{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UFCYHPY7SZDWNG4DQYX6VIMOLY","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":"7009807d6e787e95b69ed3365132c51c6ac066c3b5235c4b3c585d90cf9201e9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-02T12:10:07Z","title_canon_sha256":"c95cbb58a4e0b499d971998965129ee65dc3e96617bf58a613381ba7e3490b06"},"schema_version":"1.0","source":{"id":"2410.01458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01458","created_at":"2026-07-05T09:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01458v1","created_at":"2026-07-05T09:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01458","created_at":"2026-07-05T09:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"UFCYHPY7SZDW","created_at":"2026-07-05T09:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"UFCYHPY7SZDWNG4D","created_at":"2026-07-05T09:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"UFCYHPY7","created_at":"2026-07-05T09:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:59772760faa0e38aa45fe2cace922f3969c9af11f5319140823cc427259138f4","target":"graph","created_at":"2026-07-05T09:14:48Z","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/2410.01458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Q-shaping is an extension of Q-value initialization and serves as an alternative to reward shaping for incorporating domain knowledge to accelerate agent training, thereby improving sample efficiency by directly shaping Q-values. This approach is both general and robust across diverse tasks, allowing for immediate impact assessment while guaranteeing optimality. We evaluated Q-shaping across 20 different environments using a large language model (LLM) as the heuristic provider. The results demonstrate that Q-shaping significantly enhances sample efficiency, achieving a \\textbf{16.87\\%} improve","authors_text":"Xiefeng Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-02T12:10:07Z","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01458","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":"sha256:1cbc4d9f65cebdb7471e8ec986b2658941b22a080c59dde3c5ff9264508ae8b4","target":"record","created_at":"2026-07-05T09:14:48Z","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":"7009807d6e787e95b69ed3365132c51c6ac066c3b5235c4b3c585d90cf9201e9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-02T12:10:07Z","title_canon_sha256":"c95cbb58a4e0b499d971998965129ee65dc3e96617bf58a613381ba7e3490b06"},"schema_version":"1.0","source":{"id":"2410.01458","kind":"arxiv","version":1}},"canonical_sha256":"a14583bf1f9647669b83862feaa18e5e13f9c11e3382a264a785b5de41bf3ad4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a14583bf1f9647669b83862feaa18e5e13f9c11e3382a264a785b5de41bf3ad4","first_computed_at":"2026-07-05T09:14:48.258510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:48.258510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dtjtTpdZH7rTY4IySwZXn0gGoJ3U/3O35ZMYUlYynmxEZhgi4IvfcwgLSMmdcL3AkVJYXF3HkBpNwMFrR6YbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:48.258907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cbc4d9f65cebdb7471e8ec986b2658941b22a080c59dde3c5ff9264508ae8b4","sha256:59772760faa0e38aa45fe2cace922f3969c9af11f5319140823cc427259138f4"],"state_sha256":"74613fac2e3bd33e554b36622c009ad2a0b867298fbf4ed37118523e368d50d3"}