{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FTLKW6556QEDS4HPEGVMPSYSKR","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":"5bf6486215a1d4c49e1571a35d6de0ce6b9c9139b5c4077d14cfa071d6f991be","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:50:11Z","title_canon_sha256":"f17f197904ba41a07f14bf168dd05b2ac0574ebffa98dfef7d81573dd1c39402"},"schema_version":"1.0","source":{"id":"2210.03094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03094","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03094v2","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03094","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"FTLKW6556QED","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"FTLKW6556QEDS4HP","created_at":"2026-07-05T06:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"FTLKW655","created_at":"2026-07-05T06:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:191f7c05d7c4cf3cf024e7e927ed30592d73c2107d9e102c678bb925865bfdbd","target":"graph","created_at":"2026-07-05T06:14:36Z","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/2210.03094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Agrim Gupta, Anima Anandkumar, Guanzhi Wang, Li Fei-Fei, Linxi Fan, Yanjun Chen, Yongqiang Dou, Yuke Zhu, Yunfan Jiang, Zichen Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:50:11Z","title":"VIMA: General Robot Manipulation with Multimodal Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03094","kind":"arxiv","version":2},"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":"sha256:4e596f366eeb8a867630d36d4aadb4f3ec1ccd48bb7e83c7917b6b886bc8b01f","target":"record","created_at":"2026-07-05T06:14:36Z","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":"5bf6486215a1d4c49e1571a35d6de0ce6b9c9139b5c4077d14cfa071d6f991be","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-06T17:50:11Z","title_canon_sha256":"f17f197904ba41a07f14bf168dd05b2ac0574ebffa98dfef7d81573dd1c39402"},"schema_version":"1.0","source":{"id":"2210.03094","kind":"arxiv","version":2}},"canonical_sha256":"2cd6ab7bbdf4083970ef21aac7cb12547a70085f1f6d07f9bc41309e1c99f96d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cd6ab7bbdf4083970ef21aac7cb12547a70085f1f6d07f9bc41309e1c99f96d","first_computed_at":"2026-07-05T06:14:36.992695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:36.992695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WQoIoNEo5jOciCLRckGPY0oXl2lAEtbuI8ijdFVB4AaUtT4LBKbBytVgoSDZjkdQ/qMlm7KaCFm83pSopQogDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:36.993187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e596f366eeb8a867630d36d4aadb4f3ec1ccd48bb7e83c7917b6b886bc8b01f","sha256:191f7c05d7c4cf3cf024e7e927ed30592d73c2107d9e102c678bb925865bfdbd"],"state_sha256":"1e4ac2696ebc407cad53c69150529fe199b0103415360b1cfb10cf7a70512612"}