{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O3IMU3EV7GOULE2L36UDGJVZXW","short_pith_number":"pith:O3IMU3EV","schema_version":"1.0","canonical_sha256":"76d0ca6c95f99d45934bdfa83326b9bd8004a5425d37df4111d8f826c1ca58da","source":{"kind":"arxiv","id":"2303.13462","version":3},"attestation_state":"computed","paper":{"title":"Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"M.S. Kim, Tobias Haug","submitted_at":"2023-03-23T17:32:20Z","abstract_excerpt":"Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to gener"},"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":"2303.13462","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-03-23T17:32:20Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b3c65a4bc7cd2d47758b1ecd1c1207c06b60a91f6ee9d608decc128ed035f7dd","abstract_canon_sha256":"f8489306f9271b8c26016e28eaccd7ecf94fe96b6c80308771fcf097522c5634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:24.363288Z","signature_b64":"l/wY3Q50n2YA1OOuMyHWkUGLCutXkJb+jpjUEwqQ9C0T3r63Qkf8o7owAvwI6Gn55lqxrZkQJ/cVh7Fnzb/UAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76d0ca6c95f99d45934bdfa83326b9bd8004a5425d37df4111d8f826c1ca58da","last_reissued_at":"2026-07-05T08:52:24.362866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:24.362866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"M.S. Kim, Tobias Haug","submitted_at":"2023-03-23T17:32:20Z","abstract_excerpt":"Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13462","kind":"arxiv","version":3},"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/2303.13462/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":"2303.13462","created_at":"2026-07-05T08:52:24.362923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13462v3","created_at":"2026-07-05T08:52:24.362923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13462","created_at":"2026-07-05T08:52:24.362923+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3IMU3EV7GOU","created_at":"2026-07-05T08:52:24.362923+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3IMU3EV7GOULE2L","created_at":"2026-07-05T08:52:24.362923+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3IMU3EV","created_at":"2026-07-05T08:52:24.362923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12441","citing_title":"Efficient classical training of model-free quantum photonic reservoir","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW","json":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW.json","graph_json":"https://pith.science/api/pith-number/O3IMU3EV7GOULE2L36UDGJVZXW/graph.json","events_json":"https://pith.science/api/pith-number/O3IMU3EV7GOULE2L36UDGJVZXW/events.json","paper":"https://pith.science/paper/O3IMU3EV"},"agent_actions":{"view_html":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW","download_json":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW.json","view_paper":"https://pith.science/paper/O3IMU3EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13462&json=true","fetch_graph":"https://pith.science/api/pith-number/O3IMU3EV7GOULE2L36UDGJVZXW/graph.json","fetch_events":"https://pith.science/api/pith-number/O3IMU3EV7GOULE2L36UDGJVZXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW/action/storage_attestation","attest_author":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW/action/author_attestation","sign_citation":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW/action/citation_signature","submit_replication":"https://pith.science/pith/O3IMU3EV7GOULE2L36UDGJVZXW/action/replication_record"}},"created_at":"2026-07-05T08:52:24.362923+00:00","updated_at":"2026-07-05T08:52:24.362923+00:00"}