{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V4NUPHHG5UCVZ5IY4HLQELL5RB","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":"a6391221e09ab1b7a07f2ad9239a21c68e65b0b51a2afab987adbfa8690b71b1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T02:43:47Z","title_canon_sha256":"116fd77ee67350018f37b993e30a64cc968609c8eb001c0f80f0b5bf5b3c538a"},"schema_version":"1.0","source":{"id":"2310.10021","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10021","created_at":"2026-07-05T07:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10021v2","created_at":"2026-07-05T07:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10021","created_at":"2026-07-05T07:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"V4NUPHHG5UCV","created_at":"2026-07-05T07:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"V4NUPHHG5UCVZ5IY","created_at":"2026-07-05T07:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"V4NUPHHG","created_at":"2026-07-05T07:01:48Z"}],"graph_snapshots":[{"event_id":"sha256:2fc3702aba6c910e084558ecc24a5856bd56b72ad45aa19585a29d7a7d9e626a","target":"graph","created_at":"2026-07-05T07:01:48Z","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/2310.10021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose BOSS, an approach that automatically learns to solve new long-horizon, complex, and meaningful tasks by growing a learned skill library with minimal supervision. Prior work in reinforcement learning require expert supervision, in the form of demonstrations or rich reward functions, to learn long-horizon tasks. Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing \"skill bootstrapping,\" where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outsid","authors_text":"Jesse Zhang, Jiahui Zhang, Joseph J. Lim, Karl Pertsch, Minsuk Chang, Shao-Hua Sun, Xiang Ren, Ziyi Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T02:43:47Z","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10021","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:f54a33182ea56a5cf86f5d4e3b1a9c0e8c3c3775e4911c19b34d4b1534e4f13c","target":"record","created_at":"2026-07-05T07:01:48Z","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":"a6391221e09ab1b7a07f2ad9239a21c68e65b0b51a2afab987adbfa8690b71b1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T02:43:47Z","title_canon_sha256":"116fd77ee67350018f37b993e30a64cc968609c8eb001c0f80f0b5bf5b3c538a"},"schema_version":"1.0","source":{"id":"2310.10021","kind":"arxiv","version":2}},"canonical_sha256":"af1b479ce6ed055cf518e1d7022d7d884bb191cd7aafeaab6facff8e038d440a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af1b479ce6ed055cf518e1d7022d7d884bb191cd7aafeaab6facff8e038d440a","first_computed_at":"2026-07-05T07:01:48.174986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:48.174986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"97Qf2uOx/k3HDwxbYdWlmpJ2NZFiFVSCVJar1lVhjROVOlhJudJZvjt9zELKQGS+hiB6XVIc6pQDX5VLyKOKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:48.175478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10021","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f54a33182ea56a5cf86f5d4e3b1a9c0e8c3c3775e4911c19b34d4b1534e4f13c","sha256:2fc3702aba6c910e084558ecc24a5856bd56b72ad45aa19585a29d7a7d9e626a"],"state_sha256":"b45a66e570cf82191d26fbec265f48a0f6385820cb031450e7637ab9a97825c5"}