{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:L7LHOMQKQSNPPPLL3LCUV3FCKY","short_pith_number":"pith:L7LHOMQK","canonical_record":{"source":{"id":"2106.14421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T06:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"f5dffe8a8ad5f04a26faeafaceb8801f0c4fadf13fa86050983b2b5ceb06ae90","abstract_canon_sha256":"983ecf8896d9600df5f627f50d61d1295e8c79f49b0d46bdbc75d801df838c6d"},"schema_version":"1.0"},"canonical_sha256":"5fd677320a849af7bd6bdac54aeca2560d31a85e463ee40bf82e114d492ba9d4","source":{"kind":"arxiv","id":"2106.14421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14421","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14421v1","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14421","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"L7LHOMQKQSNP","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_16","alias_value":"L7LHOMQKQSNPPPLL","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_8","alias_value":"L7LHOMQK","created_at":"2026-07-05T02:52:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:L7LHOMQKQSNPPPLL3LCUV3FCKY","target":"record","payload":{"canonical_record":{"source":{"id":"2106.14421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T06:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"f5dffe8a8ad5f04a26faeafaceb8801f0c4fadf13fa86050983b2b5ceb06ae90","abstract_canon_sha256":"983ecf8896d9600df5f627f50d61d1295e8c79f49b0d46bdbc75d801df838c6d"},"schema_version":"1.0"},"canonical_sha256":"5fd677320a849af7bd6bdac54aeca2560d31a85e463ee40bf82e114d492ba9d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:50.697868Z","signature_b64":"PPCNF9iWjSYv1OcffAwWqi2PYF/NkCB4mppYGjFYuKnWe4Z5h6J/wFuFkpDGDiNuR65NMJqVTGDQR5+UiU2LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fd677320a849af7bd6bdac54aeca2560d31a85e463ee40bf82e114d492ba9d4","last_reissued_at":"2026-07-05T02:52:50.697397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:50.697397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.14421","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":"2026-07-05T02:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfaY0mSYQY85fz3UHGEi5X35kO5/C4/jpm4906Oh1SkowCoCzcZPwARnkR7yudDcLo6ggeBYYzIJE343oI2kCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T01:04:10.750849Z"},"content_sha256":"a88cff8f7a1f58a30536486ebc50309ab2e56f7d88fca022758f56744532c337","schema_version":"1.0","event_id":"sha256:a88cff8f7a1f58a30536486ebc50309ab2e56f7d88fca022758f56744532c337"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:L7LHOMQKQSNPPPLL3LCUV3FCKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Reinforcement Learning using Observational and Interventional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damien Grasset, Guillaume Gaudron, Maxime Gasse, Pierre-Yves Oudeyer","submitted_at":"2021-06-28T06:58:20Z","abstract_excerpt":"Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct interactions with the environment (interventional data), but has also access to a large collection of offline experiences, obtained by observing another agent interacting with the environment (observational data). A key ingredient, that makes this situation non-trivial, is that we allow the observed agent to interact with the environment based on hidden informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14421","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/2106.14421/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":"2026-07-05T02:52:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWLQmuk4E1/MTt//HNB8G68pThY7SYfG1FowIzA2TclpkRY1RYPfJgzhOVCAv6nAyba9lgE2jUqx3V/Ui2WsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T01:04:10.751209Z"},"content_sha256":"41f4580b9e2a169fe26f88754800427e85e7b42a66d9c61b5aad662644825672","schema_version":"1.0","event_id":"sha256:41f4580b9e2a169fe26f88754800427e85e7b42a66d9c61b5aad662644825672"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/bundle.json","state_url":"https://pith.science/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/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":"2026-07-28T01:04:10Z","links":{"resolver":"https://pith.science/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY","bundle":"https://pith.science/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/bundle.json","state":"https://pith.science/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7LHOMQKQSNPPPLL3LCUV3FCKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L7LHOMQKQSNPPPLL3LCUV3FCKY","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":"983ecf8896d9600df5f627f50d61d1295e8c79f49b0d46bdbc75d801df838c6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T06:58:20Z","title_canon_sha256":"f5dffe8a8ad5f04a26faeafaceb8801f0c4fadf13fa86050983b2b5ceb06ae90"},"schema_version":"1.0","source":{"id":"2106.14421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14421","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14421v1","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14421","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_12","alias_value":"L7LHOMQKQSNP","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_16","alias_value":"L7LHOMQKQSNPPPLL","created_at":"2026-07-05T02:52:50Z"},{"alias_kind":"pith_short_8","alias_value":"L7LHOMQK","created_at":"2026-07-05T02:52:50Z"}],"graph_snapshots":[{"event_id":"sha256:41f4580b9e2a169fe26f88754800427e85e7b42a66d9c61b5aad662644825672","target":"graph","created_at":"2026-07-05T02:52:50Z","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/2106.14421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct interactions with the environment (interventional data), but has also access to a large collection of offline experiences, obtained by observing another agent interacting with the environment (observational data). A key ingredient, that makes this situation non-trivial, is that we allow the observed agent to interact with the environment based on hidden informatio","authors_text":"Damien Grasset, Guillaume Gaudron, Maxime Gasse, Pierre-Yves Oudeyer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T06:58:20Z","title":"Causal Reinforcement Learning using Observational and Interventional Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14421","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:a88cff8f7a1f58a30536486ebc50309ab2e56f7d88fca022758f56744532c337","target":"record","created_at":"2026-07-05T02:52:50Z","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":"983ecf8896d9600df5f627f50d61d1295e8c79f49b0d46bdbc75d801df838c6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T06:58:20Z","title_canon_sha256":"f5dffe8a8ad5f04a26faeafaceb8801f0c4fadf13fa86050983b2b5ceb06ae90"},"schema_version":"1.0","source":{"id":"2106.14421","kind":"arxiv","version":1}},"canonical_sha256":"5fd677320a849af7bd6bdac54aeca2560d31a85e463ee40bf82e114d492ba9d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fd677320a849af7bd6bdac54aeca2560d31a85e463ee40bf82e114d492ba9d4","first_computed_at":"2026-07-05T02:52:50.697397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:50.697397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PPCNF9iWjSYv1OcffAwWqi2PYF/NkCB4mppYGjFYuKnWe4Z5h6J/wFuFkpDGDiNuR65NMJqVTGDQR5+UiU2LCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:50.697868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a88cff8f7a1f58a30536486ebc50309ab2e56f7d88fca022758f56744532c337","sha256:41f4580b9e2a169fe26f88754800427e85e7b42a66d9c61b5aad662644825672"],"state_sha256":"b6014dbc22778e8ed60bba30dcaed9cad54ffbb41e4e08a2939b06f8e51bf268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dU834RfbHzBT7D58zfCtoGcH/O1aI6qS9Au65c2vsgllZTUSY94zV35eqj5rRRTBOqyHo9ybSsV9kOS5NFmDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T01:04:10.753253Z","bundle_sha256":"fc659085dfd015342931f7c0f1e400f71a7277f8e1ff5d50514e600565cd8547"}}