{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2VRRBXUXETJ4GMJGUJNT2V4NH2","short_pith_number":"pith:2VRRBXUX","schema_version":"1.0","canonical_sha256":"d56310de9724d3c33126a25b3d578d3e958b2632f9e1ced4dd1709f8e467336d","source":{"kind":"arxiv","id":"2312.08958","version":1},"attestation_state":"computed","paper":{"title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jesse Zhang, Joseph J. Lim, Juyong Lee, Karl Pertsch, Sung Ju Hwang, Taewook Nam","submitted_at":"2023-12-14T14:07:41Z","abstract_excerpt":"We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. In our framework, the agent receives task instructions grounded in a training environment from large language models. Then, a vision-language model guides the agent in learning the multi-task language-conditioned policy by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment while prior unsupervised skill discovery methods stru"},"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":"2312.08958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T14:07:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"47decd16266b93e291c66bf8bea3d2f0dd4c8ea4453eb8b1e4c96a45eb56ed81","abstract_canon_sha256":"5a34905eb339bdf61e3cd90674f80ace669da561ba92abb8dc15a22489198803"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:11.775685Z","signature_b64":"a0EENs645AT3FSwf9dM4CTEbDUTXypE4puPPKGxisYrZGTsAk6vbV59Ps16ZdHfWgV5IVX+JGTEhs6fpPBXoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56310de9724d3c33126a25b3d578d3e958b2632f9e1ced4dd1709f8e467336d","last_reissued_at":"2026-07-05T07:24:11.775166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:11.775166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jesse Zhang, Joseph J. Lim, Juyong Lee, Karl Pertsch, Sung Ju Hwang, Taewook Nam","submitted_at":"2023-12-14T14:07:41Z","abstract_excerpt":"We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. In our framework, the agent receives task instructions grounded in a training environment from large language models. Then, a vision-language model guides the agent in learning the multi-task language-conditioned policy by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment while prior unsupervised skill discovery methods stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08958","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/2312.08958/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":"2312.08958","created_at":"2026-07-05T07:24:11.775221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08958v1","created_at":"2026-07-05T07:24:11.775221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08958","created_at":"2026-07-05T07:24:11.775221+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VRRBXUXETJ4","created_at":"2026-07-05T07:24:11.775221+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VRRBXUXETJ4GMJG","created_at":"2026-07-05T07:24:11.775221+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VRRBXUX","created_at":"2026-07-05T07:24:11.775221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.02115","citing_title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2","json":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2.json","graph_json":"https://pith.science/api/pith-number/2VRRBXUXETJ4GMJGUJNT2V4NH2/graph.json","events_json":"https://pith.science/api/pith-number/2VRRBXUXETJ4GMJGUJNT2V4NH2/events.json","paper":"https://pith.science/paper/2VRRBXUX"},"agent_actions":{"view_html":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2","download_json":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2.json","view_paper":"https://pith.science/paper/2VRRBXUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08958&json=true","fetch_graph":"https://pith.science/api/pith-number/2VRRBXUXETJ4GMJGUJNT2V4NH2/graph.json","fetch_events":"https://pith.science/api/pith-number/2VRRBXUXETJ4GMJGUJNT2V4NH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2/action/storage_attestation","attest_author":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2/action/author_attestation","sign_citation":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2/action/citation_signature","submit_replication":"https://pith.science/pith/2VRRBXUXETJ4GMJGUJNT2V4NH2/action/replication_record"}},"created_at":"2026-07-05T07:24:11.775221+00:00","updated_at":"2026-07-05T07:24:11.775221+00:00"}