{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NX6G3NMEUW5ZULURLQGUFMAYN3","short_pith_number":"pith:NX6G3NME","schema_version":"1.0","canonical_sha256":"6dfc6db584a5bb9a2e915c0d42b0186ec083cbdd350cd77db099b0a33fa6c7fd","source":{"kind":"arxiv","id":"2606.06673","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"KC Santosh, Rodrigue Rizk, Sumaly Bajracharya, Ujjwal Bhatta, Utsabi Dangol","submitted_at":"2026-06-04T19:46:45Z","abstract_excerpt":"Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration. We propose Uncertainty-Aware LLM-Guided Policy Shaping (ULPS), a novel framework that integrates a calibrated Large Language Model (LLM) into the RL training loop to provide structured, uncertainty-modulated behavioral guidance. ULPS employs an A*-based oracle to synthesize optimal symbolic trajectories, which are used to fine-tune a BERT-based language model. During training, this model supplies acti"},"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":"2606.06673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T19:46:45Z","cross_cats_sorted":[],"title_canon_sha256":"70a8ab1d85864241cfc6a92cc123478eb2b789f6470cef8b207e43aded4c889c","abstract_canon_sha256":"60ffb5b40801fd16d47188e66d6f826a5103a8adcbd708138f4a9843c1591649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:21.840203Z","signature_b64":"1vHeFQNlPDeTRvnOXuq0gBU95AYBJp7vokxbUGEWsE5ccBXzSRBqZIM5g21RdX9kfhjgejHoR5ofYXpAUdbNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dfc6db584a5bb9a2e915c0d42b0186ec083cbdd350cd77db099b0a33fa6c7fd","last_reissued_at":"2026-06-08T01:04:21.838829Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:21.838829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"KC Santosh, Rodrigue Rizk, Sumaly Bajracharya, Ujjwal Bhatta, Utsabi Dangol","submitted_at":"2026-06-04T19:46:45Z","abstract_excerpt":"Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration. We propose Uncertainty-Aware LLM-Guided Policy Shaping (ULPS), a novel framework that integrates a calibrated Large Language Model (LLM) into the RL training loop to provide structured, uncertainty-modulated behavioral guidance. ULPS employs an A*-based oracle to synthesize optimal symbolic trajectories, which are used to fine-tune a BERT-based language model. During training, this model supplies acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06673","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/2606.06673/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":"2606.06673","created_at":"2026-06-08T01:04:21.839187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06673v1","created_at":"2026-06-08T01:04:21.839187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06673","created_at":"2026-06-08T01:04:21.839187+00:00"},{"alias_kind":"pith_short_12","alias_value":"NX6G3NMEUW5Z","created_at":"2026-06-08T01:04:21.839187+00:00"},{"alias_kind":"pith_short_16","alias_value":"NX6G3NMEUW5ZULUR","created_at":"2026-06-08T01:04:21.839187+00:00"},{"alias_kind":"pith_short_8","alias_value":"NX6G3NME","created_at":"2026-06-08T01:04:21.839187+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/NX6G3NMEUW5ZULURLQGUFMAYN3","json":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3.json","graph_json":"https://pith.science/api/pith-number/NX6G3NMEUW5ZULURLQGUFMAYN3/graph.json","events_json":"https://pith.science/api/pith-number/NX6G3NMEUW5ZULURLQGUFMAYN3/events.json","paper":"https://pith.science/paper/NX6G3NME"},"agent_actions":{"view_html":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3","download_json":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3.json","view_paper":"https://pith.science/paper/NX6G3NME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06673&json=true","fetch_graph":"https://pith.science/api/pith-number/NX6G3NMEUW5ZULURLQGUFMAYN3/graph.json","fetch_events":"https://pith.science/api/pith-number/NX6G3NMEUW5ZULURLQGUFMAYN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3/action/storage_attestation","attest_author":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3/action/author_attestation","sign_citation":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3/action/citation_signature","submit_replication":"https://pith.science/pith/NX6G3NMEUW5ZULURLQGUFMAYN3/action/replication_record"}},"created_at":"2026-06-08T01:04:21.839187+00:00","updated_at":"2026-06-08T01:04:21.839187+00:00"}