{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DMRLIEQTXE25BECUM3ALRDXPQI","short_pith_number":"pith:DMRLIEQT","canonical_record":{"source":{"id":"2303.16563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f65e2cbdaea637b8d5ecf101ea2608af608dd8c9e0689588cd6c29222bb2ed4","abstract_canon_sha256":"994fbafd69a3131701b529afa8c612312f3d7f527ea9edb2d31ee607e3e04346"},"schema_version":"1.0"},"canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","source":{"kind":"arxiv","id":"2303.16563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16563","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16563v2","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16563","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"DMRLIEQTXE25","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"DMRLIEQTXE25BECU","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"DMRLIEQT","created_at":"2026-07-05T07:19:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DMRLIEQTXE25BECUM3ALRDXPQI","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f65e2cbdaea637b8d5ecf101ea2608af608dd8c9e0689588cd6c29222bb2ed4","abstract_canon_sha256":"994fbafd69a3131701b529afa8c612312f3d7f527ea9edb2d31ee607e3e04346"},"schema_version":"1.0"},"canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:44.195803Z","signature_b64":"8CG5e+08CWQFBFqY41g2wErBdNgWH7mqCziWoRxUxy12p0rysoo3PL0jrsgKIxY0h/HSmczXIuAOcdc+qAnEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","last_reissued_at":"2026-07-05T07:19:44.195321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:44.195321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16563","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":"2026-07-05T07:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aaI3WrRFw/pvFUXAVp3if6osYxw3xFZenNFiukAFQj5D1Nx+dx/heJMmGOTfp6313BJIz7q/aYyNkLisUAYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:06:44.971104Z"},"content_sha256":"92bc047d8c006031a6d895bf501e8d5b6890c3a11f35a839b0c49c1be518e4c4","schema_version":"1.0","event_id":"sha256:92bc047d8c006031a6d895bf501e8d5b6890c3a11f35a839b0c49c1be518e4c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DMRLIEQTXE25BECUM3ALRDXPQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Feiyang Xie, Hao Dong, Haoqi Yuan, Hongcheng Wang, Penglin Cai, Zongqing Lu","submitted_at":"2023-03-29T09:45:50Z","abstract_excerpt":"We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16563","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/2303.16563/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":"2026-07-05T07:19:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cioferPxlYYbQBH3zphMh6AXE99h9ND63F5GIVx5RT30ZRJMnLiFzQdEMa0KvcE1Jqt4K8CW4KUXZkl2rAWcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:06:44.972090Z"},"content_sha256":"edea3eb74329de4f4244eb83286611246371b7ffd6826b4e2ad0d389faed462d","schema_version":"1.0","event_id":"sha256:edea3eb74329de4f4244eb83286611246371b7ffd6826b4e2ad0d389faed462d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/bundle.json","state_url":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMRLIEQTXE25BECUM3ALRDXPQI/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":"2026-08-05T22:06:44Z","links":{"resolver":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI","bundle":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/bundle.json","state":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMRLIEQTXE25BECUM3ALRDXPQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DMRLIEQTXE25BECUM3ALRDXPQI","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":"994fbafd69a3131701b529afa8c612312f3d7f527ea9edb2d31ee607e3e04346","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","title_canon_sha256":"8f65e2cbdaea637b8d5ecf101ea2608af608dd8c9e0689588cd6c29222bb2ed4"},"schema_version":"1.0","source":{"id":"2303.16563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16563","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16563v2","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16563","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"DMRLIEQTXE25","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"DMRLIEQTXE25BECU","created_at":"2026-07-05T07:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"DMRLIEQT","created_at":"2026-07-05T07:19:44Z"}],"graph_snapshots":[{"event_id":"sha256:edea3eb74329de4f4244eb83286611246371b7ffd6826b4e2ad0d389faed462d","target":"graph","created_at":"2026-07-05T07:19:44Z","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/2303.16563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides ","authors_text":"Chi Zhang, Feiyang Xie, Hao Dong, Haoqi Yuan, Hongcheng Wang, Penglin Cai, Zongqing Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16563","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":"sha256:92bc047d8c006031a6d895bf501e8d5b6890c3a11f35a839b0c49c1be518e4c4","target":"record","created_at":"2026-07-05T07:19:44Z","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":"994fbafd69a3131701b529afa8c612312f3d7f527ea9edb2d31ee607e3e04346","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","title_canon_sha256":"8f65e2cbdaea637b8d5ecf101ea2608af608dd8c9e0689588cd6c29222bb2ed4"},"schema_version":"1.0","source":{"id":"2303.16563","kind":"arxiv","version":2}},"canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","first_computed_at":"2026-07-05T07:19:44.195321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:44.195321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8CG5e+08CWQFBFqY41g2wErBdNgWH7mqCziWoRxUxy12p0rysoo3PL0jrsgKIxY0h/HSmczXIuAOcdc+qAnEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:44.195803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92bc047d8c006031a6d895bf501e8d5b6890c3a11f35a839b0c49c1be518e4c4","sha256:edea3eb74329de4f4244eb83286611246371b7ffd6826b4e2ad0d389faed462d"],"state_sha256":"87f751145ce7d703bbcbb47b1011035bd5d44498a6c422457da55c436eedfa1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8U/X3bJE4+kSC997r3TruLZou+OTenMVJcTnmss715l+YcSRsAsKSwzntW2uti52t0VaQeB1mzR7TowHtX2kBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:06:44.978356Z","bundle_sha256":"1e381e5d6207ddfb47ea90ee3f47d372d3ace1deb0e321084d2993e041eaceb3"}}