{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZWSV27YJO65AYQGJYHOFP2CMUT","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":"1121ffa0efd68818a6a5e1e837627903247456379f4fc3686c90d48fb249d7b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T11:31:01Z","title_canon_sha256":"67b3d8007c145582229561287283fb92883fdbf1bcf5a839538ec35cf4aa2ebb"},"schema_version":"1.0","source":{"id":"2310.08235","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08235","created_at":"2026-07-05T07:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08235v2","created_at":"2026-07-05T07:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08235","created_at":"2026-07-05T07:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZWSV27YJO65A","created_at":"2026-07-05T07:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZWSV27YJO65AYQGJ","created_at":"2026-07-05T07:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZWSV27YJ","created_at":"2026-07-05T07:17:55Z"}],"graph_snapshots":[{"event_id":"sha256:9839bc860eaafb19d72e78922292985c1d4b16b16c96fd13d7d26243fcae9f03","target":"graph","created_at":"2026-07-05T07:17:55Z","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/2310.08235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations. A new learning framework is derived to allow learning such instruction-following controllers from gameplay videos while producing a video instruction encoder that induces a structured goal space. We implement our agent GROOT in a simple yet effective encoder-decoder architecture based on causal transformers. We evaluat","authors_text":"Anji Liu, Bowei Zhang, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zihao Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T11:31:01Z","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08235","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:a4b6a37b9ae6a907b17b0a213e86bd2fa00241a5b31970a38a349d659414e1c6","target":"record","created_at":"2026-07-05T07:17:55Z","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":"1121ffa0efd68818a6a5e1e837627903247456379f4fc3686c90d48fb249d7b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T11:31:01Z","title_canon_sha256":"67b3d8007c145582229561287283fb92883fdbf1bcf5a839538ec35cf4aa2ebb"},"schema_version":"1.0","source":{"id":"2310.08235","kind":"arxiv","version":2}},"canonical_sha256":"cda55d7f0977ba0c40c9c1dc57e84ca4f6e2bf3b4ef0e26f5475877c223ac8e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cda55d7f0977ba0c40c9c1dc57e84ca4f6e2bf3b4ef0e26f5475877c223ac8e7","first_computed_at":"2026-07-05T07:17:55.092070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:55.092070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cd1LRiGabImKMmvD94xkquW7HReqXLwPviS/P80O/U313dBReoSlJ+galjZ+QPWAJW0V5QuTZJjprP2JgKbUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:55.092551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08235","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4b6a37b9ae6a907b17b0a213e86bd2fa00241a5b31970a38a349d659414e1c6","sha256:9839bc860eaafb19d72e78922292985c1d4b16b16c96fd13d7d26243fcae9f03"],"state_sha256":"7b1a7804c5871b460f49bb2e4eb1eaccfee14e978e7204d614f7a63d3345d1f2"}