{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RCVTFHNKC7XEAUDRK5HTOOGOEA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"40efea16c6b94d7601b2cacd2e960bdfa5fadda1bf1c9fa9dcbe849f46b103ce","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T04:12:23Z","title_canon_sha256":"1ada9cde792120bf76a812348abe99ee93aff0634bb9802a512d2013c9934aa6"},"schema_version":"1.0","source":{"id":"2112.03482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03482","created_at":"2026-07-05T04:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03482v2","created_at":"2026-07-05T04:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03482","created_at":"2026-07-05T04:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"RCVTFHNKC7XE","created_at":"2026-07-05T04:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"RCVTFHNKC7XEAUDR","created_at":"2026-07-05T04:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"RCVTFHNK","created_at":"2026-07-05T04:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:efe59e4a7e8cd73af61958b5a28e8f2fdf7d660bac62bba27db15207973bed61","target":"graph","created_at":"2026-07-05T04:22:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.03482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world tasks of interest are generally poorly defined by human-readable descriptions and have no pre-defined reward signals unless it is defined by a human designer. Conversely, data-driven algorithms are often designed to solve a specific, narrowly defined, task with performance metrics that drives the agent's learning. In this work, we present the solution that won first place and was awarded the most human-like agent in the 2021 NeurIPS Competition MineRL BASALT Challenge: Learning from Human Feedback in Minecraft, which challenged participants to use human data to solve four tasks defi","authors_text":"Bharat Prakash, David Watkins-Valls, Nicholas Waytowich, Vinicius G. Goecks","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T04:12:23Z","title":"Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03482","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3d2ee079b2e026c6edd9c25f48d3bca506e0891f2371d03c59215b73b1ae33b4","target":"record","created_at":"2026-07-05T04:22:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"40efea16c6b94d7601b2cacd2e960bdfa5fadda1bf1c9fa9dcbe849f46b103ce","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T04:12:23Z","title_canon_sha256":"1ada9cde792120bf76a812348abe99ee93aff0634bb9802a512d2013c9934aa6"},"schema_version":"1.0","source":{"id":"2112.03482","kind":"arxiv","version":2}},"canonical_sha256":"88ab329daa17ee405071574f3738ce20328929bc9cb12ef9d52d9ed284cf07c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88ab329daa17ee405071574f3738ce20328929bc9cb12ef9d52d9ed284cf07c5","first_computed_at":"2026-07-05T04:22:39.676952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:39.676952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"re/muRRkjY3NFIR5go1tNEcRTtmvTc1v5l1ybhk2eP5ArhmFdCEgv7NdrAgBds2feQjEme1n7c5eHXbcSV8+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:39.677376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d2ee079b2e026c6edd9c25f48d3bca506e0891f2371d03c59215b73b1ae33b4","sha256:efe59e4a7e8cd73af61958b5a28e8f2fdf7d660bac62bba27db15207973bed61"],"state_sha256":"f0f97fddfd253bdc8012a7287ff124e972fc527307aa4b46fce6967bdaeef4a6"}