{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DCGTKG3OMROCQWHVZU4Q4FACCZ","short_pith_number":"pith:DCGTKG3O","schema_version":"1.0","canonical_sha256":"188d351b6e645c2858f5cd390e1402165e4c95eff29ef95c5a9ce334f595e6e9","source":{"kind":"arxiv","id":"2311.02058","version":4},"attestation_state":"computed","paper":{"title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Rutav Shah, Weikang Wan, Yifeng Zhu, Yuke Zhu","submitted_at":"2023-11-03T17:38:35Z","abstract_excerpt":"We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of pr"},"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":"2311.02058","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-03T17:38:35Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b56ca8451d662a3fd7edc11ce596b246e4f19a25f991365923210810fe96d49b","abstract_canon_sha256":"4dda3e4af9bb52a9fb4a3bea3b2c229554ea1cfc4b3309a6b14512d272e9be12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:19.879169Z","signature_b64":"FgfNDsegCexOxyDO8bGkuET5dacSiyxhwLhUHGMOWUkMvLyF1J7kSWZZWI3zmlf6LMre3sOzPzZv784AToouCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"188d351b6e645c2858f5cd390e1402165e4c95eff29ef95c5a9ce334f595e6e9","last_reissued_at":"2026-07-05T09:39:19.878617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:19.878617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Rutav Shah, Weikang Wan, Yifeng Zhu, Yuke Zhu","submitted_at":"2023-11-03T17:38:35Z","abstract_excerpt":"We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02058","kind":"arxiv","version":4},"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/2311.02058/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":"2311.02058","created_at":"2026-07-05T09:39:19.878681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02058v4","created_at":"2026-07-05T09:39:19.878681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02058","created_at":"2026-07-05T09:39:19.878681+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCGTKG3OMROC","created_at":"2026-07-05T09:39:19.878681+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCGTKG3OMROCQWHV","created_at":"2026-07-05T09:39:19.878681+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCGTKG3O","created_at":"2026-07-05T09:39:19.878681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ","json":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ.json","graph_json":"https://pith.science/api/pith-number/DCGTKG3OMROCQWHVZU4Q4FACCZ/graph.json","events_json":"https://pith.science/api/pith-number/DCGTKG3OMROCQWHVZU4Q4FACCZ/events.json","paper":"https://pith.science/paper/DCGTKG3O"},"agent_actions":{"view_html":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ","download_json":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ.json","view_paper":"https://pith.science/paper/DCGTKG3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02058&json=true","fetch_graph":"https://pith.science/api/pith-number/DCGTKG3OMROCQWHVZU4Q4FACCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DCGTKG3OMROCQWHVZU4Q4FACCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ/action/storage_attestation","attest_author":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ/action/author_attestation","sign_citation":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ/action/citation_signature","submit_replication":"https://pith.science/pith/DCGTKG3OMROCQWHVZU4Q4FACCZ/action/replication_record"}},"created_at":"2026-07-05T09:39:19.878681+00:00","updated_at":"2026-07-05T09:39:19.878681+00:00"}