{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VV6F6ZIXT3CZT4QQZD37G2BZI4","short_pith_number":"pith:VV6F6ZIX","schema_version":"1.0","canonical_sha256":"ad7c5f65179ec599f210c8f7f3683947063adad28eff75d7fbd7a1be98b666a0","source":{"kind":"arxiv","id":"2605.16429","version":1},"attestation_state":"computed","paper":{"title":"QuantFPFlow: Quantum Amplitude Estimation for Fokker--Planck Policy Optimisation in Continuous Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abraham Itzhak Weinberg","submitted_at":"2026-05-14T18:35:38Z","abstract_excerpt":"We introduce \\textbf{QuantFPFlow}, a reinforcement learning framework that integrates quantum amplitude estimation into the Fokker--Planck~(FP) formulation of stochastic policy optimisation. Classical continuous-space RL agents must estimate the FP partition function $Z = \\int e^{-V(\\mathbf{x})/D}\\,d\\mathbf{x}$ at cost $\\calO(1/\\varepsilon^{2})$; QuantFPFlow replaces this with a Grover-amplified amplitude estimator achieving $\\calO(1/\\varepsilon)$ -- a provable quadratic speedup. While the full quantum acceleration requires fault-tolerant hardware, the quantum-inspired classical simulation dem"},"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":"2605.16429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T18:35:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f32756e437d80d1cc3f3f4fb82f51d0f77e7562ba20d47c0230240e74740d9c","abstract_canon_sha256":"65fa682029762d7d602fe69ce3485dd012038403a007ac050e801449216c468e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:21.714350Z","signature_b64":"y5IpmM2Bb/P84gwcdQ1Fj2OSxOPe8q1jEQ/ZCrdWcMpia8X9wSkmBkkKAmE2miQZrJDvg2EUKMb8eFB+Q9zwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7c5f65179ec599f210c8f7f3683947063adad28eff75d7fbd7a1be98b666a0","last_reissued_at":"2026-05-20T00:02:21.713628Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:21.713628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuantFPFlow: Quantum Amplitude Estimation for Fokker--Planck Policy Optimisation in Continuous Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abraham Itzhak Weinberg","submitted_at":"2026-05-14T18:35:38Z","abstract_excerpt":"We introduce \\textbf{QuantFPFlow}, a reinforcement learning framework that integrates quantum amplitude estimation into the Fokker--Planck~(FP) formulation of stochastic policy optimisation. Classical continuous-space RL agents must estimate the FP partition function $Z = \\int e^{-V(\\mathbf{x})/D}\\,d\\mathbf{x}$ at cost $\\calO(1/\\varepsilon^{2})$; QuantFPFlow replaces this with a Grover-amplified amplitude estimator achieving $\\calO(1/\\varepsilon)$ -- a provable quadratic speedup. While the full quantum acceleration requires fault-tolerant hardware, the quantum-inspired classical simulation dem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16429","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/2605.16429/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:41:56.546863Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.583432Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a264554fa894ce1618045c0e364cb0771d3de3627f1f74669b314d5c2ca6c2bd"},"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":"2605.16429","created_at":"2026-05-20T00:02:21.713740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16429v1","created_at":"2026-05-20T00:02:21.713740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16429","created_at":"2026-05-20T00:02:21.713740+00:00"},{"alias_kind":"pith_short_12","alias_value":"VV6F6ZIXT3CZ","created_at":"2026-05-20T00:02:21.713740+00:00"},{"alias_kind":"pith_short_16","alias_value":"VV6F6ZIXT3CZT4QQ","created_at":"2026-05-20T00:02:21.713740+00:00"},{"alias_kind":"pith_short_8","alias_value":"VV6F6ZIX","created_at":"2026-05-20T00:02:21.713740+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/VV6F6ZIXT3CZT4QQZD37G2BZI4","json":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4.json","graph_json":"https://pith.science/api/pith-number/VV6F6ZIXT3CZT4QQZD37G2BZI4/graph.json","events_json":"https://pith.science/api/pith-number/VV6F6ZIXT3CZT4QQZD37G2BZI4/events.json","paper":"https://pith.science/paper/VV6F6ZIX"},"agent_actions":{"view_html":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4","download_json":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4.json","view_paper":"https://pith.science/paper/VV6F6ZIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16429&json=true","fetch_graph":"https://pith.science/api/pith-number/VV6F6ZIXT3CZT4QQZD37G2BZI4/graph.json","fetch_events":"https://pith.science/api/pith-number/VV6F6ZIXT3CZT4QQZD37G2BZI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4/action/storage_attestation","attest_author":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4/action/author_attestation","sign_citation":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4/action/citation_signature","submit_replication":"https://pith.science/pith/VV6F6ZIXT3CZT4QQZD37G2BZI4/action/replication_record"}},"created_at":"2026-05-20T00:02:21.713740+00:00","updated_at":"2026-05-20T00:02:21.713740+00:00"}