{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3FGTKV43BN4Q5BMKBS4W2P4MPK","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":"4a69ec6b4c8b393d74a93df1e64e94f606f29201b9ff7ac6d3b7db1853150554","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T06:47:01Z","title_canon_sha256":"6cad73d5d2058db0d2878bfc0875ad6103e3c19d4d01101741203f596ed9778d"},"schema_version":"1.0","source":{"id":"2603.11600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11600","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11600v2","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11600","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"3FGTKV43BN4Q","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"3FGTKV43BN4Q5BMK","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"3FGTKV43","created_at":"2026-06-01T01:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:05824e2fe3906764204268579ef6cf6621f681b4ab6cf3847b10e555d666b0ef","target":"graph","created_at":"2026-06-01T01:03:51Z","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/2603.11600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms -- assumed known a priori -- directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization ob","authors_text":"Jue Yang, Mingan Zhao, Qijun Liao, Xinxin Zhao, Yiting Kang, Yong Zhang","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T06:47:01Z","title":"Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11600","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":"sha256:2f7423c2b59f22951dbf1aecfc0c8c4426e0121b946676e7e4e3c79f3791d181","target":"record","created_at":"2026-06-01T01:03:51Z","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":"4a69ec6b4c8b393d74a93df1e64e94f606f29201b9ff7ac6d3b7db1853150554","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-12T06:47:01Z","title_canon_sha256":"6cad73d5d2058db0d2878bfc0875ad6103e3c19d4d01101741203f596ed9778d"},"schema_version":"1.0","source":{"id":"2603.11600","kind":"arxiv","version":2}},"canonical_sha256":"d94d35579b0b790e858a0cb96d3f8c7ab49d7dde57cec54f350b48606915ccf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d94d35579b0b790e858a0cb96d3f8c7ab49d7dde57cec54f350b48606915ccf8","first_computed_at":"2026-06-01T01:03:51.869105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:51.869105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQA/BnbXp2GviZxL5M7Dcv/pZjULyD3zG91SkKC6BQqxtepvif9atMBi3ONmkWvLXk/nCpvgmsNFCLJ6L0BUDA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:51.870191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f7423c2b59f22951dbf1aecfc0c8c4426e0121b946676e7e4e3c79f3791d181","sha256:05824e2fe3906764204268579ef6cf6621f681b4ab6cf3847b10e555d666b0ef"],"state_sha256":"9a578678b11dca3dc9bfca3dc7a805114b6a0bd6e76ac1c2c5a1d77e509084cb"}