{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GDTRDDCGIWDJGEVX3BE777XH3M","short_pith_number":"pith:GDTRDDCG","schema_version":"1.0","canonical_sha256":"30e7118c4645869312b7d849fffee7db0d95c83e69824581aaf195880c9a912f","source":{"kind":"arxiv","id":"2308.13542","version":1},"attestation_state":"computed","paper":{"title":"LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hung Le, Laknath Buddhika Semage, Santu Rana, Sunil Gupta, Svetha Venkatesh, Thommen George Karimpanal, Truyen Tran","submitted_at":"2023-08-21T02:07:35Z","abstract_excerpt":"Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. For example, by observing a partial stack of cubes, LLMs can predict the correct sequence in which the remaining cubes should be stacked by extrapolating the observed patterns (e.g., cube sizes, colors or other attributes) in the partial stack. In this work, we introduce LaGR (Language-Guided Reinforcement learning), which uses this"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.13542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-21T02:07:35Z","cross_cats_sorted":[],"title_canon_sha256":"9096639f8b6ba4c8fe6a6c31b97f6e5fdd56f5059448694509ee616bd39acfb2","abstract_canon_sha256":"3558b66dfe1fbed6c1a359ebfab9d42118dfe8e3b64ab7c464b8ba91429e1aaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:51.890209Z","signature_b64":"thPU2iwYfM0V6ZWkCb2Kz7nVYGkP4jmxHG6v4TMMCXMbk/cekL0aSlIBK6Xs0ca9mHzhDpXUhIsWtx02McFCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e7118c4645869312b7d849fffee7db0d95c83e69824581aaf195880c9a912f","last_reissued_at":"2026-07-05T06:44:51.889823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:51.889823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hung Le, Laknath Buddhika Semage, Santu Rana, Sunil Gupta, Svetha Venkatesh, Thommen George Karimpanal, Truyen Tran","submitted_at":"2023-08-21T02:07:35Z","abstract_excerpt":"Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. For example, by observing a partial stack of cubes, LLMs can predict the correct sequence in which the remaining cubes should be stacked by extrapolating the observed patterns (e.g., cube sizes, colors or other attributes) in the partial stack. In this work, we introduce LaGR (Language-Guided Reinforcement learning), which uses this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13542","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.13542/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.13542","created_at":"2026-07-05T06:44:51.889883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13542v1","created_at":"2026-07-05T06:44:51.889883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13542","created_at":"2026-07-05T06:44:51.889883+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDTRDDCGIWDJ","created_at":"2026-07-05T06:44:51.889883+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDTRDDCGIWDJGEVX","created_at":"2026-07-05T06:44:51.889883+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDTRDDCG","created_at":"2026-07-05T06:44:51.889883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M","json":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M.json","graph_json":"https://pith.science/api/pith-number/GDTRDDCGIWDJGEVX3BE777XH3M/graph.json","events_json":"https://pith.science/api/pith-number/GDTRDDCGIWDJGEVX3BE777XH3M/events.json","paper":"https://pith.science/paper/GDTRDDCG"},"agent_actions":{"view_html":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M","download_json":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M.json","view_paper":"https://pith.science/paper/GDTRDDCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13542&json=true","fetch_graph":"https://pith.science/api/pith-number/GDTRDDCGIWDJGEVX3BE777XH3M/graph.json","fetch_events":"https://pith.science/api/pith-number/GDTRDDCGIWDJGEVX3BE777XH3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M/action/storage_attestation","attest_author":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M/action/author_attestation","sign_citation":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M/action/citation_signature","submit_replication":"https://pith.science/pith/GDTRDDCGIWDJGEVX3BE777XH3M/action/replication_record"}},"created_at":"2026-07-05T06:44:51.889883+00:00","updated_at":"2026-07-05T06:44:51.889883+00:00"}