{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HSTQG4I3XOTAOVH7WZHEERMJTX","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":"df505377e413d4367e824f5211e89e03127babcdad70fa6216a79e4dfa4f7850","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:04:07Z","title_canon_sha256":"027b2b3c33233c5c777b54c82f580629cf89ccb746fca65371b2d984d11f6e18"},"schema_version":"1.0","source":{"id":"2301.12050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12050","created_at":"2026-07-05T06:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12050v2","created_at":"2026-07-05T06:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12050","created_at":"2026-07-05T06:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"HSTQG4I3XOTA","created_at":"2026-07-05T06:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"HSTQG4I3XOTAOVH7","created_at":"2026-07-05T06:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"HSTQG4I3","created_at":"2026-07-05T06:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:fdb385ab707f408c741b9f04dc906889e65ae2e07f8d32f5fd8e6daca2e428cb","target":"graph","created_at":"2026-07-05T06:04:53Z","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/2301.12050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of the world. However, if initialized with knowledge of high-level subgoals and transitions between subgoals, RL agents could utilize this Abstract World Model (AWM) for planning and exploration. We propose using few-shot large language models (LLMs) to hypothesize an AWM, that will be verified through world experience, to improve sample efficiency of RL agents. Our DECKARD agent applies LLM-guided exploration to item crafting in Minecraft in two phases: (1) the Dream phase where the agent uses an LLM to de","authors_text":"Alane Suhr, Hannaneh Hajishirzi, Kolby Nottingham, Prithviraj Ammanabrolu, Roy Fox, Sameer Singh, Yejin Choi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:04:07Z","title":"Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12050","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":"sha256:815461c5e208851c7fd9eba2e8602bfdda8178ea72fcf4f7f7147c615284545d","target":"record","created_at":"2026-07-05T06:04:53Z","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":"df505377e413d4367e824f5211e89e03127babcdad70fa6216a79e4dfa4f7850","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:04:07Z","title_canon_sha256":"027b2b3c33233c5c777b54c82f580629cf89ccb746fca65371b2d984d11f6e18"},"schema_version":"1.0","source":{"id":"2301.12050","kind":"arxiv","version":2}},"canonical_sha256":"3ca703711bbba60754ffb64e4245899de4879c4725056c4be0a25f2bfa8ec43c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ca703711bbba60754ffb64e4245899de4879c4725056c4be0a25f2bfa8ec43c","first_computed_at":"2026-07-05T06:04:53.959861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:53.959861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJ6YmHR0s9iUUvc0O0S8H7qrNXouvoxxJIru8567GgVBroLZAfkhm3/CqsLd0ficlE+7hlZz6cFPdzlEBY0RBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:53.960386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:815461c5e208851c7fd9eba2e8602bfdda8178ea72fcf4f7f7147c615284545d","sha256:fdb385ab707f408c741b9f04dc906889e65ae2e07f8d32f5fd8e6daca2e428cb"],"state_sha256":"98570419409c4ddda838a9513a5ee9dbfc4d7f2ea126655b46c71a784b1ab83b"}