{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4NUPHHG5UCVZ5IY4HLQELL5RB","short_pith_number":"pith:V4NUPHHG","schema_version":"1.0","canonical_sha256":"af1b479ce6ed055cf518e1d7022d7d884bb191cd7aafeaab6facff8e038d440a","source":{"kind":"arxiv","id":"2310.10021","version":2},"attestation_state":"computed","paper":{"title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jesse Zhang, Jiahui Zhang, Joseph J. Lim, Karl Pertsch, Minsuk Chang, Shao-Hua Sun, Xiang Ren, Ziyi Liu","submitted_at":"2023-10-16T02:43:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.10021","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T02:43:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"116fd77ee67350018f37b993e30a64cc968609c8eb001c0f80f0b5bf5b3c538a","abstract_canon_sha256":"a6391221e09ab1b7a07f2ad9239a21c68e65b0b51a2afab987adbfa8690b71b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:48.175478Z","signature_b64":"97Qf2uOx/k3HDwxbYdWlmpJ2NZFiFVSCVJar1lVhjROVOlhJudJZvjt9zELKQGS+hiB6XVIc6pQDX5VLyKOKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1b479ce6ed055cf518e1d7022d7d884bb191cd7aafeaab6facff8e038d440a","last_reissued_at":"2026-07-05T07:01:48.174986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:48.174986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jesse Zhang, Jiahui Zhang, Joseph J. Lim, Karl Pertsch, Minsuk Chang, Shao-Hua Sun, Xiang Ren, Ziyi Liu","submitted_at":"2023-10-16T02:43:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10021","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/2310.10021/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.10021","created_at":"2026-07-05T07:01:48.175043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10021v2","created_at":"2026-07-05T07:01:48.175043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10021","created_at":"2026-07-05T07:01:48.175043+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4NUPHHG5UCV","created_at":"2026-07-05T07:01:48.175043+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4NUPHHG5UCVZ5IY","created_at":"2026-07-05T07:01:48.175043+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4NUPHHG","created_at":"2026-07-05T07:01:48.175043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07999","citing_title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31958","citing_title":"Adapting Generalist Robot Policies with Semantic Reinforcement Learning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":238,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01474","citing_title":"ReMedi: Reasoner for Medical Clinical Prediction","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB","json":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB.json","graph_json":"https://pith.science/api/pith-number/V4NUPHHG5UCVZ5IY4HLQELL5RB/graph.json","events_json":"https://pith.science/api/pith-number/V4NUPHHG5UCVZ5IY4HLQELL5RB/events.json","paper":"https://pith.science/paper/V4NUPHHG"},"agent_actions":{"view_html":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB","download_json":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB.json","view_paper":"https://pith.science/paper/V4NUPHHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10021&json=true","fetch_graph":"https://pith.science/api/pith-number/V4NUPHHG5UCVZ5IY4HLQELL5RB/graph.json","fetch_events":"https://pith.science/api/pith-number/V4NUPHHG5UCVZ5IY4HLQELL5RB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB/action/storage_attestation","attest_author":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB/action/author_attestation","sign_citation":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB/action/citation_signature","submit_replication":"https://pith.science/pith/V4NUPHHG5UCVZ5IY4HLQELL5RB/action/replication_record"}},"created_at":"2026-07-05T07:01:48.175043+00:00","updated_at":"2026-07-05T07:01:48.175043+00:00"}