{"paper":{"title":"Parity Supervision as a Driver of Generalization in Quantum Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Parity supervision enables quantum Born machines to generalize from finite samples to unseen states by transferring evidence through parity moments.","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Claudia Linnhoff-Popien, Daniel Hein, Jonas Stein, Markus Baumann, Steffen Udluft, Tobias Rohe","submitted_at":"2026-05-11T09:24:12Z","abstract_excerpt":"Generative models learn probability distributions in order to produce new samples beyond a finite training set. Their usefulness therefore depends on assigning probability to valid but previously unseen states. In a controlled benchmark, we test whether parity-based training provides an inductive bias for this kind of generalization in instantaneous quantum polynomial-time (IQP) circuit Born machines. We compare the same IQP circuit trained with parity supervision and coordinate-wise mean-squared error (MSE), together with classical controls. Parity supervision improves exact distributional fi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Parity supervision improves exact forward Kullback-Leibler fit and unseen high-value-state recovery over IQP-MSE, while the maximum-entropy control does not reproduce the full effect. A parameter-free spectral reconstruction shows that parity moments already transfer evidence from observed samples to structurally compatible unseen states, which the IQP circuit further refines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The distribution to be learned, the parity objective, and the circuit architecture are structurally aligned; without this alignment the generalization benefit is not claimed to hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Parity supervision improves exact KL fit and recovery of unseen high-value states in IQP Born machines beyond MSE training or max-entropy controls via parity-moment evidence transfer.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Parity supervision enables quantum Born machines to generalize from finite samples to unseen states by transferring evidence through parity moments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4ef8ce220358a3b9b51f130ebf84402d70bb5aab7bb53c111193abc7030165ba"},"source":{"id":"2605.10258","kind":"arxiv","version":2},"verdict":{"id":"a25621bb-599e-40b3-8bd2-8a1ac3ce71fe","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:22:12.005098Z","strongest_claim":"Parity supervision improves exact forward Kullback-Leibler fit and unseen high-value-state recovery over IQP-MSE, while the maximum-entropy control does not reproduce the full effect. A parameter-free spectral reconstruction shows that parity moments already transfer evidence from observed samples to structurally compatible unseen states, which the IQP circuit further refines.","one_line_summary":"Parity supervision improves exact KL fit and recovery of unseen high-value states in IQP Born machines beyond MSE training or max-entropy controls via parity-moment evidence transfer.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The distribution to be learned, the parity objective, and the circuit architecture are structurally aligned; without this alignment the generalization benefit is not claimed to hold.","pith_extraction_headline":"Parity supervision enables quantum Born machines to generalize from finite samples to unseen states by transferring evidence through parity moments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10258/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.872451Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:37:44.245858Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.573624Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:31:52.904798Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7065718a7e207775a07481373e94caddbe6266c09757c39d82168036bdfac8f3"},"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"}