{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I4AMHPHRVLYWXVMSIMMTLFDTGG","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":"1ffb2531b44cb9252a2130876ae03dbac25f673e9c79874f2cd2206266004668","cross_cats_sorted":["cs.AI","quant-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T06:03:32Z","title_canon_sha256":"e1d050b32744dccafeac06a97eda9eb0b877eff42ec66378d6c8108e69cdd639"},"schema_version":"1.0","source":{"id":"2505.11862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11862","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11862v2","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11862","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"I4AMHPHRVLYW","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"I4AMHPHRVLYWXVMS","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"I4AMHPHR","created_at":"2026-07-05T11:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:02a7396a61f17f5297d40399554086aba78a8a1f1796d16f069e0b8b9fe4bbb5","target":"graph","created_at":"2026-07-05T11:17:45Z","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/2505.11862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Q-Policy, a hybrid quantum-classical reinforcement learning (RL) framework that mathematically accelerates policy evaluation and optimization by exploiting quantum computing primitives. Q-Policy encodes value functions in quantum superposition, enabling simultaneous evaluation of multiple state-action pairs via amplitude encoding and quantum parallelism. We introduce a quantum-enhanced policy iteration algorithm with provable polynomial reductions in sample complexity for the evaluation step, under standard assumptions. To demonstrate the technical feasibility and theoretical soundn","authors_text":"Aarav Lala, Kalyan Cherukuri, Yash Yardi","cross_cats":["cs.AI","quant-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T06:03:32Z","title":"Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11862","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:f90de0cca73a481b571c936eb3e86e70b6a0fef8a394142eafbb8365b28d7fef","target":"record","created_at":"2026-07-05T11:17:45Z","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":"1ffb2531b44cb9252a2130876ae03dbac25f673e9c79874f2cd2206266004668","cross_cats_sorted":["cs.AI","quant-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T06:03:32Z","title_canon_sha256":"e1d050b32744dccafeac06a97eda9eb0b877eff42ec66378d6c8108e69cdd639"},"schema_version":"1.0","source":{"id":"2505.11862","kind":"arxiv","version":2}},"canonical_sha256":"4700c3bcf1aaf16bd592431935947331ae077462904122b9ca431e17355ef8b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4700c3bcf1aaf16bd592431935947331ae077462904122b9ca431e17355ef8b5","first_computed_at":"2026-07-05T11:17:45.489086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:45.489086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hYATS/9xVUp4K98NmGI6d6PLHM/dClf2vNZ3zWhjrRYLPFoo2G/OPc8OrMdIS/79n5nczdQwdpvmnLbOYbNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:45.489561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90de0cca73a481b571c936eb3e86e70b6a0fef8a394142eafbb8365b28d7fef","sha256:02a7396a61f17f5297d40399554086aba78a8a1f1796d16f069e0b8b9fe4bbb5"],"state_sha256":"301da0acd7107ad68cd3e3a2f06cad1d1117bf52c99c80dca8b9c57882a18af2"}