{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5EU2T5SEDKURGJVORSBOF3FBY","short_pith_number":"pith:Q5EU2T5S","schema_version":"1.0","canonical_sha256":"87494d4fb220d548993574641717650e34b7276de88f7e89380e7e06302a424f","source":{"kind":"arxiv","id":"2606.27246","version":1},"attestation_state":"computed","paper":{"title":"Effective Covariance Dynamics in Solvable High-Dimensional GANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Bond, Zafer Do\\u{g}an","submitted_at":"2026-06-25T16:33:54Z","abstract_excerpt":"We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data with structured latent covariance. Prior solvable GAN analyses assume unconditional signals with diagonal latent covariance; we extend the multi-feature discriminator setting to class-dependent, correlated, and non-zero-mean latent structure. For the quadratic energy discriminator, all such heterogeneity enters the dynamics through a probability-weighted effective second moment. We prove that the stochastic microscopic training proc"},"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":"2606.27246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T16:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"0f6f8d573b79534e68d2b0f2066323eebf15541118d7bf01c1b6a08d720e0faa","abstract_canon_sha256":"e26fce60ad21040b68d4b4dc8944895a2ec19de779d0cb92a5e46d60a2f1b25a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:16.329343Z","signature_b64":"FYtKIBqb4hKDVesQnjIp5i0uaVGR4QNEpkUSiybkslAcrc19KTJiGMM49Ikuv+AviHw3M259THH+qJVAY4wLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87494d4fb220d548993574641717650e34b7276de88f7e89380e7e06302a424f","last_reissued_at":"2026-06-26T01:16:16.328938Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:16.328938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Covariance Dynamics in Solvable High-Dimensional GANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Bond, Zafer Do\\u{g}an","submitted_at":"2026-06-25T16:33:54Z","abstract_excerpt":"We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data with structured latent covariance. Prior solvable GAN analyses assume unconditional signals with diagonal latent covariance; we extend the multi-feature discriminator setting to class-dependent, correlated, and non-zero-mean latent structure. For the quadratic energy discriminator, all such heterogeneity enters the dynamics through a probability-weighted effective second moment. We prove that the stochastic microscopic training proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27246","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/2606.27246/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":"2606.27246","created_at":"2026-06-26T01:16:16.328995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27246v1","created_at":"2026-06-26T01:16:16.328995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27246","created_at":"2026-06-26T01:16:16.328995+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5EU2T5SEDKU","created_at":"2026-06-26T01:16:16.328995+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5EU2T5SEDKURGJV","created_at":"2026-06-26T01:16:16.328995+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5EU2T5S","created_at":"2026-06-26T01:16:16.328995+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/Q5EU2T5SEDKURGJVORSBOF3FBY","json":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY.json","graph_json":"https://pith.science/api/pith-number/Q5EU2T5SEDKURGJVORSBOF3FBY/graph.json","events_json":"https://pith.science/api/pith-number/Q5EU2T5SEDKURGJVORSBOF3FBY/events.json","paper":"https://pith.science/paper/Q5EU2T5S"},"agent_actions":{"view_html":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY","download_json":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY.json","view_paper":"https://pith.science/paper/Q5EU2T5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27246&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5EU2T5SEDKURGJVORSBOF3FBY/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5EU2T5SEDKURGJVORSBOF3FBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY/action/storage_attestation","attest_author":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY/action/author_attestation","sign_citation":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY/action/citation_signature","submit_replication":"https://pith.science/pith/Q5EU2T5SEDKURGJVORSBOF3FBY/action/replication_record"}},"created_at":"2026-06-26T01:16:16.328995+00:00","updated_at":"2026-06-26T01:16:16.328995+00:00"}