{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DBRC7MHCZPX6UW3GXJBJRFTD6K","short_pith_number":"pith:DBRC7MHC","schema_version":"1.0","canonical_sha256":"18622fb0e2cbefea5b66ba42989663f28259e6a89f73e41d0279da70072155bc","source":{"kind":"arxiv","id":"2306.00937","version":3},"attestation_state":"computed","paper":{"title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Harris Chan, Jimmy Ba, Keiran Paster, Shalev Lifshitz, Sheila McIlraith","submitted_at":"2023-06-01T17:39:41Z","abstract_excerpt":"Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces a methodology, inspired by unCLIP, for instruction-tuning generative models of behavior without relying on a large dataset of instruction-labeled trajectories. Using this methodology, we create an instruction-tuned Video Pretraining (VPT) model called STEVE-1, which can follow short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent spac"},"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":"2306.00937","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-01T17:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"30945364301eea26d51033abca530a2350716bfada2e5b026d3ea6f47282ff21","abstract_canon_sha256":"20b3f119f7b280ea25ca38e7437e53913a6fc455c598666b6ba080267d073af8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:53.953766Z","signature_b64":"k2PYA5mrtZJ7+s4rjYsRjz5NsS4XU9Miu2+ADjR74cbcUEHufsj+UDjY9mRjV8ykPGgx2lBopvXd1vzX8mmtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18622fb0e2cbefea5b66ba42989663f28259e6a89f73e41d0279da70072155bc","last_reissued_at":"2026-07-05T07:40:53.953344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:53.953344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Harris Chan, Jimmy Ba, Keiran Paster, Shalev Lifshitz, Sheila McIlraith","submitted_at":"2023-06-01T17:39:41Z","abstract_excerpt":"Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces a methodology, inspired by unCLIP, for instruction-tuning generative models of behavior without relying on a large dataset of instruction-labeled trajectories. Using this methodology, we create an instruction-tuned Video Pretraining (VPT) model called STEVE-1, which can follow short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00937","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/2306.00937/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":"2306.00937","created_at":"2026-07-05T07:40:53.953404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00937v3","created_at":"2026-07-05T07:40:53.953404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00937","created_at":"2026-07-05T07:40:53.953404+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBRC7MHCZPX6","created_at":"2026-07-05T07:40:53.953404+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBRC7MHCZPX6UW3G","created_at":"2026-07-05T07:40:53.953404+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBRC7MHC","created_at":"2026-07-05T07:40:53.953404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2302.01560","citing_title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13918","citing_title":"CA2: Code-Aware Agent for Automated Game Testing","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K","json":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K.json","graph_json":"https://pith.science/api/pith-number/DBRC7MHCZPX6UW3GXJBJRFTD6K/graph.json","events_json":"https://pith.science/api/pith-number/DBRC7MHCZPX6UW3GXJBJRFTD6K/events.json","paper":"https://pith.science/paper/DBRC7MHC"},"agent_actions":{"view_html":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K","download_json":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K.json","view_paper":"https://pith.science/paper/DBRC7MHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00937&json=true","fetch_graph":"https://pith.science/api/pith-number/DBRC7MHCZPX6UW3GXJBJRFTD6K/graph.json","fetch_events":"https://pith.science/api/pith-number/DBRC7MHCZPX6UW3GXJBJRFTD6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K/action/storage_attestation","attest_author":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K/action/author_attestation","sign_citation":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K/action/citation_signature","submit_replication":"https://pith.science/pith/DBRC7MHCZPX6UW3GXJBJRFTD6K/action/replication_record"}},"created_at":"2026-07-05T07:40:53.953404+00:00","updated_at":"2026-07-05T07:40:53.953404+00:00"}