{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PLLC5AVS5WEDIC5QFA67XG62QU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bc02c5e8874ed0b8cdb08e7abd43b31b233d879d121e40194d8df2e6d7cb26c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-05T07:00:46Z","title_canon_sha256":"b0e2e699004269a41dde253f3c12cbe96fb770354db21ea7d621d9daf9a0a743"},"schema_version":"1.0","source":{"id":"2403.02709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02709","created_at":"2026-07-05T07:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02709v1","created_at":"2026-07-05T07:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02709","created_at":"2026-07-05T07:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"PLLC5AVS5WED","created_at":"2026-07-05T07:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"PLLC5AVS5WEDIC5Q","created_at":"2026-07-05T07:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"PLLC5AVS","created_at":"2026-07-05T07:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:98e84151a8ba313ed9c4c18e6bd3cb0befb59bd111f5fd467bf26785df6e9f89","target":"graph","created_at":"2026-07-05T07:52:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.02709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-05T07:00:46Z","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02709","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36c1b0a45b7e80a4b2570056ff5a2e01cb8e5f9d5444c0494e8d86753bcf0835","target":"record","created_at":"2026-07-05T07:52:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bc02c5e8874ed0b8cdb08e7abd43b31b233d879d121e40194d8df2e6d7cb26c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-05T07:00:46Z","title_canon_sha256":"b0e2e699004269a41dde253f3c12cbe96fb770354db21ea7d621d9daf9a0a743"},"schema_version":"1.0","source":{"id":"2403.02709","kind":"arxiv","version":1}},"canonical_sha256":"7ad62e82b2ed88340bb0283dfb9bda852a7e1432f9f585b815961d296a23adf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ad62e82b2ed88340bb0283dfb9bda852a7e1432f9f585b815961d296a23adf0","first_computed_at":"2026-07-05T07:52:21.291892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:21.291892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"59Ehuy3pI6zIVIKm/ufSaGFwpwl3IuHr6+hfuG8TSAPYLXBBdE0V2X8k6OqEjTaoyjTtXEMKQsLKtJW83137Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:21.292364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36c1b0a45b7e80a4b2570056ff5a2e01cb8e5f9d5444c0494e8d86753bcf0835","sha256:98e84151a8ba313ed9c4c18e6bd3cb0befb59bd111f5fd467bf26785df6e9f89"],"state_sha256":"262be7b39fc2c5bbd998a1305574a547e99799b9321c64cdbc3f4b42380bdbae"}