{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBNHSZUZ35EQYNVWQFSAFU35F5","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":"0e93e8ef22252a298bbb8fc2208d212bee3be68716ec11bfaba09b76d87f2a75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:26:41Z","title_canon_sha256":"5102f5471f9ad6324e491571a43d7acd6261a059529c2efa73104d7d8c0b9ae2"},"schema_version":"1.0","source":{"id":"2403.03141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03141","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03141v1","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03141","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_12","alias_value":"KBNHSZUZ35EQ","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_16","alias_value":"KBNHSZUZ35EQYNVW","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_8","alias_value":"KBNHSZUZ","created_at":"2026-07-05T07:52:36Z"}],"graph_snapshots":[{"event_id":"sha256:34b2a5c43584de8b34b79ba1a8be63271d3058e89b57dcfc5c3997fb7d8a77a2","target":"graph","created_at":"2026-07-05T07:52:36Z","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/2403.03141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\\textit{tabula rasa}$ reinforcement learning (RL) agents. Large Language Models (LLMs), with a wealth of world knowledge, can help RL agents learn quickly and adapt to distribution shifts. In this work, we introduce Language Guided Exploration (LGE) framework, which uses a pre-trained language model (called GUIDE ) to provide decision-level guidance to an RL agent (called EXPLORER). We observe that on ScienceWorld (Wang et al.","authors_text":"Dhruvesh Patel, Hitesh Golchha, Keerthiram Murugesan, Sahil Yerawar, Soham Dan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:26:41Z","title":"Language Guided Exploration for RL Agents in Text Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03141","kind":"arxiv","version":1},"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":"sha256:9dd653060cfc231196be86f9a5b6e5ab3f99e9f704762372fd68cfccc3b44735","target":"record","created_at":"2026-07-05T07:52:36Z","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":"0e93e8ef22252a298bbb8fc2208d212bee3be68716ec11bfaba09b76d87f2a75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T17:26:41Z","title_canon_sha256":"5102f5471f9ad6324e491571a43d7acd6261a059529c2efa73104d7d8c0b9ae2"},"schema_version":"1.0","source":{"id":"2403.03141","kind":"arxiv","version":1}},"canonical_sha256":"505a796699df490c36b6816402d37d2f723dc8f9d58b56c1bf6b51f5d72bb140","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"505a796699df490c36b6816402d37d2f723dc8f9d58b56c1bf6b51f5d72bb140","first_computed_at":"2026-07-05T07:52:36.527550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:36.527550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8I1npYdf7DjQ/ZLzHNoM546kX+6G5zQtfl4H65KgLDE8g/tJKHa4ttx9nGPxJDUlHEzhIHQ/SmbWHzyELt4sBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:36.527893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dd653060cfc231196be86f9a5b6e5ab3f99e9f704762372fd68cfccc3b44735","sha256:34b2a5c43584de8b34b79ba1a8be63271d3058e89b57dcfc5c3997fb7d8a77a2"],"state_sha256":"0f0b959b98d0ba3625b3a39703f02c7a22561656ebba07ce04290e64428ba769"}