{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E525X2U3G7NO3CGCAXRBRULTPP","short_pith_number":"pith:E525X2U3","schema_version":"1.0","canonical_sha256":"2775dbea9b37daed88c205e218d1737bce6a2f42eb17ce3a36248b513debe5e9","source":{"kind":"arxiv","id":"2109.06957","version":3},"attestation_state":"computed","paper":{"title":"Critical Points in Quantum Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Eric R. Anschuetz","submitted_at":"2021-09-14T20:34:28Z","abstract_excerpt":"One of the most important properties of neural networks is the clustering of local minima of the loss function near the global minimum, enabling efficient training. Though generative models implemented on quantum computers are known to be more expressive than their traditional counterparts, it has empirically been observed that these models experience a transition in the quality of their local minima. Namely, below some critical number of parameters, all local minima are far from the global minimum in function value; above this critical parameter count, all local minima are good approximators "},"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":"2109.06957","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2021-09-14T20:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"be430f2aa23a5f3baa151660f7760aa65d1653e986297b739deb40036633adbf","abstract_canon_sha256":"6d3c4aa08e6205ea135bd63a8bf0b90d62334fb2ad0913f5ee41a68cc9f40ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:28.807538Z","signature_b64":"k8BYQ2TbmN3Z6+Dy4v3edXFGt5q94K3wbhyeIfnEMecIepUeKoiDLCwlip9+YlHMIvj22hrK3InQ5BL12EgABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2775dbea9b37daed88c205e218d1737bce6a2f42eb17ce3a36248b513debe5e9","last_reissued_at":"2026-07-05T05:32:28.807019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:28.807019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Critical Points in Quantum Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Eric R. Anschuetz","submitted_at":"2021-09-14T20:34:28Z","abstract_excerpt":"One of the most important properties of neural networks is the clustering of local minima of the loss function near the global minimum, enabling efficient training. Though generative models implemented on quantum computers are known to be more expressive than their traditional counterparts, it has empirically been observed that these models experience a transition in the quality of their local minima. Namely, below some critical number of parameters, all local minima are far from the global minimum in function value; above this critical parameter count, all local minima are good approximators "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06957","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/2109.06957/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":"2109.06957","created_at":"2026-07-05T05:32:28.807077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06957v3","created_at":"2026-07-05T05:32:28.807077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06957","created_at":"2026-07-05T05:32:28.807077+00:00"},{"alias_kind":"pith_short_12","alias_value":"E525X2U3G7NO","created_at":"2026-07-05T05:32:28.807077+00:00"},{"alias_kind":"pith_short_16","alias_value":"E525X2U3G7NO3CGC","created_at":"2026-07-05T05:32:28.807077+00:00"},{"alias_kind":"pith_short_8","alias_value":"E525X2U3","created_at":"2026-07-05T05:32:28.807077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05719","citing_title":"Symmetries and overparametrization properties of Hamiltonian variational ansatzes for the $(1+1)$d $\\mathbb{Z}_2$ lattice gauge theory","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28483","citing_title":"Quantum Fourier Generative Models Trainable at Large Scale","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP","json":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP.json","graph_json":"https://pith.science/api/pith-number/E525X2U3G7NO3CGCAXRBRULTPP/graph.json","events_json":"https://pith.science/api/pith-number/E525X2U3G7NO3CGCAXRBRULTPP/events.json","paper":"https://pith.science/paper/E525X2U3"},"agent_actions":{"view_html":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP","download_json":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP.json","view_paper":"https://pith.science/paper/E525X2U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06957&json=true","fetch_graph":"https://pith.science/api/pith-number/E525X2U3G7NO3CGCAXRBRULTPP/graph.json","fetch_events":"https://pith.science/api/pith-number/E525X2U3G7NO3CGCAXRBRULTPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP/action/storage_attestation","attest_author":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP/action/author_attestation","sign_citation":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP/action/citation_signature","submit_replication":"https://pith.science/pith/E525X2U3G7NO3CGCAXRBRULTPP/action/replication_record"}},"created_at":"2026-07-05T05:32:28.807077+00:00","updated_at":"2026-07-05T05:32:28.807077+00:00"}