{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EIKKKWLHVJESAH2VXMV7X64LUY","short_pith_number":"pith:EIKKKWLH","canonical_record":{"source":{"id":"2207.07560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T16:06:33Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"64a63dd380e3cff3040507c286f22edbe76df4217bc630292417e08655d590a0","abstract_canon_sha256":"fb3162dd6aecb8a6f934957aa425109df58ea458c24bc463cc44473b1abc7e42"},"schema_version":"1.0"},"canonical_sha256":"2214a55967aa49201f55bb2bfbfb8ba6245ad77451132f1b867d69c4257e94c7","source":{"kind":"arxiv","id":"2207.07560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07560","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07560v2","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07560","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"EIKKKWLHVJES","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"EIKKKWLHVJESAH2V","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"EIKKKWLH","created_at":"2026-07-05T05:24:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EIKKKWLHVJESAH2VXMV7X64LUY","target":"record","payload":{"canonical_record":{"source":{"id":"2207.07560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T16:06:33Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"64a63dd380e3cff3040507c286f22edbe76df4217bc630292417e08655d590a0","abstract_canon_sha256":"fb3162dd6aecb8a6f934957aa425109df58ea458c24bc463cc44473b1abc7e42"},"schema_version":"1.0"},"canonical_sha256":"2214a55967aa49201f55bb2bfbfb8ba6245ad77451132f1b867d69c4257e94c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:12.829949Z","signature_b64":"b8DbFHjEjSznCtM7DgUxBwWeEJINB+Ose0NPpoQNgVPLleu+4+iOh6g9r6VFw0nZ5oxNWcfCDSbFZXVrDCk2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2214a55967aa49201f55bb2bfbfb8ba6245ad77451132f1b867d69c4257e94c7","last_reissued_at":"2026-07-05T05:24:12.829507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:12.829507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.07560","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":"2026-07-05T05:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uW6ojKzEz6a7SZ5+usP0n3QdZA6YZn9EKEnZe8C46m9cnnFMg8mL9ONHS/tm3Zr6hN36CWLgnN1UVK8G0aQYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:41:11.878606Z"},"content_sha256":"19bc5cd613e6f938e226c0f1e6b14ba49c7f9a06bd7f697239fc39b0e8e5510c","schema_version":"1.0","event_id":"sha256:19bc5cd613e6f938e226c0f1e6b14ba49c7f9a06bd7f697239fc39b0e8e5510c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EIKKKWLHVJESAH2VXMV7X64LUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill-based Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Lucy Xiaoyang Shi, Youngwoon Lee","submitted_at":"2022-07-15T16:06:33Z","abstract_excerpt":"Model-based reinforcement learning (RL) is a sample-efficient way of learning complex behaviors by leveraging a learned single-step dynamics model to plan actions in imagination. However, planning every action for long-horizon tasks is not practical, akin to a human planning out every muscle movement. Instead, humans efficiently plan with high-level skills to solve complex tasks. From this intuition, we propose a Skill-based Model-based RL framework (SkiMo) that enables planning in the skill space using a skill dynamics model, which directly predicts the skill outcomes, rather than predicting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07560","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/2207.07560/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":"2026-07-05T05:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOsM1qK6xMy0vo/lIZOiz42nW/PCG84ttao/g1wBTx7Wylq+Vw1vhOqXeV0RCjOpQThK14tG5vHXYSL6YEpWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:41:11.879583Z"},"content_sha256":"ba781ec31a612acfd2a15d15eb14aded4b012a4467af983507f6c377b6439a89","schema_version":"1.0","event_id":"sha256:ba781ec31a612acfd2a15d15eb14aded4b012a4467af983507f6c377b6439a89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIKKKWLHVJESAH2VXMV7X64LUY/bundle.json","state_url":"https://pith.science/pith/EIKKKWLHVJESAH2VXMV7X64LUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIKKKWLHVJESAH2VXMV7X64LUY/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":"2026-08-14T17:41:11Z","links":{"resolver":"https://pith.science/pith/EIKKKWLHVJESAH2VXMV7X64LUY","bundle":"https://pith.science/pith/EIKKKWLHVJESAH2VXMV7X64LUY/bundle.json","state":"https://pith.science/pith/EIKKKWLHVJESAH2VXMV7X64LUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIKKKWLHVJESAH2VXMV7X64LUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EIKKKWLHVJESAH2VXMV7X64LUY","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":"fb3162dd6aecb8a6f934957aa425109df58ea458c24bc463cc44473b1abc7e42","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T16:06:33Z","title_canon_sha256":"64a63dd380e3cff3040507c286f22edbe76df4217bc630292417e08655d590a0"},"schema_version":"1.0","source":{"id":"2207.07560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07560","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07560v2","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07560","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"EIKKKWLHVJES","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"EIKKKWLHVJESAH2V","created_at":"2026-07-05T05:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"EIKKKWLH","created_at":"2026-07-05T05:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:ba781ec31a612acfd2a15d15eb14aded4b012a4467af983507f6c377b6439a89","target":"graph","created_at":"2026-07-05T05:24:12Z","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/2207.07560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL) is a sample-efficient way of learning complex behaviors by leveraging a learned single-step dynamics model to plan actions in imagination. However, planning every action for long-horizon tasks is not practical, akin to a human planning out every muscle movement. Instead, humans efficiently plan with high-level skills to solve complex tasks. From this intuition, we propose a Skill-based Model-based RL framework (SkiMo) that enables planning in the skill space using a skill dynamics model, which directly predicts the skill outcomes, rather than predicting ","authors_text":"Joseph J. Lim, Lucy Xiaoyang Shi, Youngwoon Lee","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T16:06:33Z","title":"Skill-based Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07560","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":"sha256:19bc5cd613e6f938e226c0f1e6b14ba49c7f9a06bd7f697239fc39b0e8e5510c","target":"record","created_at":"2026-07-05T05:24:12Z","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":"fb3162dd6aecb8a6f934957aa425109df58ea458c24bc463cc44473b1abc7e42","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T16:06:33Z","title_canon_sha256":"64a63dd380e3cff3040507c286f22edbe76df4217bc630292417e08655d590a0"},"schema_version":"1.0","source":{"id":"2207.07560","kind":"arxiv","version":2}},"canonical_sha256":"2214a55967aa49201f55bb2bfbfb8ba6245ad77451132f1b867d69c4257e94c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2214a55967aa49201f55bb2bfbfb8ba6245ad77451132f1b867d69c4257e94c7","first_computed_at":"2026-07-05T05:24:12.829507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:12.829507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8DbFHjEjSznCtM7DgUxBwWeEJINB+Ose0NPpoQNgVPLleu+4+iOh6g9r6VFw0nZ5oxNWcfCDSbFZXVrDCk2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:12.829949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19bc5cd613e6f938e226c0f1e6b14ba49c7f9a06bd7f697239fc39b0e8e5510c","sha256:ba781ec31a612acfd2a15d15eb14aded4b012a4467af983507f6c377b6439a89"],"state_sha256":"bd9c0b87098c45a4959fdf0cb7c9792d67f80ade94e61484a555cf7cc5fa1d20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVVL0m4xTMmNgyzrV6ej6I0UElNeYNKX052VJkqIupXCNSmobrSIWWQRhG59xUNtA9D0zzfIjvp5Hxx7maYCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:41:11.885485Z","bundle_sha256":"e1c1903b2dd4f2209ab7d790df4ebb8402aac4f4343a21b47b9e2dd16cf3ac7b"}}