{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFIMTQIMJL4J7NAXN62TVIX5VL","short_pith_number":"pith:MFIMTQIM","schema_version":"1.0","canonical_sha256":"6150c9c10c4af89fb4176fb53aa2fdaafcca15f172f69215ce58ab939722e571","source":{"kind":"arxiv","id":"2606.29293","version":1},"attestation_state":"computed","paper":{"title":"Private training in quantum machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Elham Kashefi, Fr\\'ed\\'eric Grosshans, Tigran Sedrakyan","submitted_at":"2026-06-28T09:28:58Z","abstract_excerpt":"With the emergence of machine learning (ML) models trained on large datasets containing potentially sensitive data, a major question in AI safety is how to make learning private with respect to the training data. Similar to classical machine learning, quantum machine learning (QML) models are not devoid of privacy vulnerabilities. Differential privacy (DP) is a standard tool for training ML models on sensitive data, but its impact in QML remains poorly understood. In this work we study private training in hybrid variational QML models using a classical private DP-SGD optimizer applied to pipel"},"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":"2606.29293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2026-06-28T09:28:58Z","cross_cats_sorted":[],"title_canon_sha256":"ff9c97492c9425271a84e3e2381c76ceda513ad482e11ef29a0da6eca238bd38","abstract_canon_sha256":"a3174c6f272d5dc12ca74cc7e686ca59b968112b425b01367494fe19f4eeef4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:00.522352Z","signature_b64":"58ZT7VyelJvTovWxbVsIUUuQuc7/hzZem2T1pDr6nvUUPlxjfLXPjU4cfr8UgvrvQEdS324HuctAH+IevVMABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6150c9c10c4af89fb4176fb53aa2fdaafcca15f172f69215ce58ab939722e571","last_reissued_at":"2026-06-30T01:18:00.521787Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:00.521787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private training in quantum machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Elham Kashefi, Fr\\'ed\\'eric Grosshans, Tigran Sedrakyan","submitted_at":"2026-06-28T09:28:58Z","abstract_excerpt":"With the emergence of machine learning (ML) models trained on large datasets containing potentially sensitive data, a major question in AI safety is how to make learning private with respect to the training data. Similar to classical machine learning, quantum machine learning (QML) models are not devoid of privacy vulnerabilities. Differential privacy (DP) is a standard tool for training ML models on sensitive data, but its impact in QML remains poorly understood. In this work we study private training in hybrid variational QML models using a classical private DP-SGD optimizer applied to pipel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29293","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/2606.29293/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":"2606.29293","created_at":"2026-06-30T01:18:00.521876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29293v1","created_at":"2026-06-30T01:18:00.521876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29293","created_at":"2026-06-30T01:18:00.521876+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFIMTQIMJL4J","created_at":"2026-06-30T01:18:00.521876+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFIMTQIMJL4J7NAX","created_at":"2026-06-30T01:18:00.521876+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFIMTQIM","created_at":"2026-06-30T01:18:00.521876+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/MFIMTQIMJL4J7NAXN62TVIX5VL","json":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL.json","graph_json":"https://pith.science/api/pith-number/MFIMTQIMJL4J7NAXN62TVIX5VL/graph.json","events_json":"https://pith.science/api/pith-number/MFIMTQIMJL4J7NAXN62TVIX5VL/events.json","paper":"https://pith.science/paper/MFIMTQIM"},"agent_actions":{"view_html":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL","download_json":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL.json","view_paper":"https://pith.science/paper/MFIMTQIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29293&json=true","fetch_graph":"https://pith.science/api/pith-number/MFIMTQIMJL4J7NAXN62TVIX5VL/graph.json","fetch_events":"https://pith.science/api/pith-number/MFIMTQIMJL4J7NAXN62TVIX5VL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL/action/storage_attestation","attest_author":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL/action/author_attestation","sign_citation":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL/action/citation_signature","submit_replication":"https://pith.science/pith/MFIMTQIMJL4J7NAXN62TVIX5VL/action/replication_record"}},"created_at":"2026-06-30T01:18:00.521876+00:00","updated_at":"2026-06-30T01:18:00.521876+00:00"}