{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NUSO4L65BSL7USTP27LBZRLVS6","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":"15a24a65d068b20e3767843c4298625aeb367d935f73e11d0435f38e57f57360","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-10T11:17:58Z","title_canon_sha256":"4620623b9689c314298b176567663fc337d2519a79d85bf23ebb4bf73876270b"},"schema_version":"1.0","source":{"id":"2311.05997","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05997","created_at":"2026-07-05T07:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05997v3","created_at":"2026-07-05T07:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05997","created_at":"2026-07-05T07:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"NUSO4L65BSL7","created_at":"2026-07-05T07:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"NUSO4L65BSL7USTP","created_at":"2026-07-05T07:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"NUSO4L65","created_at":"2026-07-05T07:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:05a31e0503fba5b9ecf4282ec19ca888e629dcd44df194ad7ffc0f970216854a","target":"graph","created_at":"2026-07-05T07:18:31Z","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/2311.05997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all withi","authors_text":"Anji Liu, Bowei Zhang, Haowei Lin, Jinbing Hou, Shaofei Cai, Xiaojian Ma, Yaodong Yang, Yitao Liang, Yonggang Jin, Zhaofeng He, Zihao Wang, Zilong Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-10T11:17:58Z","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05997","kind":"arxiv","version":3},"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":"sha256:36a6ce9ce3a6bc46f9f624cb0a6dae482fcd5b88467c9764fa936ffef09ef67a","target":"record","created_at":"2026-07-05T07:18:31Z","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":"15a24a65d068b20e3767843c4298625aeb367d935f73e11d0435f38e57f57360","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-10T11:17:58Z","title_canon_sha256":"4620623b9689c314298b176567663fc337d2519a79d85bf23ebb4bf73876270b"},"schema_version":"1.0","source":{"id":"2311.05997","kind":"arxiv","version":3}},"canonical_sha256":"6d24ee2fdd0c97fa4a6fd7d61cc575979504d107577cfc0d68773ad5309873fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d24ee2fdd0c97fa4a6fd7d61cc575979504d107577cfc0d68773ad5309873fa","first_computed_at":"2026-07-05T07:18:31.492203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:31.492203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nm1SZAa0O+PaEQEYzeVrHpDkh2donF2sl8h0e5YTK+iuLZu60JTfKbfCxbO6Dx0yk+u4stjHt4noH6V+J+DCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:31.492764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05997","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36a6ce9ce3a6bc46f9f624cb0a6dae482fcd5b88467c9764fa936ffef09ef67a","sha256:05a31e0503fba5b9ecf4282ec19ca888e629dcd44df194ad7ffc0f970216854a"],"state_sha256":"751413d3dbff33de99e1943cb13b9de326a11e4da84e595ef07de3fc6a6e2e05"}