{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RMANWZLVMKS34LOOMOGHS63BNY","short_pith_number":"pith:RMANWZLV","canonical_record":{"source":{"id":"2605.15098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-05-14T17:17:02Z","cross_cats_sorted":["cs.AR","cs.DC","cs.PF"],"title_canon_sha256":"ab0278035131fd083be6076e11dda2875d9c963675ce40413b017a366cb77c05","abstract_canon_sha256":"f34c7d8e569f91a86d6822de689fe972e5ed3b1ba7c2d49d608421437fe4e5db"},"schema_version":"1.0"},"canonical_sha256":"8b00db657562a5be2dce638c797b616e309a2da07e1f9297a2f021458ea82c37","source":{"kind":"arxiv","id":"2605.15098","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15098","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15098v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"RMANWZLVMKS3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RMANWZLVMKS34LOO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RMANWZLV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RMANWZLVMKS34LOOMOGHS63BNY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-05-14T17:17:02Z","cross_cats_sorted":["cs.AR","cs.DC","cs.PF"],"title_canon_sha256":"ab0278035131fd083be6076e11dda2875d9c963675ce40413b017a366cb77c05","abstract_canon_sha256":"f34c7d8e569f91a86d6822de689fe972e5ed3b1ba7c2d49d608421437fe4e5db"},"schema_version":"1.0"},"canonical_sha256":"8b00db657562a5be2dce638c797b616e309a2da07e1f9297a2f021458ea82c37","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"8b00db657562a5be2dce638c797b616e309a2da07e1f9297a2f021458ea82c37","last_reissued_at":"2026-05-17T21:57:19.171156Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.842436Z"},"source_kind":"arxiv","source_id":"2605.15098","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uX1eVMgvIbGv8HzGtH3cCSSzAns5bZKsZkXcOP9c8bzPQ42zPUnac6i4nqetWbXw2u+qUxwzADrM+zM083YDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:45:45.025400Z"},"content_sha256":"37116cd5a5e19b68f312e188c1a81b8eac8323df98942c89e7a8378d5ab2bc1c","schema_version":"1.0","event_id":"sha256:37116cd5a5e19b68f312e188c1a81b8eac8323df98942c89e7a8378d5ab2bc1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RMANWZLVMKS34LOOMOGHS63BNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating State-Vector Quantum Simulation on Integrated GPUs via Cache Locality Optimization: A Cross-Architecture Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows.","cross_cats":["cs.AR","cs.DC","cs.PF"],"primary_cat":"quant-ph","authors_text":"Eduarda Rodrigues Monteiro, Evandro Chagas Ribeiro da Rosa, Fernando Augusto Caletti de Barros, Gabriel Fernandes Thomaz, Jerusa Marchi","submitted_at":"2026-05-14T17:17:02Z","abstract_excerpt":"The classical simulation of quantum algorithms is a crucial tool for circuit development, testing, and validation. Although acceleration using GPUs significantly reduces simulation time, most high-performance simulators rely on vendor-specific frameworks that target data-center hardware. To broaden access to quantum simulation, this work proposes a vendor-agnostic approach targeting the integrated GPUs commonly found in consumer-grade laptops. A primary challenge in state-vector simulation is its inherently poor spatial locality, which creates a memory bandwidth bottleneck. Consequently, basel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the proposed optimization successfully mitigates performance degradation at larger qubit scales. In particular, for a 28-qubit simulation, the optimization reversed a performance deficit on an Intel Core i5, improving the GPU speedup over the CPU from 0.95x to 1.89x, and increased the Apple M1 Pro speedup from 3.71x to 5.88x.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the state partitioning reorganization can be performed with negligible overhead and that the resulting cache behavior remains consistent across diverse integrated GPU architectures without architecture-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"State partitioning optimization improves cache locality and reverses GPU performance deficits for 28-qubit quantum state-vector simulations on integrated GPUs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9951763dfbdbe38c022831f2d4188338b45ff0af477e44cb5484e355ed4040e9"},"source":{"id":"2605.15098","kind":"arxiv","version":1},"verdict":{"id":"63ef5013-3c2a-4bb3-939b-04f2cbeb710d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:07:11.695368Z","strongest_claim":"the proposed optimization successfully mitigates performance degradation at larger qubit scales. In particular, for a 28-qubit simulation, the optimization reversed a performance deficit on an Intel Core i5, improving the GPU speedup over the CPU from 0.95x to 1.89x, and increased the Apple M1 Pro speedup from 3.71x to 5.88x.","one_line_summary":"State partitioning optimization improves cache locality and reverses GPU performance deficits for 28-qubit quantum state-vector simulations on integrated GPUs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the state partitioning reorganization can be performed with negligible overhead and that the resulting cache behavior remains consistent across diverse integrated GPU architectures without architecture-specific tuning.","pith_extraction_headline":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows."