{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CFBINT54LQ4XKO547MEPRY56FT","short_pith_number":"pith:CFBINT54","schema_version":"1.0","canonical_sha256":"114286cfbc5c39753bbcfb08f8e3be2cf83de9c8048c57a4fec785613b3d08dc","source":{"kind":"arxiv","id":"2411.00508","version":4},"attestation_state":"computed","paper":{"title":"CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Byoung-Tak Zhang, Gi-Cheon Kang, Junghyun Kim, Jun Ki Lee, Kyuhwan Shim","submitted_at":"2024-11-01T10:48:03Z","abstract_excerpt":"Teaching robots desired skills in real-world environments remains challenging, especially for non-experts. A key bottleneck is that collecting robotic data often requires expertise or specialized hardware, limiting accessibility and scalability. We posit that natural language offers an intuitive and accessible interface for robot learning. To this end, we study two aspects: (1) enabling non-experts to collect robotic data through natural language supervision (e.g., \"move the arm to the right\") and (2) training robot policies directly from this supervision. Specifically, we introduce a data col"},"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":"2411.00508","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-01T10:48:03Z","cross_cats_sorted":[],"title_canon_sha256":"7f27385fb0e244c1d75da12cfee3a061099fe649328950855c25eafdc369ebd0","abstract_canon_sha256":"1bcc3759c0033af00e091e4223d307a41f49d23a89a68a026272298f82c03886"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:02.210326Z","signature_b64":"sDzuSwleFzxu3Y2vTpXrFU0sP1xCv8bSWibZU7Tdh5WZMMdf9eSaQwPE/90szPQFuzAkLhkxX2Ddp5L5fIASAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"114286cfbc5c39753bbcfb08f8e3be2cf83de9c8048c57a4fec785613b3d08dc","last_reissued_at":"2026-07-05T11:01:02.209834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:02.209834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Byoung-Tak Zhang, Gi-Cheon Kang, Junghyun Kim, Jun Ki Lee, Kyuhwan Shim","submitted_at":"2024-11-01T10:48:03Z","abstract_excerpt":"Teaching robots desired skills in real-world environments remains challenging, especially for non-experts. A key bottleneck is that collecting robotic data often requires expertise or specialized hardware, limiting accessibility and scalability. We posit that natural language offers an intuitive and accessible interface for robot learning. To this end, we study two aspects: (1) enabling non-experts to collect robotic data through natural language supervision (e.g., \"move the arm to the right\") and (2) training robot policies directly from this supervision. Specifically, we introduce a data col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00508","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/2411.00508/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":"2411.00508","created_at":"2026-07-05T11:01:02.209891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00508v4","created_at":"2026-07-05T11:01:02.209891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00508","created_at":"2026-07-05T11:01:02.209891+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFBINT54LQ4X","created_at":"2026-07-05T11:01:02.209891+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFBINT54LQ4XKO54","created_at":"2026-07-05T11:01:02.209891+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFBINT54","created_at":"2026-07-05T11:01:02.209891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20999","citing_title":"Inductive Generalization for Robotic Manipulation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11751","citing_title":"Grounded World Model for Semantically Generalizable Planning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT","json":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT.json","graph_json":"https://pith.science/api/pith-number/CFBINT54LQ4XKO547MEPRY56FT/graph.json","events_json":"https://pith.science/api/pith-number/CFBINT54LQ4XKO547MEPRY56FT/events.json","paper":"https://pith.science/paper/CFBINT54"},"agent_actions":{"view_html":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT","download_json":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT.json","view_paper":"https://pith.science/paper/CFBINT54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00508&json=true","fetch_graph":"https://pith.science/api/pith-number/CFBINT54LQ4XKO547MEPRY56FT/graph.json","fetch_events":"https://pith.science/api/pith-number/CFBINT54LQ4XKO547MEPRY56FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT/action/storage_attestation","attest_author":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT/action/author_attestation","sign_citation":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT/action/citation_signature","submit_replication":"https://pith.science/pith/CFBINT54LQ4XKO547MEPRY56FT/action/replication_record"}},"created_at":"2026-07-05T11:01:02.209891+00:00","updated_at":"2026-07-05T11:01:02.209891+00:00"}