{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZK4FKFDQW4HVOOFX7JZFHJSBOA","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":"7436ce5bd041c7c629c23419fa8abbe12cc38b0e796a2d0bebc175005b4a2980","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T21:16:03Z","title_canon_sha256":"9e2cc5836f6d3b2f46f9ac0c05447b2ae4f30ae82daadf26ef5eb2a7bb5d7a77"},"schema_version":"1.0","source":{"id":"2302.06692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06692","created_at":"2026-07-05T06:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06692v2","created_at":"2026-07-05T06:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06692","created_at":"2026-07-05T06:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZK4FKFDQW4HV","created_at":"2026-07-05T06:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZK4FKFDQW4HVOOFX","created_at":"2026-07-05T06:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZK4FKFDQ","created_at":"2026-07-05T06:50:53Z"}],"graph_snapshots":[{"event_id":"sha256:3edf5c7a59c3c259dc50a90f7322594d2e9e8b43acb4207f8bcf29cb73e6a295","target":"graph","created_at":"2026-07-05T06:50:53Z","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/2302.06692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by rewarding agents for visiting novel states or transitions, but these methods offer limited benefits in large environments where most discovered novelty is irrelevant for downstream tasks. We describe a method that uses background knowledge from text corpora to shape exploration. This method, called ELLM (Exploring with LLMs) rewards an agent for achieving goals suggested by a language model prompted with a descriptio","authors_text":"Abhishek Gupta, C\\'edric Colas, Jacob Andreas, Olivia Watkins, Pieter Abbeel, Trevor Darrell, Yuqing Du, Zihan Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T21:16:03Z","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06692","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":"sha256:97132efbda63eb68af90ac785106deca83b5dbb638be4cecad107a23d17bf8bc","target":"record","created_at":"2026-07-05T06:50:53Z","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":"7436ce5bd041c7c629c23419fa8abbe12cc38b0e796a2d0bebc175005b4a2980","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T21:16:03Z","title_canon_sha256":"9e2cc5836f6d3b2f46f9ac0c05447b2ae4f30ae82daadf26ef5eb2a7bb5d7a77"},"schema_version":"1.0","source":{"id":"2302.06692","kind":"arxiv","version":2}},"canonical_sha256":"cab8551470b70f5738b7fa7253a641703ee7d09e306063ea74251931525540ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab8551470b70f5738b7fa7253a641703ee7d09e306063ea74251931525540ec","first_computed_at":"2026-07-05T06:50:53.744262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:53.744262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCbxv98SOpGnV/V+h4Sek61PlZnsuryVVlwKX3KEU0B4MYrcYM0Y9On+ugWjTufs4zHTz0/MuA2YFlNWbH+yAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:53.744765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97132efbda63eb68af90ac785106deca83b5dbb638be4cecad107a23d17bf8bc","sha256:3edf5c7a59c3c259dc50a90f7322594d2e9e8b43acb4207f8bcf29cb73e6a295"],"state_sha256":"6729844968a9bd56eb47a41da903cd4b01836578aa99d5ccdb865be8c13cc698"}