{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QVAOVEJJ25ABCJBWU67XS43YDJ","short_pith_number":"pith:QVAOVEJJ","canonical_record":{"source":{"id":"2112.04907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T09:24:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f1179d58af8feae8170f24e96b14620ef9bcd3035da7ff1e5c79fd7def14ed86","abstract_canon_sha256":"d412145b3c0c065d2327cdc8860401fc680a3d6dac5c1c996a90a1b029f8cb2e"},"schema_version":"1.0"},"canonical_sha256":"8540ea9129d740112436a7bf7973781a4648bca21c93983248d1076efce32200","source":{"kind":"arxiv","id":"2112.04907","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04907","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04907v1","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04907","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"QVAOVEJJ25AB","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"QVAOVEJJ25ABCJBW","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"QVAOVEJJ","created_at":"2026-07-05T03:39:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QVAOVEJJ25ABCJBWU67XS43YDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.04907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T09:24:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f1179d58af8feae8170f24e96b14620ef9bcd3035da7ff1e5c79fd7def14ed86","abstract_canon_sha256":"d412145b3c0c065d2327cdc8860401fc680a3d6dac5c1c996a90a1b029f8cb2e"},"schema_version":"1.0"},"canonical_sha256":"8540ea9129d740112436a7bf7973781a4648bca21c93983248d1076efce32200","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:27.100465Z","signature_b64":"igyjatqSYnaLT1uMKRrckbxfZ0LdcTjhSC7r6BUI4UWmtyFiJvW/NIlzZ27s4A8n6pmRh08VrcIJZlCG5WrNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8540ea9129d740112436a7bf7973781a4648bca21c93983248d1076efce32200","last_reissued_at":"2026-07-05T03:39:27.099747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:27.099747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.04907","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":"2026-07-05T03:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ivUds3Uga/7tV3mDaoQxArqfMDNIUoMxPjIdJAwrY1Oeaa+YRxnIM3eoKFbSodX0ms1JAlSqZTCuDE62eiJ7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:52:03.206697Z"},"content_sha256":"83a15373e3ad5c7c6015197a8279e98cef578e9f8ad3f00dfe935333bdca3457","schema_version":"1.0","event_id":"sha256:83a15373e3ad5c7c6015197a8279e98cef578e9f8ad3f00dfe935333bdca3457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QVAOVEJJ25ABCJBWU67XS43YDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Jianing Shi, Junyou Li, Qiang Fu, Wei Yang, Zichuan Lin","submitted_at":"2021-12-07T09:24:49Z","abstract_excerpt":"Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04907","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/2112.04907/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":"2026-07-05T03:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDShHg+cfnKX4sE+BWiabf9KkstpCXqNgFZ1FLMD5zFVEdjuAv4V8QdzHvrUPlG/I2WQxjLwjpY03ddFF1TpAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:52:03.207495Z"},"content_sha256":"70827f04607836d4b7000ef202a583c65171c23c6c2c0f8213ecd72af86eabbc","schema_version":"1.0","event_id":"sha256:70827f04607836d4b7000ef202a583c65171c23c6c2c0f8213ecd72af86eabbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/bundle.json","state_url":"https://pith.science/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/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":"2026-08-17T20:52:03Z","links":{"resolver":"https://pith.science/pith/QVAOVEJJ25ABCJBWU67XS43YDJ","bundle":"https://pith.science/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/bundle.json","state":"https://pith.science/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVAOVEJJ25ABCJBWU67XS43YDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QVAOVEJJ25ABCJBWU67XS43YDJ","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":"d412145b3c0c065d2327cdc8860401fc680a3d6dac5c1c996a90a1b029f8cb2e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T09:24:49Z","title_canon_sha256":"f1179d58af8feae8170f24e96b14620ef9bcd3035da7ff1e5c79fd7def14ed86"},"schema_version":"1.0","source":{"id":"2112.04907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04907","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04907v1","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04907","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"QVAOVEJJ25AB","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"QVAOVEJJ25ABCJBW","created_at":"2026-07-05T03:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"QVAOVEJJ","created_at":"2026-07-05T03:39:27Z"}],"graph_snapshots":[{"event_id":"sha256:70827f04607836d4b7000ef202a583c65171c23c6c2c0f8213ecd72af86eabbc","target":"graph","created_at":"2026-07-05T03:39:27Z","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/2112.04907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve e","authors_text":"Deheng Ye, Jianing Shi, Junyou Li, Qiang Fu, Wei Yang, Zichuan Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T09:24:49Z","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04907","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":"sha256:83a15373e3ad5c7c6015197a8279e98cef578e9f8ad3f00dfe935333bdca3457","target":"record","created_at":"2026-07-05T03:39:27Z","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":"d412145b3c0c065d2327cdc8860401fc680a3d6dac5c1c996a90a1b029f8cb2e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T09:24:49Z","title_canon_sha256":"f1179d58af8feae8170f24e96b14620ef9bcd3035da7ff1e5c79fd7def14ed86"},"schema_version":"1.0","source":{"id":"2112.04907","kind":"arxiv","version":1}},"canonical_sha256":"8540ea9129d740112436a7bf7973781a4648bca21c93983248d1076efce32200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8540ea9129d740112436a7bf7973781a4648bca21c93983248d1076efce32200","first_computed_at":"2026-07-05T03:39:27.099747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:27.099747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"igyjatqSYnaLT1uMKRrckbxfZ0LdcTjhSC7r6BUI4UWmtyFiJvW/NIlzZ27s4A8n6pmRh08VrcIJZlCG5WrNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:27.100465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83a15373e3ad5c7c6015197a8279e98cef578e9f8ad3f00dfe935333bdca3457","sha256:70827f04607836d4b7000ef202a583c65171c23c6c2c0f8213ecd72af86eabbc"],"state_sha256":"5a0c5d9c165120793049f0c3e1c1efd66887931c8dc00c4b39de33781489f9fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EoXQCzxq4P2pcrKlwwXaR/VAR8idX+fyq/6jkgSyJs3EmSYqRlyVALVw7KRWMIis3hG5qFxhq0BMeP/x+UB3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:52:03.219556Z","bundle_sha256":"74d814fae74ba0fb8a0cf802fc4051c2bc319cdbdf1b82913587b9d3b9b37f44"}}