{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZZ3QUFOPK4SPPMZM4WQE5CZWZ","short_pith_number":"pith:IZZ3QUFO","schema_version":"1.0","canonical_sha256":"4673b850ae7ab927bd99672d027459b65205bacaf9df140b85a77fd80ad226ce","source":{"kind":"arxiv","id":"2403.12037","version":2},"attestation_state":"computed","paper":{"title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshen Zhou, Jing Shao, Lu Sheng, Ruimao Zhang, Yiran Qin, Yu Qiao, Yuzhou Huang, Zhenfei Yin","submitted_at":"2024-03-18T17:59:42Z","abstract_excerpt":"It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Lan"},"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":"2403.12037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"3ade6026ae4464c0ac50c4176cd87b2f7c783c8f7041dab767361c049b9eeb4a","abstract_canon_sha256":"2d9dfd6c171c038dba8f52538318c17bc61fec7854cf8283bd28b462b57a57ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:54.044694Z","signature_b64":"yLWzLi5E04yoPqcZ/5W1Y+lGPMJbx02OB8xtabENigAEnx3Pywn/36/vyZhuhdTIx3UdwHICznxTUjGyVLaRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4673b850ae7ab927bd99672d027459b65205bacaf9df140b85a77fd80ad226ce","last_reissued_at":"2026-07-05T07:57:54.044098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:54.044098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enshen Zhou, Jing Shao, Lu Sheng, Ruimao Zhang, Yiran Qin, Yu Qiao, Yuzhou Huang, Zhenfei Yin","submitted_at":"2024-03-18T17:59:42Z","abstract_excerpt":"It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12037","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/2403.12037/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":"2403.12037","created_at":"2026-07-05T07:57:54.044201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12037v2","created_at":"2026-07-05T07:57:54.044201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12037","created_at":"2026-07-05T07:57:54.044201+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZZ3QUFOPK4S","created_at":"2026-07-05T07:57:54.044201+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZZ3QUFOPK4SPPMZ","created_at":"2026-07-05T07:57:54.044201+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZZ3QUFO","created_at":"2026-07-05T07:57:54.044201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12852","citing_title":"WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20601","citing_title":"Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ","json":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ.json","graph_json":"https://pith.science/api/pith-number/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/graph.json","events_json":"https://pith.science/api/pith-number/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/events.json","paper":"https://pith.science/paper/IZZ3QUFO"},"agent_actions":{"view_html":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ","download_json":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ.json","view_paper":"https://pith.science/paper/IZZ3QUFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12037&json=true","fetch_graph":"https://pith.science/api/pith-number/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/action/storage_attestation","attest_author":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/action/author_attestation","sign_citation":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/action/citation_signature","submit_replication":"https://pith.science/pith/IZZ3QUFOPK4SPPMZM4WQE5CZWZ/action/replication_record"}},"created_at":"2026-07-05T07:57:54.044201+00:00","updated_at":"2026-07-05T07:57:54.044201+00:00"}