{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Q6DVXAVLP2F2G6JKEAJ7NUWRK6","short_pith_number":"pith:Q6DVXAVL","canonical_record":{"source":{"id":"2201.11861","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T23:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"3a1959935735edec520c4528c4b03e1643204351b8a9184c5b23fe5c8b138a7c","abstract_canon_sha256":"374747e0e637eb0298fc032025190b205fb3bda4fd5d67d385b60c8f54c123f8"},"schema_version":"1.0"},"canonical_sha256":"87875b82ab7e8ba3792a2013f6d2d157a4d6d7591f46d67716bdceb61486dcd7","source":{"kind":"arxiv","id":"2201.11861","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11861","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11861v2","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11861","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q6DVXAVLP2F2","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q6DVXAVLP2F2G6JK","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q6DVXAVL","created_at":"2026-07-05T03:58:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Q6DVXAVLP2F2G6JKEAJ7NUWRK6","target":"record","payload":{"canonical_record":{"source":{"id":"2201.11861","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T23:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"3a1959935735edec520c4528c4b03e1643204351b8a9184c5b23fe5c8b138a7c","abstract_canon_sha256":"374747e0e637eb0298fc032025190b205fb3bda4fd5d67d385b60c8f54c123f8"},"schema_version":"1.0"},"canonical_sha256":"87875b82ab7e8ba3792a2013f6d2d157a4d6d7591f46d67716bdceb61486dcd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:20.492816Z","signature_b64":"VpHOjZMi9h4g3Z+glP1cwSfz37ncj8BOc9jPddG9hXeWEuPkfnow6Rwu11d01uVIkduN2YcFeUVrJkpHzfHyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87875b82ab7e8ba3792a2013f6d2d157a4d6d7591f46d67716bdceb61486dcd7","last_reissued_at":"2026-07-05T03:58:20.492351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:20.492351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.11861","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uVmQ251Tn96ejjfHZkrJOPwiseM/33lvQx4kf+YAIw3Y+XPQXmEaefVUy9EVRtFZ/8AVICwpSMgAnpaa0oE0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T00:23:52.577754Z"},"content_sha256":"06525251322f6708d2d7ca4829d0a8f3da78f1306ce99dd4bd84d216a0177842","schema_version":"1.0","event_id":"sha256:06525251322f6708d2d7ca4829d0a8f3da78f1306ce99dd4bd84d216a0177842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Q6DVXAVLP2F2G6JKEAJ7NUWRK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Challenges of Exploration for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arunkumar Byravan, Markus Wulfmeier, Martin Riedmiller, Michael Bloesch, Nathan Lambert, Tim Hertweck, Vibhavari Dasagi, William Whitney","submitted_at":"2022-01-27T23:59:56Z","abstract_excerpt":"Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in the offline setting, but just as critical to data-efficient RL is the collection of informative data. The task-agnostic setting for data collection, where the task is not known a priori, is of particular interest due to the possibility of collecting a single dataset and using it to solve several downstream tasks as they arise. We investigate this setting via curio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11861","kind":"arxiv","version":2},"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/2201.11861/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":"2026-07-05T03:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMG3/C2RHOuQrDt6pW7o5yHux84WHaHbFAf+7wpvQEBColxs6ETyhiHtw6MtOuYlsIH+bA6E707q6zHQhtqJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T00:23:52.578120Z"},"content_sha256":"5261c22453424fcca0ecb59acf7c78f15f3905462c448cd8c5f2233014234dc1","schema_version":"1.0","event_id":"sha256:5261c22453424fcca0ecb59acf7c78f15f3905462c448cd8c5f2233014234dc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/bundle.json","state_url":"https://pith.science/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/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":"2026-07-22T00:23:52Z","links":{"resolver":"https://pith.science/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6","bundle":"https://pith.science/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/bundle.json","state":"https://pith.science/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6DVXAVLP2F2G6JKEAJ7NUWRK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Q6DVXAVLP2F2G6JKEAJ7NUWRK6","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":"374747e0e637eb0298fc032025190b205fb3bda4fd5d67d385b60c8f54c123f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T23:59:56Z","title_canon_sha256":"3a1959935735edec520c4528c4b03e1643204351b8a9184c5b23fe5c8b138a7c"},"schema_version":"1.0","source":{"id":"2201.11861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11861","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11861v2","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11861","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q6DVXAVLP2F2","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q6DVXAVLP2F2G6JK","created_at":"2026-07-05T03:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q6DVXAVL","created_at":"2026-07-05T03:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:5261c22453424fcca0ecb59acf7c78f15f3905462c448cd8c5f2233014234dc1","target":"graph","created_at":"2026-07-05T03:58:20Z","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/2201.11861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in the offline setting, but just as critical to data-efficient RL is the collection of informative data. The task-agnostic setting for data collection, where the task is not known a priori, is of particular interest due to the possibility of collecting a single dataset and using it to solve several downstream tasks as they arise. We investigate this setting via curio","authors_text":"Arunkumar Byravan, Markus Wulfmeier, Martin Riedmiller, Michael Bloesch, Nathan Lambert, Tim Hertweck, Vibhavari Dasagi, William Whitney","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T23:59:56Z","title":"The Challenges of Exploration for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11861","kind":"arxiv","version":2},"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":"sha256:06525251322f6708d2d7ca4829d0a8f3da78f1306ce99dd4bd84d216a0177842","target":"record","created_at":"2026-07-05T03:58:20Z","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":"374747e0e637eb0298fc032025190b205fb3bda4fd5d67d385b60c8f54c123f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T23:59:56Z","title_canon_sha256":"3a1959935735edec520c4528c4b03e1643204351b8a9184c5b23fe5c8b138a7c"},"schema_version":"1.0","source":{"id":"2201.11861","kind":"arxiv","version":2}},"canonical_sha256":"87875b82ab7e8ba3792a2013f6d2d157a4d6d7591f46d67716bdceb61486dcd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87875b82ab7e8ba3792a2013f6d2d157a4d6d7591f46d67716bdceb61486dcd7","first_computed_at":"2026-07-05T03:58:20.492351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:20.492351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VpHOjZMi9h4g3Z+glP1cwSfz37ncj8BOc9jPddG9hXeWEuPkfnow6Rwu11d01uVIkduN2YcFeUVrJkpHzfHyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:20.492816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.11861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06525251322f6708d2d7ca4829d0a8f3da78f1306ce99dd4bd84d216a0177842","sha256:5261c22453424fcca0ecb59acf7c78f15f3905462c448cd8c5f2233014234dc1"],"state_sha256":"4fe6a486c82394fcf64cbe6ddda7f2e159719897f47049d9cc2ba8b192daaef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"niOwn9w/dB/n8h4lwr8zuMRVo7O6BZclpuUmcLL2uHVpr3w2SxnBrn0LI/mgTmWMfrhxCrO6M8A0ZCJjretKDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T00:23:52.580206Z","bundle_sha256":"71fe62ea0a8adf9c23fcd6efadf8261ea56ce3fccae77ae69bbdd11e1b551b04"}}