},"references":{"count":14,"sample":[{"doi":"","year":2025,"title":"Quantum Software Engineering: Roadmap and Chal- lenges Ahead,","work_id":"aff14af5-e87e-453d-a648-59c9d4216aec","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Quantum Computing in the NISQ era and beyond,","work_id":"f3d5423c-5324-4b46-a490-c74e72d74168","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Simulation of Quantum Computers: Review and Acceleration Oppor- tunities,","work_id":"f630f667-bd9e-4b0f-9885-b99b73ec8c4f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1997,"title":"Stabilizer Codes and Quantum Error Correction,","work_id":"20cfbf22-7d35-40af-ab4e-cd0ce600c7ce","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"qHiPSTER: The Quantum High Performance Software Testing Environment,","work_id":"b628ee3c-a754-42ca-b64c-eabfa7a0eded","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"b52290a4474c6d47162438505dfe9dd7303998960d2d801fd75646154a5288c5","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"},"verdict_id":"63ef5013-3c2a-4bb3-939b-04f2cbeb710d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tOorhc5aTQF+MMLRqqp15Dk4g/H8+89cmoHRlcG5nSPcwJAN8sUwb06KUPkEocY2kK1xK3ny2CAEn2pTV8fRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:45:45.026400Z"},"content_sha256":"b228ce458da03477c243db98a44172fb2e0cf76d785f2a2f4b862c67472edf99","schema_version":"1.0","event_id":"sha256:b228ce458da03477c243db98a44172fb2e0cf76d785f2a2f4b862c67472edf99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMANWZLVMKS34LOOMOGHS63BNY/bundle.json","state_url":"https://pith.science/pith/RMANWZLVMKS34LOOMOGHS63BNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMANWZLVMKS34LOOMOGHS63BNY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T08:45:45Z","links":{"resolver":"https://pith.science/pith/RMANWZLVMKS34LOOMOGHS63BNY","bundle":"https://pith.science/pith/RMANWZLVMKS34LOOMOGHS63BNY/bundle.json","state":"https://pith.science/pith/RMANWZLVMKS34LOOMOGHS63BNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMANWZLVMKS34LOOMOGHS63BNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RMANWZLVMKS34LOOMOGHS63BNY","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":"f34c7d8e569f91a86d6822de689fe972e5ed3b1ba7c2d49d608421437fe4e5db","cross_cats_sorted":["cs.AR","cs.DC","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-05-14T17:17:02Z","title_canon_sha256":"ab0278035131fd083be6076e11dda2875d9c963675ce40413b017a366cb77c05"},"schema_version":"1.0","source":{"id":"2605.15098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15098","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15098v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"RMANWZLVMKS3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RMANWZLVMKS34LOO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RMANWZLV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b228ce458da03477c243db98a44172fb2e0cf76d785f2a2f4b862c67472edf99","target":"graph","created_at":"2026-05-17T21:57:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"the proposed optimization successfully mitigates performance degradation at larger qubit scales. In particular, for a 28-qubit simulation, the optimization reversed a performance deficit on an Intel Core i5, improving the GPU speedup over the CPU from 0.95x to 1.89x, and increased the Apple M1 Pro speedup from 3.71x to 5.88x."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the state partitioning reorganization can be performed with negligible overhead and that the resulting cache behavior remains consistent across diverse integrated GPU architectures without architecture-specific tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"State partitioning optimization improves cache locality and reverses GPU performance deficits for 28-qubit quantum state-vector simulations on integrated GPUs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows."