{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FTLKW6556QEDS4HPEGVMPSYSKR","short_pith_number":"pith:FTLKW655","schema_version":"1.0","canonical_sha256":"2cd6ab7bbdf4083970ef21aac7cb12547a70085f1f6d07f9bc41309e1c99f96d","source":{"kind":"arxiv","id":"2210.03094","version":2},"attestation_state":"computed","paper":{"title":"VIMA: General Robot Manipulation with Multimodal Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Agrim Gupta, Anima Anandkumar, Guanzhi Wang, Li Fei-Fei, Linxi Fan, Yanjun Chen, Yongqiang Dou, Yuke Zhu, Yunfan Jiang, Zichen Zhang","submitted_at":"2022-10-06T17:50:11Z","abstract_excerpt":"Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we dev"},"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":"2210.03094","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:50:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f17f197904ba41a07f14bf168dd05b2ac0574ebffa98dfef7d81573dd1c39402","abstract_canon_sha256":"5bf6486215a1d4c49e1571a35d6de0ce6b9c9139b5c4077d14cfa071d6f991be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:36.993187Z","signature_b64":"WQoIoNEo5jOciCLRckGPY0oXl2lAEtbuI8ijdFVB4AaUtT4LBKbBytVgoSDZjkdQ/qMlm7KaCFm83pSopQogDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd6ab7bbdf4083970ef21aac7cb12547a70085f1f6d07f9bc41309e1c99f96d","last_reissued_at":"2026-07-05T06:14:36.992695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:36.992695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIMA: General Robot Manipulation with Multimodal Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Agrim Gupta, Anima Anandkumar, Guanzhi Wang, Li Fei-Fei, Linxi Fan, Yanjun Chen, Yongqiang Dou, Yuke Zhu, Yunfan Jiang, Zichen Zhang","submitted_at":"2022-10-06T17:50:11Z","abstract_excerpt":"Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03094","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/2210.03094/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":"2210.03094","created_at":"2026-07-05T06:14:36.992755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03094v2","created_at":"2026-07-05T06:14:36.992755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03094","created_at":"2026-07-05T06:14:36.992755+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTLKW6556QED","created_at":"2026-07-05T06:14:36.992755+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTLKW6556QEDS4HP","created_at":"2026-07-05T06:14:36.992755+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTLKW655","created_at":"2026-07-05T06:14:36.992755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06256","citing_title":"Diagnosing Semantic Handoff Failures in Agent-Orchestrated Vision-Language-Action Skill Composition","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24633","citing_title":"Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":229,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07999","citing_title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06491","citing_title":"TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27759","citing_title":"Colosseum V2: Benchmarking Generalization for Vision Language Action Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29864","citing_title":"LLM-Guided Future Hypotheses for Horizon-Aware Exploration in Multi-Step Robot Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00113","citing_title":"World Models for Robotic Manipulation: A Survey","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28634","citing_title":"PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27251","citing_title":"Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08574","citing_title":"DeepFleet: Multi-Agent Foundation Models for Mobile Robots","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14058","citing_title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11550","citing_title":"Scaling Robot Learning with Semantically Imagined Experience","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR","json":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR.json","graph_json":"https://pith.science/api/pith-number/FTLKW6556QEDS4HPEGVMPSYSKR/graph.json","events_json":"https://pith.science/api/pith-number/FTLKW6556QEDS4HPEGVMPSYSKR/events.json","paper":"https://pith.science/paper/FTLKW655"},"agent_actions":{"view_html":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR","download_json":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR.json","view_paper":"https://pith.science/paper/FTLKW655","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03094&json=true","fetch_graph":"https://pith.science/api/pith-number/FTLKW6556QEDS4HPEGVMPSYSKR/graph.json","fetch_events":"https://pith.science/api/pith-number/FTLKW6556QEDS4HPEGVMPSYSKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR/action/storage_attestation","attest_author":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR/action/author_attestation","sign_citation":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR/action/citation_signature","submit_replication":"https://pith.science/pith/FTLKW6556QEDS4HPEGVMPSYSKR/action/replication_record"}},"created_at":"2026-07-05T06:14:36.992755+00:00","updated_at":"2026-07-05T06:14:36.992755+00:00"}