{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NPKJTQT2E7CJHMDB4Y4B7I3PB3","short_pith_number":"pith:NPKJTQT2","schema_version":"1.0","canonical_sha256":"6bd499c27a27c493b061e6381fa36f0ec607e5878590cec7ff6f68a0ae06da28","source":{"kind":"arxiv","id":"1907.13440","version":1},"attestation_state":"computed","paper":{"title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Houghton, Cayden Codel, Manuela Veloso, Nicholay Topin, Phillip Wang, Ruslan Salakhutdinov, William H. Guss","submitted_at":"2019-07-29T18:10:30Z","abstract_excerpt":"The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched less. As demonstrated in the computer vision and natural language processing communities, large-scale datasets have the capacity to facilitate research by serving as an experimental and benchmarking platform for new methods. However, existing datasets compatible with reinforcement learning simulators do not have sufficient scale, structure, and quality to enable the further dev"},"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":"1907.13440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-29T18:10:30Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"b8f43293f18192920d7d68d70ae73538e5ce4fd56e973cfe6947f94b03edf105","abstract_canon_sha256":"04c0bd549baf1c4407bd0bebf72d8d9e1dbbf9529aa98d711c49384120834d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:49.823513Z","signature_b64":"X8gHTCLzkT9Pw3SKM1tcGPo7fCXEH7RAWJ/YxWrsTkvmr1nggijOtQEYmftQGEQ4PTKLPLnmdbWwQrcdGXMSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bd499c27a27c493b061e6381fa36f0ec607e5878590cec7ff6f68a0ae06da28","last_reissued_at":"2026-07-04T23:50:49.823136Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:49.823136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Houghton, Cayden Codel, Manuela Veloso, Nicholay Topin, Phillip Wang, Ruslan Salakhutdinov, William H. Guss","submitted_at":"2019-07-29T18:10:30Z","abstract_excerpt":"The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched less. As demonstrated in the computer vision and natural language processing communities, large-scale datasets have the capacity to facilitate research by serving as an experimental and benchmarking platform for new methods. However, existing datasets compatible with reinforcement learning simulators do not have sufficient scale, structure, and quality to enable the further dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13440","kind":"arxiv","version":1},"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/1907.13440/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":"1907.13440","created_at":"2026-07-04T23:50:49.823195+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.13440v1","created_at":"2026-07-04T23:50:49.823195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13440","created_at":"2026-07-04T23:50:49.823195+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPKJTQT2E7CJ","created_at":"2026-07-04T23:50:49.823195+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPKJTQT2E7CJHMDB","created_at":"2026-07-04T23:50:49.823195+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPKJTQT2","created_at":"2026-07-04T23:50:49.823195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02125","citing_title":"Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":62,"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":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3","json":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3.json","graph_json":"https://pith.science/api/pith-number/NPKJTQT2E7CJHMDB4Y4B7I3PB3/graph.json","events_json":"https://pith.science/api/pith-number/NPKJTQT2E7CJHMDB4Y4B7I3PB3/events.json","paper":"https://pith.science/paper/NPKJTQT2"},"agent_actions":{"view_html":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3","download_json":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3.json","view_paper":"https://pith.science/paper/NPKJTQT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.13440&json=true","fetch_graph":"https://pith.science/api/pith-number/NPKJTQT2E7CJHMDB4Y4B7I3PB3/graph.json","fetch_events":"https://pith.science/api/pith-number/NPKJTQT2E7CJHMDB4Y4B7I3PB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3/action/storage_attestation","attest_author":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3/action/author_attestation","sign_citation":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3/action/citation_signature","submit_replication":"https://pith.science/pith/NPKJTQT2E7CJHMDB4Y4B7I3PB3/action/replication_record"}},"created_at":"2026-07-04T23:50:49.823195+00:00","updated_at":"2026-07-04T23:50:49.823195+00:00"}