{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q3BH4TAKLXTD5DZ3BAJ6HV255M","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":"e63e1ed3e3d46229ca4450487bd44a0a760be8b5803120d713f72a9a5c260c88","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T17:55:45Z","title_canon_sha256":"3d741dccf0e19464a2352da7b7b75ffe7b1fb452916534b30b0a1d258093ce6d"},"schema_version":"1.0","source":{"id":"2312.07472","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07472","created_at":"2026-07-05T08:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07472v4","created_at":"2026-07-05T08:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07472","created_at":"2026-07-05T08:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q3BH4TAKLXTD","created_at":"2026-07-05T08:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q3BH4TAKLXTD5DZ3","created_at":"2026-07-05T08:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q3BH4TAK","created_at":"2026-07-05T08:01:00Z"}],"graph_snapshots":[{"event_id":"sha256:dd89895ceda73780903db13f33ddf9442828deae6d8dd785d3ae1c83e92b55be","target":"graph","created_at":"2026-07-05T08:01:00Z","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/2312.07472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is a long-lasting goal to design an embodied system that can solve long-horizon open-world tasks in human-like ways. However, existing approaches usually struggle with compound difficulties caused by the logic-aware decomposition and context-aware execution of these tasks. To this end, we introduce MP5, an open-ended multimodal embodied system built upon the challenging Minecraft simulator, which can decompose feasible sub-objectives, design sophisticated situation-aware plans, and perform embodied action control, with frequent communication with a goal-conditioned active perception scheme.","authors_text":"Enshen Zhou, Jing Shao, Lu Sheng, Qichang Liu, Ruimao Zhang, Yiran Qin, Yu Qiao, Zhenfei Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T17:55:45Z","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07472","kind":"arxiv","version":4},"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:e53a7828b8c7c82bdaefeafe75d8333fceeff334cc096a9779360cbe56776cfe","target":"record","created_at":"2026-07-05T08:01:00Z","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":"e63e1ed3e3d46229ca4450487bd44a0a760be8b5803120d713f72a9a5c260c88","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T17:55:45Z","title_canon_sha256":"3d741dccf0e19464a2352da7b7b75ffe7b1fb452916534b30b0a1d258093ce6d"},"schema_version":"1.0","source":{"id":"2312.07472","kind":"arxiv","version":4}},"canonical_sha256":"86c27e4c0a5de63e8f3b0813e3d75deb16f7375f367b21e56f59a087daa715e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86c27e4c0a5de63e8f3b0813e3d75deb16f7375f367b21e56f59a087daa715e9","first_computed_at":"2026-07-05T08:01:00.859031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:00.859031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mkmX7se6IdUz8U0eZ6nI7G91pZ6t7PNFOsve18UYUkN+1ZcO7JgagCaJV9D41soImfd0QtKywt4RzsXdL+z3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:00.859494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07472","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e53a7828b8c7c82bdaefeafe75d8333fceeff334cc096a9779360cbe56776cfe","sha256:dd89895ceda73780903db13f33ddf9442828deae6d8dd785d3ae1c83e92b55be"],"state_sha256":"57b4d6148f0d80e322f4474ce780bcf7c6f58f7ed533def410c7204bbd31a260"}