{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FKSFZGNSF2ILVJV26FMEV5CXJY","short_pith_number":"pith:FKSFZGNS","schema_version":"1.0","canonical_sha256":"2aa45c99b22e90baa6baf1584af4574e0445164d790b78b5ad6869cc07c18b4a","source":{"kind":"arxiv","id":"2311.15209","version":3},"attestation_state":"computed","paper":{"title":"See and Think: Embodied Agent in Virtual Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoang Wang, Li Boyi, Shengyu Hao, Shidong Cao, Tian Ye, Wenhao Chai, Xuan Wang, Zhonghan Zhao","submitted_at":"2023-11-26T06:38:16Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. STEVE comprises three key components: vision perception, language instruction, and code action. Vision perception involves interpreting visual information in the environment, which is then integrated into the LLMs component with agent state and task instruction. Language instruction is responsible for iterative reasoning and deco"},"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":"2311.15209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-26T06:38:16Z","cross_cats_sorted":[],"title_canon_sha256":"fcc936944b305cd8bac08aab4b743ca77081892626412bf3c6bf220e69c84f87","abstract_canon_sha256":"8d941007d275c01607c0e240dddf704b49d34bec9444d5c7adb09b420ed1a7df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:41.828179Z","signature_b64":"OH/R1pQW97LZ1nJAmdlslca/W8TPJ8VxS7ENmUg+Ssqv02kFITdgxAbTCdeARQaQiNvJK4aI6wvrk9UiB8CKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aa45c99b22e90baa6baf1584af4574e0445164d790b78b5ad6869cc07c18b4a","last_reissued_at":"2026-07-05T08:41:41.827547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:41.827547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"See and Think: Embodied Agent in Virtual Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoang Wang, Li Boyi, Shengyu Hao, Shidong Cao, Tian Ye, Wenhao Chai, Xuan Wang, Zhonghan Zhao","submitted_at":"2023-11-26T06:38:16Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. STEVE comprises three key components: vision perception, language instruction, and code action. Vision perception involves interpreting visual information in the environment, which is then integrated into the LLMs component with agent state and task instruction. Language instruction is responsible for iterative reasoning and deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15209","kind":"arxiv","version":3},"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/2311.15209/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":"2311.15209","created_at":"2026-07-05T08:41:41.827628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15209v3","created_at":"2026-07-05T08:41:41.827628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15209","created_at":"2026-07-05T08:41:41.827628+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKSFZGNSF2IL","created_at":"2026-07-05T08:41:41.827628+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKSFZGNSF2ILVJV2","created_at":"2026-07-05T08:41:41.827628+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKSFZGNS","created_at":"2026-07-05T08:41:41.827628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07429","citing_title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07752","citing_title":"MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY","json":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY.json","graph_json":"https://pith.science/api/pith-number/FKSFZGNSF2ILVJV26FMEV5CXJY/graph.json","events_json":"https://pith.science/api/pith-number/FKSFZGNSF2ILVJV26FMEV5CXJY/events.json","paper":"https://pith.science/paper/FKSFZGNS"},"agent_actions":{"view_html":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY","download_json":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY.json","view_paper":"https://pith.science/paper/FKSFZGNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15209&json=true","fetch_graph":"https://pith.science/api/pith-number/FKSFZGNSF2ILVJV26FMEV5CXJY/graph.json","fetch_events":"https://pith.science/api/pith-number/FKSFZGNSF2ILVJV26FMEV5CXJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY/action/storage_attestation","attest_author":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY/action/author_attestation","sign_citation":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY/action/citation_signature","submit_replication":"https://pith.science/pith/FKSFZGNSF2ILVJV26FMEV5CXJY/action/replication_record"}},"created_at":"2026-07-05T08:41:41.827628+00:00","updated_at":"2026-07-05T08:41:41.827628+00:00"}