{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TXBOCHH3ZSHATIR6U56OCBZ24M","short_pith_number":"pith:TXBOCHH3","schema_version":"1.0","canonical_sha256":"9dc2e11cfbcc8e09a23ea77ce1073ae33317824eee07433f06251ce2d20e55e1","source":{"kind":"arxiv","id":"2311.01977","version":2},"attestation_state":"computed","paper":{"title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Chuyuan Fu, Hao Su, Jiayuan Gu, Kanishka Rao, Karol Hausman, Keerthana Gopalakrishnan, Montserrat Gonzalez Arenas, Paul Wohlhart, Peng Xu, Priya Sundaresan, Quan Vuong, Sean Kirmani, Ted Xiao, Wenhao Yu, Yao Lu, Zhuo Xu","submitted_at":"2023-11-03T15:31:51Z","abstract_excerpt":"Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a language-conditioned policy trained on pick-and-place tasks will not be able to generalize to a folding task, even if the arm trajectory of folding is similar to pick-and-place. Our key insight is that this kind of generalization becomes feasible if we represent the task through rough trajectory sketches. "},"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":"2311.01977","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-03T15:31:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"51c5bb83b2cb46ff4bcfed846b47126fd3ed128a2abc89bfb156100d3f6c6802","abstract_canon_sha256":"bc53923459acd2164582fd035aeda5d624ccfb79ae5e609052324bca3c3f18ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:04.566631Z","signature_b64":"VbDNup2CmWFy58soNzy/qwcyLys+5ftTAxp1/c5VLEjNWoq8W8lgCaXubZ3xFrV0x2wql5IRuRisNc7r7xSCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dc2e11cfbcc8e09a23ea77ce1073ae33317824eee07433f06251ce2d20e55e1","last_reissued_at":"2026-07-05T07:09:04.566202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:04.566202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Chuyuan Fu, Hao Su, Jiayuan Gu, Kanishka Rao, Karol Hausman, Keerthana Gopalakrishnan, Montserrat Gonzalez Arenas, Paul Wohlhart, Peng Xu, Priya Sundaresan, Quan Vuong, Sean Kirmani, Ted Xiao, Wenhao Yu, Yao Lu, Zhuo Xu","submitted_at":"2023-11-03T15:31:51Z","abstract_excerpt":"Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a language-conditioned policy trained on pick-and-place tasks will not be able to generalize to a folding task, even if the arm trajectory of folding is similar to pick-and-place. Our key insight is that this kind of generalization becomes feasible if we represent the task through rough trajectory sketches. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01977","kind":"arxiv","version":2},"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/2311.01977/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":"2311.01977","created_at":"2026-07-05T07:09:04.566256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01977v2","created_at":"2026-07-05T07:09:04.566256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01977","created_at":"2026-07-05T07:09:04.566256+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXBOCHH3ZSHA","created_at":"2026-07-05T07:09:04.566256+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXBOCHH3ZSHATIR6","created_at":"2026-07-05T07:09:04.566256+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXBOCHH3","created_at":"2026-07-05T07:09:04.566256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25136","citing_title":"Memory Retrieval in Visuomotor Policies for Long-Horizon Robot Control","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06761","citing_title":"AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31234","citing_title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31958","citing_title":"Adapting Generalist Robot Policies with Semantic Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03480","citing_title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16743","citing_title":"LACE: Latent Visual Representation for Cross-Embodiment Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13998","citing_title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00025","citing_title":"Any-point Trajectory Modeling for Policy Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2510.13778","citing_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22615","citing_title":"GazeVLA: Learning Human Intention for Robotic Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19509","citing_title":"Assessing VLM-Driven Semantic-Affordance Inference for Non-Humanoid Robot Morphologies","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10096","citing_title":"ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09462","citing_title":"Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04811","citing_title":"AnyUser: Translating Sketched User Intent into Domestic Robots","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M","json":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M.json","graph_json":"https://pith.science/api/pith-number/TXBOCHH3ZSHATIR6U56OCBZ24M/graph.json","events_json":"https://pith.science/api/pith-number/TXBOCHH3ZSHATIR6U56OCBZ24M/events.json","paper":"https://pith.science/paper/TXBOCHH3"},"agent_actions":{"view_html":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M","download_json":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M.json","view_paper":"https://pith.science/paper/TXBOCHH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01977&json=true","fetch_graph":"https://pith.science/api/pith-number/TXBOCHH3ZSHATIR6U56OCBZ24M/graph.json","fetch_events":"https://pith.science/api/pith-number/TXBOCHH3ZSHATIR6U56OCBZ24M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M/action/storage_attestation","attest_author":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M/action/author_attestation","sign_citation":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M/action/citation_signature","submit_replication":"https://pith.science/pith/TXBOCHH3ZSHATIR6U56OCBZ24M/action/replication_record"}},"created_at":"2026-07-05T07:09:04.566256+00:00","updated_at":"2026-07-05T07:09:04.566256+00:00"}