{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3BH4TAKLXTD5DZ3BAJ6HV255M","short_pith_number":"pith:Q3BH4TAK","schema_version":"1.0","canonical_sha256":"86c27e4c0a5de63e8f3b0813e3d75deb16f7375f367b21e56f59a087daa715e9","source":{"kind":"arxiv","id":"2312.07472","version":4},"attestation_state":"computed","paper":{"title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshen Zhou, Jing Shao, Lu Sheng, Qichang Liu, Ruimao Zhang, Yiran Qin, Yu Qiao, Zhenfei Yin","submitted_at":"2023-12-12T17:55:45Z","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."},"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":"2312.07472","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T17:55:45Z","cross_cats_sorted":[],"title_canon_sha256":"3d741dccf0e19464a2352da7b7b75ffe7b1fb452916534b30b0a1d258093ce6d","abstract_canon_sha256":"e63e1ed3e3d46229ca4450487bd44a0a760be8b5803120d713f72a9a5c260c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:00.859494Z","signature_b64":"mkmX7se6IdUz8U0eZ6nI7G91pZ6t7PNFOsve18UYUkN+1ZcO7JgagCaJV9D41soImfd0QtKywt4RzsXdL+z3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c27e4c0a5de63e8f3b0813e3d75deb16f7375f367b21e56f59a087daa715e9","last_reissued_at":"2026-07-05T08:01:00.859031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:00.859031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshen Zhou, Jing Shao, Lu Sheng, Qichang Liu, Ruimao Zhang, Yiran Qin, Yu Qiao, Zhenfei Yin","submitted_at":"2023-12-12T17:55:45Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07472","kind":"arxiv","version":4},"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/2312.07472/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":"2312.07472","created_at":"2026-07-05T08:01:00.859093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07472v4","created_at":"2026-07-05T08:01:00.859093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07472","created_at":"2026-07-05T08:01:00.859093+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3BH4TAKLXTD","created_at":"2026-07-05T08:01:00.859093+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3BH4TAKLXTD5DZ3","created_at":"2026-07-05T08:01:00.859093+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3BH4TAK","created_at":"2026-07-05T08:01:00.859093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00949","citing_title":"STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M","json":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M.json","graph_json":"https://pith.science/api/pith-number/Q3BH4TAKLXTD5DZ3BAJ6HV255M/graph.json","events_json":"https://pith.science/api/pith-number/Q3BH4TAKLXTD5DZ3BAJ6HV255M/events.json","paper":"https://pith.science/paper/Q3BH4TAK"},"agent_actions":{"view_html":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M","download_json":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M.json","view_paper":"https://pith.science/paper/Q3BH4TAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07472&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3BH4TAKLXTD5DZ3BAJ6HV255M/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3BH4TAKLXTD5DZ3BAJ6HV255M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M/action/storage_attestation","attest_author":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M/action/author_attestation","sign_citation":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M/action/citation_signature","submit_replication":"https://pith.science/pith/Q3BH4TAKLXTD5DZ3BAJ6HV255M/action/replication_record"}},"created_at":"2026-07-05T08:01:00.859093+00:00","updated_at":"2026-07-05T08:01:00.859093+00:00"}