{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I4AMHPHRVLYWXVMSIMMTLFDTGG","short_pith_number":"pith:I4AMHPHR","schema_version":"1.0","canonical_sha256":"4700c3bcf1aaf16bd592431935947331ae077462904122b9ca431e17355ef8b5","source":{"kind":"arxiv","id":"2505.11862","version":2},"attestation_state":"computed","paper":{"title":"Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","quant-ph"],"primary_cat":"cs.LG","authors_text":"Aarav Lala, Kalyan Cherukuri, Yash Yardi","submitted_at":"2025-05-17T06:03:32Z","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"},"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":"2505.11862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T06:03:32Z","cross_cats_sorted":["cs.AI","quant-ph"],"title_canon_sha256":"e1d050b32744dccafeac06a97eda9eb0b877eff42ec66378d6c8108e69cdd639","abstract_canon_sha256":"1ffb2531b44cb9252a2130876ae03dbac25f673e9c79874f2cd2206266004668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:45.489561Z","signature_b64":"2hYATS/9xVUp4K98NmGI6d6PLHM/dClf2vNZ3zWhjrRYLPFoo2G/OPc8OrMdIS/79n5nczdQwdpvmnLbOYbNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4700c3bcf1aaf16bd592431935947331ae077462904122b9ca431e17355ef8b5","last_reissued_at":"2026-07-05T11:17:45.489086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:45.489086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","quant-ph"],"primary_cat":"cs.LG","authors_text":"Aarav Lala, Kalyan Cherukuri, Yash Yardi","submitted_at":"2025-05-17T06:03:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11862","kind":"arxiv","version":2},"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/2505.11862/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":"2505.11862","created_at":"2026-07-05T11:17:45.489144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11862v2","created_at":"2026-07-05T11:17:45.489144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11862","created_at":"2026-07-05T11:17:45.489144+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4AMHPHRVLYW","created_at":"2026-07-05T11:17:45.489144+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4AMHPHRVLYWXVMS","created_at":"2026-07-05T11:17:45.489144+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4AMHPHR","created_at":"2026-07-05T11:17:45.489144+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/I4AMHPHRVLYWXVMSIMMTLFDTGG","json":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG.json","graph_json":"https://pith.science/api/pith-number/I4AMHPHRVLYWXVMSIMMTLFDTGG/graph.json","events_json":"https://pith.science/api/pith-number/I4AMHPHRVLYWXVMSIMMTLFDTGG/events.json","paper":"https://pith.science/paper/I4AMHPHR"},"agent_actions":{"view_html":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG","download_json":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG.json","view_paper":"https://pith.science/paper/I4AMHPHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11862&json=true","fetch_graph":"https://pith.science/api/pith-number/I4AMHPHRVLYWXVMSIMMTLFDTGG/graph.json","fetch_events":"https://pith.science/api/pith-number/I4AMHPHRVLYWXVMSIMMTLFDTGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG/action/storage_attestation","attest_author":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG/action/author_attestation","sign_citation":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG/action/citation_signature","submit_replication":"https://pith.science/pith/I4AMHPHRVLYWXVMSIMMTLFDTGG/action/replication_record"}},"created_at":"2026-07-05T11:17:45.489144+00:00","updated_at":"2026-07-05T11:17:45.489144+00:00"}