{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PLLC5AVS5WEDIC5QFA67XG62QU","short_pith_number":"pith:PLLC5AVS","schema_version":"1.0","canonical_sha256":"7ad62e82b2ed88340bb0283dfb9bda852a7e1432f9f585b815961d296a23adf0","source":{"kind":"arxiv","id":"2403.02709","version":1},"attestation_state":"computed","paper":{"title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajinkya Jain, Dorsa Sadigh, Jeannette Bohg, Jiayuan Gu, Karol Hausman, Michael Stark, Peng Xu, Priya Sundaresan, Quan Vuong, Sean Kirmani, Stefan Schaal, Ted Xiao, Tianhe Yu","submitted_at":"2024-03-05T07:00:46Z","abstract_excerpt":"Natural language and images are commonly used as goal representations in goal-conditioned imitation learning (IL). However, natural language can be ambiguous and images can be over-specified. In this work, we propose hand-drawn sketches as a modality for goal specification in visual imitation learning. Sketches are easy for users to provide on the fly like language, but similar to images they can also help a downstream policy to be spatially-aware and even go beyond images to disambiguate task-relevant from task-irrelevant objects. We present RT-Sketch, a goal-conditioned policy for manipulati"},"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":"2403.02709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-05T07:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"b0e2e699004269a41dde253f3c12cbe96fb770354db21ea7d621d9daf9a0a743","abstract_canon_sha256":"bc02c5e8874ed0b8cdb08e7abd43b31b233d879d121e40194d8df2e6d7cb26c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:21.292364Z","signature_b64":"59Ehuy3pI6zIVIKm/ufSaGFwpwl3IuHr6+hfuG8TSAPYLXBBdE0V2X8k6OqEjTaoyjTtXEMKQsLKtJW83137Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad62e82b2ed88340bb0283dfb9bda852a7e1432f9f585b815961d296a23adf0","last_reissued_at":"2026-07-05T07:52:21.291892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:21.291892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ajinkya Jain, Dorsa Sadigh, Jeannette Bohg, Jiayuan Gu, Karol Hausman, Michael Stark, Peng Xu, Priya Sundaresan, Quan Vuong, Sean Kirmani, Stefan Schaal, Ted Xiao, Tianhe Yu","submitted_at":"2024-03-05T07:00:46Z","abstract_excerpt":"Natural language and images are commonly used as goal representations in goal-conditioned imitation learning (IL). However, natural language can be ambiguous and images can be over-specified. In this work, we propose hand-drawn sketches as a modality for goal specification in visual imitation learning. Sketches are easy for users to provide on the fly like language, but similar to images they can also help a downstream policy to be spatially-aware and even go beyond images to disambiguate task-relevant from task-irrelevant objects. We present RT-Sketch, a goal-conditioned policy for manipulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02709","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/2403.02709/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":"2403.02709","created_at":"2026-07-05T07:52:21.291947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02709v1","created_at":"2026-07-05T07:52:21.291947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02709","created_at":"2026-07-05T07:52:21.291947+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLLC5AVS5WED","created_at":"2026-07-05T07:52:21.291947+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLLC5AVS5WEDIC5Q","created_at":"2026-07-05T07:52:21.291947+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLLC5AVS","created_at":"2026-07-05T07:52:21.291947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU","json":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU.json","graph_json":"https://pith.science/api/pith-number/PLLC5AVS5WEDIC5QFA67XG62QU/graph.json","events_json":"https://pith.science/api/pith-number/PLLC5AVS5WEDIC5QFA67XG62QU/events.json","paper":"https://pith.science/paper/PLLC5AVS"},"agent_actions":{"view_html":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU","download_json":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU.json","view_paper":"https://pith.science/paper/PLLC5AVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02709&json=true","fetch_graph":"https://pith.science/api/pith-number/PLLC5AVS5WEDIC5QFA67XG62QU/graph.json","fetch_events":"https://pith.science/api/pith-number/PLLC5AVS5WEDIC5QFA67XG62QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU/action/storage_attestation","attest_author":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU/action/author_attestation","sign_citation":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU/action/citation_signature","submit_replication":"https://pith.science/pith/PLLC5AVS5WEDIC5QFA67XG62QU/action/replication_record"}},"created_at":"2026-07-05T07:52:21.291947+00:00","updated_at":"2026-07-05T07:52:21.291947+00:00"}