{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QRSMJ2MROXNV7H4MXLFV3GVEIW","short_pith_number":"pith:QRSMJ2MR","canonical_record":{"source":{"id":"2211.14827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-27T13:37:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"19f462e72881c3f83dbf42c2c68bb5e27ce23136ec88a4481f8ec78f3bc49cf9","abstract_canon_sha256":"1fc29745fe056720830d74f22dcc9d0bddd0ef7bff4c04abb34579585167abc5"},"schema_version":"1.0"},"canonical_sha256":"8464c4e99175db5f9f8cbacb5d9aa445a1ed764f8f8f0fbde3ab21d980d14945","source":{"kind":"arxiv","id":"2211.14827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14827","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14827v1","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14827","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"QRSMJ2MROXNV","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"QRSMJ2MROXNV7H4M","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"QRSMJ2MR","created_at":"2026-07-05T05:19:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QRSMJ2MROXNV7H4MXLFV3GVEIW","target":"record","payload":{"canonical_record":{"source":{"id":"2211.14827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-27T13:37:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"19f462e72881c3f83dbf42c2c68bb5e27ce23136ec88a4481f8ec78f3bc49cf9","abstract_canon_sha256":"1fc29745fe056720830d74f22dcc9d0bddd0ef7bff4c04abb34579585167abc5"},"schema_version":"1.0"},"canonical_sha256":"8464c4e99175db5f9f8cbacb5d9aa445a1ed764f8f8f0fbde3ab21d980d14945","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:44.298257Z","signature_b64":"R3gmCmjIOYfxMa2Saz5o0tV4zikdS49mmvtd2Z953EmF4/SWFXQfFtjNPq1uQldAUVWGRXHFjkTBaAL/ZPB8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8464c4e99175db5f9f8cbacb5d9aa445a1ed764f8f8f0fbde3ab21d980d14945","last_reissued_at":"2026-07-05T05:19:44.297856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:44.297856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.14827","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":"2026-07-05T05:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5dKLEucD5yVYNY5SigTCZrlbKiYdLF6LHy6MWty4Tp8msUJKLHHUyP9XRPK3A5IuBKDGIfVEN7Mxk09xifoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:07:58.598988Z"},"content_sha256":"fe0b6841c4a29860b4433f7b0d78e26e4076894c93a4b4ba10e10e0e815058c6","schema_version":"1.0","event_id":"sha256:fe0b6841c4a29860b4433f7b0d78e26e4076894c93a4b4ba10e10e0e815058c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QRSMJ2MROXNV7H4MXLFV3GVEIW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain Generalization for Robust Model-Based 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":"Alan Clark, David Krueger, Robert Kirk, Shoaib Ahmed Siddiqui, Stephen Chung, Usman Anwar","submitted_at":"2022-11-27T13:37:49Z","abstract_excerpt":"Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we know which demonstrators generated each dataset, but make no assumptions about the underlying policies of the demonstrators. This is the most natural setting when collecting data from multiple human operators, yet remains unexplored. Since different demonstrators induce different data distributions, we show that this can be naturally framed as a domain generali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14827","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/2211.14827/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":"2026-07-05T05:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HquFAMU5MgnB77YwNTN8Rts+n52/eIcP6swqMN3rE2dmF8RipO7qJuP7wthM6NBlrJgvTpVXtfUfS8HeMUlzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:07:58.599506Z"},"content_sha256":"009fdd5035132ff20c4d5a7d7d1902071ce12be48457df7ce6e0c5f815eda3e2","schema_version":"1.0","event_id":"sha256:009fdd5035132ff20c4d5a7d7d1902071ce12be48457df7ce6e0c5f815eda3e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/bundle.json","state_url":"https://pith.science/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/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":"2026-08-12T21:07:58Z","links":{"resolver":"https://pith.science/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW","bundle":"https://pith.science/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/bundle.json","state":"https://pith.science/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRSMJ2MROXNV7H4MXLFV3GVEIW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QRSMJ2MROXNV7H4MXLFV3GVEIW","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":"1fc29745fe056720830d74f22dcc9d0bddd0ef7bff4c04abb34579585167abc5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-27T13:37:49Z","title_canon_sha256":"19f462e72881c3f83dbf42c2c68bb5e27ce23136ec88a4481f8ec78f3bc49cf9"},"schema_version":"1.0","source":{"id":"2211.14827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14827","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14827v1","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14827","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"QRSMJ2MROXNV","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"QRSMJ2MROXNV7H4M","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"QRSMJ2MR","created_at":"2026-07-05T05:19:44Z"}],"graph_snapshots":[{"event_id":"sha256:009fdd5035132ff20c4d5a7d7d1902071ce12be48457df7ce6e0c5f815eda3e2","target":"graph","created_at":"2026-07-05T05:19:44Z","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/2211.14827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we know which demonstrators generated each dataset, but make no assumptions about the underlying policies of the demonstrators. This is the most natural setting when collecting data from multiple human operators, yet remains unexplored. Since different demonstrators induce different data distributions, we show that this can be naturally framed as a domain generali","authors_text":"Alan Clark, David Krueger, Robert Kirk, Shoaib Ahmed Siddiqui, Stephen Chung, Usman Anwar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-27T13:37:49Z","title":"Domain Generalization for Robust Model-Based Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14827","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:fe0b6841c4a29860b4433f7b0d78e26e4076894c93a4b4ba10e10e0e815058c6","target":"record","created_at":"2026-07-05T05:19:44Z","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":"1fc29745fe056720830d74f22dcc9d0bddd0ef7bff4c04abb34579585167abc5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-27T13:37:49Z","title_canon_sha256":"19f462e72881c3f83dbf42c2c68bb5e27ce23136ec88a4481f8ec78f3bc49cf9"},"schema_version":"1.0","source":{"id":"2211.14827","kind":"arxiv","version":1}},"canonical_sha256":"8464c4e99175db5f9f8cbacb5d9aa445a1ed764f8f8f0fbde3ab21d980d14945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8464c4e99175db5f9f8cbacb5d9aa445a1ed764f8f8f0fbde3ab21d980d14945","first_computed_at":"2026-07-05T05:19:44.297856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:44.297856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3gmCmjIOYfxMa2Saz5o0tV4zikdS49mmvtd2Z953EmF4/SWFXQfFtjNPq1uQldAUVWGRXHFjkTBaAL/ZPB8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:44.298257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.14827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe0b6841c4a29860b4433f7b0d78e26e4076894c93a4b4ba10e10e0e815058c6","sha256:009fdd5035132ff20c4d5a7d7d1902071ce12be48457df7ce6e0c5f815eda3e2"],"state_sha256":"e5a532009fc01a21d6e491914fea5428ee0b6e486f3ee162e7657e962bf40043"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4XzgxA4KGo127+iZ9olZIJ2tGypRUhFoPIH3RXlB4cYRXK5ondDVeABtYh1NNriPaHaHPJECfau0kihcnEfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:07:58.603718Z","bundle_sha256":"40416ad94040e60ef9b3738b08ca3162be697a2088ddbe8eaa9e4c49180a607c"}}