a29562b603814f62d5a7d2c45c884fc9763562","schema_version":"1.0","event_id":"sha256:a4ccceca2a93ee5951ed8b95f5a29562b603814f62d5a7d2c45c884fc9763562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZK7QOUIWVUMCWAIW5MJGBIM7TQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Georg Ostrovski, Pablo Samuel Castro, Will Dabney","submitted_at":"2021-10-26T20:50:49Z","abstract_excerpt":"Learning to act from observational data without active environmental interaction is a well-known challenge in Reinforcement Learning (RL). Recent approaches involve constraints on the learned policy or conservative updates, preventing strong deviations from the state-action distribution of the dataset. Although these methods are evaluated using non-linear function approximation, theoretical justifications are mostly limited to the tabular or linear cases. Given the impressive results of deep reinforcement learning, we argue for a need to more clearly understand the challenges in this setting.\n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14020","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/2110.14020/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":"2026-07-05T03:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrCCFOfzTlYjuGmxHPvS9OMoWpNTSZ5WRziK8BLTrtjajeo7VhpuKZi8tqk0KwfSFJuHeicj6xQKpaFoxxdZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:25:39.083267Z"},"content_sha256":"70926cb67b236ad6f19c6795710237798c544bb534a4826298d4b11e56a6696b","schema_version":"1.0","event_id":"sha256:70926cb67b236ad6f19c6795710237798c544bb534a4826298d4b11e56a6696b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/bundle.json","state_url":"https://pith.science/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/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":"2026-08-12T17:25:39Z","links":{"resolver":"https://pith.science/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ","bundle":"https://pith.science/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/bundle.json","state":"https://pith.science/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK7QOUIWVUMCWAIW5MJGBIM7TQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZK7QOUIWVUMCWAIW5MJGBIM7TQ","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":"cc3a77daeeb4c91464641ef211b05db6303ab4dfcde6789df3c2ef04b40484f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T20:50:49Z","title_canon_sha256":"ed22ca5e47f6fc55a16b702f61118ef3493f8694c5338cac3bde8832b41518ed"},"schema_version":"1.0","source":{"id":"2110.14020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14020","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14020v1","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14020","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZK7QOUIWVUMC","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZK7QOUIWVUMCWAIW","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZK7QOUIW","created_at":"2026-07-05T03:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:70926cb67b236ad6f19c6795710237798c544bb534a4826298d4b11e56a6696b","target":"graph","created_at":"2026-07-05T03:26:22Z","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/2110.14020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to act from observational data without active environmental interaction is a well-known challenge in Reinforcement Learning (RL). Recent approaches involve constraints on the learned policy or conservative updates, preventing strong deviations from the state-action distribution of the dataset. Although these methods are evaluated using non-linear function approximation, theoretical justifications are mostly limited to the tabular or linear cases. Given the impressive results of deep reinforcement learning, we argue for a need to more clearly understand the challenges in this setting.\n","authors_text":"Georg Ostrovski, Pablo Samuel Castro, Will Dabney","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T20:50:49Z","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14020","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:a4ccceca2a93ee5951ed8b95f5a29562b603814f62d5a7d2c45c884fc9763562","target":"record","created_at":"2026-07-05T03:26:22Z","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":"cc3a77daeeb4c91464641ef211b05db6303ab4dfcde6789df3c2ef04b40484f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T20:50:49Z","title_canon_sha256":"ed22ca5e47f6fc55a16b702f61118ef3493f8694c5338cac3bde8832b41518ed"},"schema_version":"1.0","source":{"id":"2110.14020","kind":"arxiv","version":1}},"canonical_sha256":"cabf075116ad182b0116eb1260a19f9c2b16b1b7b699d59b60a256f9abf529f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabf075116ad182b0116eb1260a19f9c2b16b1b7b699d59b60a256f9abf529f7","first_computed_at":"2026-07-05T03:26:22.927932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:22.927932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RRgOKSuaIoWp4ZizYwrj5BY/usv6BBaMlkcCbVdqAhgLF09d/Y4w+JvKMuZ5Jbm4lvTjFr550QB33Kxuf3x3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:22.928364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4ccceca2a93ee5951ed8b95f5a29562b603814f62d5a7d2c45c884fc9763562","sha256:70926cb67b236ad6f19c6795710237798c544bb534a4826298d4b11e56a6696b"],"state_sha256":"424bcadeedf34399e8e024f09bc0b73ea204bb0efe71026bc3de28c1998703f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHoJlJVmgRfbTXLeWt/vVExSqEyOURjopxDr6biy5Wgf/0zTlVEnMslgaNHnT+fRsix9++gBFCeZHuShu4LmAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T17:25:39.092665Z","bundle_sha256":"ac7304d0e5e5fac8a583f94293a613c4939c8e761be41904427a283e62cf85a0"}}