}],"snapshot_sha256":"9951763dfbdbe38c022831f2d4188338b45ff0af477e44cb5484e355ed4040e9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The classical simulation of quantum algorithms is a crucial tool for circuit development, testing, and validation. Although acceleration using GPUs significantly reduces simulation time, most high-performance simulators rely on vendor-specific frameworks that target data-center hardware. To broaden access to quantum simulation, this work proposes a vendor-agnostic approach targeting the integrated GPUs commonly found in consumer-grade laptops. A primary challenge in state-vector simulation is its inherently poor spatial locality, which creates a memory bandwidth bottleneck. Consequently, basel","authors_text":"Eduarda Rodrigues Monteiro, Evandro Chagas Ribeiro da Rosa, Fernando Augusto Caletti de Barros, Gabriel Fernandes Thomaz, Jerusa Marchi","cross_cats":["cs.AR","cs.DC","cs.PF"],"headline":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-05-14T17:17:02Z","title":"Accelerating State-Vector Quantum Simulation on Integrated GPUs via Cache Locality Optimization: A Cross-Architecture Evaluation"},"references":{"count":14,"internal_anchors":0,"resolved_work":14,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Quantum Software Engineering: Roadmap and Chal- lenges Ahead,","work_id":"aff14af5-e87e-453d-a648-59c9d4216aec","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Quantum Computing in the NISQ era and beyond,","work_id":"f3d5423c-5324-4b46-a490-c74e72d74168","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Simulation of Quantum Computers: Review and Acceleration Oppor- tunities,","work_id":"f630f667-bd9e-4b0f-9885-b99b73ec8c4f","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Stabilizer Codes and Quantum Error Correction,","work_id":"20cfbf22-7d35-40af-ab4e-cd0ce600c7ce","year":1997},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"qHiPSTER: The Quantum High Performance Software Testing Environment,","work_id":"b628ee3c-a754-42ca-b64c-eabfa7a0eded","year":2016}],"snapshot_sha256":"b52290a4474c6d47162438505dfe9dd7303998960d2d801fd75646154a5288c5"},"source":{"id":"2605.15098","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:07:11.695368Z","id":"63ef5013-3c2a-4bb3-939b-04f2cbeb710d","model_set":{"reader":"grok-4.3"},"one_line_summary":"State partitioning optimization improves cache locality and reverses GPU performance deficits for 28-qubit quantum state-vector simulations on integrated GPUs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Reorganizing the quantum state vector for last-level cache locality reverses GPU performance degradation on integrated hardware as qubit count grows.","strongest_claim":"the proposed optimization successfully mitigates performance degradation at larger qubit scales. In particular, for a 28-qubit simulation, the optimization reversed a performance deficit on an Intel Core i5, improving the GPU speedup over the CPU from 0.95x to 1.89x, and increased the Apple M1 Pro speedup from 3.71x to 5.88x.","weakest_assumption":"That the state partitioning reorganization can be performed with negligible overhead and that the resulting cache behavior remains consistent across diverse integrated GPU architectures without architecture-specific tuning."}},"verdict_id":"63ef5013-3c2a-4bb3-939b-04f2cbeb710d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37116cd5a5e19b68f312e188c1a81b8eac8323df98942c89e7a8378d5ab2bc1c","target":"record","created_at":"2026-05-17T21:18:33Z","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":"f34c7d8e569f91a86d6822de689fe972e5ed3b1ba7c2d49d608421437fe4e5db","cross_cats_sorted":["cs.AR","cs.DC","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-05-14T17:17:02Z","title_canon_sha256":"ab0278035131fd083be6076e11dda2875d9c963675ce40413b017a366cb77c05"},"schema_version":"1.0","source":{"id":"2605.15098","kind":"arxiv","version":1}},"canonical_sha256":"8b00db657562a5be2dce638c797b616e309a2da07e1f9297a2f021458ea82c37","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b00db657562a5be2dce638c797b616e309a2da07e1f9297a2f021458ea82c37","first_computed_at":"2026-05-17T21:40:25.842436Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:19.171156Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37116cd5a5e19b68f312e188c1a81b8eac8323df98942c89e7a8378d5ab2bc1c","sha256:b228ce458da03477c243db98a44172fb2e0cf76d785f2a2f4b862c67472edf99"],"state_sha256":"c74285428b81a0f1b4578202e7e01a1a25ab6e37479c6ccb8e3cfb2034e91283"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RU6rCxPO4eGxDr4XHRwVTadQP2zyzMDBML+XsC027VgSZHlUnfqw1NOYBzd8tLoPi0k3WPAEfg99BxTS4VJwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:45:45.030956Z","bundle_sha256":"079bc60e6fe9b97ff27be622129e30102f5c3aa66207bb0763babb7f74585a4a"}}