{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CTARZXU75B3FHWDURFP7ZODFLE","short_pith_number":"pith:CTARZXU7","schema_version":"1.0","canonical_sha256":"14c11cde9fe87653d874895ffcb8655929d265b7aeee20eb90e7b8059b3113d7","source":{"kind":"arxiv","id":"2409.05865","version":1},"attestation_state":"computed","paper":{"title":"Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaron Edsinger, Chris Paxton, Haritheja Etukuru, Julian Mehu, Lerrel Pinto, Norihito Naka, Nur Muhammad Mahi Shafiullah, Seungjae Lee, Soumith Chintala, Zijin Hu","submitted_at":"2024-09-09T17:59:50Z","abstract_excerpt":"Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given sufficient training data in an environment, robot policies can generalize to demonstrated variations in that environment. However, needing to finetune robot models to every new environment stands in stark contrast to models in language or vision that can be deployed zero-shot for open-world problems. In this work, we present Robot Utility Models (RUMs), a framework for training and deploying"},"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":"2409.05865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-09T17:59:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0a0513ed03f51ecdd7a9972708b18f587c2075ae5d304f315d4068867c82f89","abstract_canon_sha256":"39589b0c1023107e45389178d32e429c4f91e7b6391e52dbc9fae16a804dee76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:55.407420Z","signature_b64":"+C8rBdmPOiH9YgFT2Ema23lVU9HnqrvM37P/TalCLYxH9QeOF53UL90laWSXiJuOhuEnH2H4Y0qJKZskP8RsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c11cde9fe87653d874895ffcb8655929d265b7aeee20eb90e7b8059b3113d7","last_reissued_at":"2026-07-05T09:04:55.406947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:55.406947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaron Edsinger, Chris Paxton, Haritheja Etukuru, Julian Mehu, Lerrel Pinto, Norihito Naka, Nur Muhammad Mahi Shafiullah, Seungjae Lee, Soumith Chintala, Zijin Hu","submitted_at":"2024-09-09T17:59:50Z","abstract_excerpt":"Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given sufficient training data in an environment, robot policies can generalize to demonstrated variations in that environment. However, needing to finetune robot models to every new environment stands in stark contrast to models in language or vision that can be deployed zero-shot for open-world problems. In this work, we present Robot Utility Models (RUMs), a framework for training and deploying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05865","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/2409.05865/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":"2409.05865","created_at":"2026-07-05T09:04:55.407004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05865v1","created_at":"2026-07-05T09:04:55.407004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05865","created_at":"2026-07-05T09:04:55.407004+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTARZXU75B3F","created_at":"2026-07-05T09:04:55.407004+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTARZXU75B3FHWDU","created_at":"2026-07-05T09:04:55.407004+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTARZXU7","created_at":"2026-07-05T09:04:55.407004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06706","citing_title":"Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review","ref_index":153,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07637","citing_title":"Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07637","citing_title":"Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2410.24164","citing_title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE","json":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE.json","graph_json":"https://pith.science/api/pith-number/CTARZXU75B3FHWDURFP7ZODFLE/graph.json","events_json":"https://pith.science/api/pith-number/CTARZXU75B3FHWDURFP7ZODFLE/events.json","paper":"https://pith.science/paper/CTARZXU7"},"agent_actions":{"view_html":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE","download_json":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE.json","view_paper":"https://pith.science/paper/CTARZXU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05865&json=true","fetch_graph":"https://pith.science/api/pith-number/CTARZXU75B3FHWDURFP7ZODFLE/graph.json","fetch_events":"https://pith.science/api/pith-number/CTARZXU75B3FHWDURFP7ZODFLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE/action/storage_attestation","attest_author":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE/action/author_attestation","sign_citation":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE/action/citation_signature","submit_replication":"https://pith.science/pith/CTARZXU75B3FHWDURFP7ZODFLE/action/replication_record"}},"created_at":"2026-07-05T09:04:55.407004+00:00","updated_at":"2026-07-05T09:04:55.407004+00:00"}