{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SEWW3H2LOUGZDPE7FV2HPYLPZM","short_pith_number":"pith:SEWW3H2L","schema_version":"1.0","canonical_sha256":"912d6d9f4b750d91bc9f2d7477e16fcb21407da5df91e2c7af8e792b73dc2763","source":{"kind":"arxiv","id":"2102.05132","version":1},"attestation_state":"computed","paper":{"title":"Using Deep LSD to build operators in GANs latent space with meaning in real space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.soft"],"primary_cat":"cs.LG","authors_text":"James A. Glazier, J. Quetzalcoatl Toledo-Marin","submitted_at":"2021-02-09T21:05:20Z","abstract_excerpt":"Generative models rely on the key idea that data can be represented in terms of latent variables which are uncorrelated by definition. Lack of correlation is important because it suggests that the latent space manifold is simpler to understand and manipulate. Generative models are widely used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). Here we propose a method to build a set of linearly independent vectors in the latent space of a GANs, which we call quasi-eigenvectors. These quasi-eigenvectors have two key properties: i) They span all th"},"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":"2102.05132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T21:05:20Z","cross_cats_sorted":["cond-mat.soft"],"title_canon_sha256":"784e4d69b1281bb7b5274b0ff840756e274a9cd69a54e8c9d472555494a788d7","abstract_canon_sha256":"0ee4ecd287a9c250a2597c072a69f68423493f4be775ba41bc51a5183bd8ccef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:15.330788Z","signature_b64":"LE5SE4OT/2lQZ+2cr3bjdGoh+kQq/7mdvGMzJe9haFY5VBpr6fbn8lYwj++e6b2YGrD7xV/gGMbNP6w7VMkhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"912d6d9f4b750d91bc9f2d7477e16fcb21407da5df91e2c7af8e792b73dc2763","last_reissued_at":"2026-07-05T02:14:15.330374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:15.330374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Deep LSD to build operators in GANs latent space with meaning in real space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.soft"],"primary_cat":"cs.LG","authors_text":"James A. Glazier, J. Quetzalcoatl Toledo-Marin","submitted_at":"2021-02-09T21:05:20Z","abstract_excerpt":"Generative models rely on the key idea that data can be represented in terms of latent variables which are uncorrelated by definition. Lack of correlation is important because it suggests that the latent space manifold is simpler to understand and manipulate. Generative models are widely used in deep learning, e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs). Here we propose a method to build a set of linearly independent vectors in the latent space of a GANs, which we call quasi-eigenvectors. These quasi-eigenvectors have two key properties: i) They span all th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05132","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/2102.05132/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":"2102.05132","created_at":"2026-07-05T02:14:15.330436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05132v1","created_at":"2026-07-05T02:14:15.330436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05132","created_at":"2026-07-05T02:14:15.330436+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEWW3H2LOUGZ","created_at":"2026-07-05T02:14:15.330436+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEWW3H2LOUGZDPE7","created_at":"2026-07-05T02:14:15.330436+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEWW3H2L","created_at":"2026-07-05T02:14:15.330436+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/SEWW3H2LOUGZDPE7FV2HPYLPZM","json":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM.json","graph_json":"https://pith.science/api/pith-number/SEWW3H2LOUGZDPE7FV2HPYLPZM/graph.json","events_json":"https://pith.science/api/pith-number/SEWW3H2LOUGZDPE7FV2HPYLPZM/events.json","paper":"https://pith.science/paper/SEWW3H2L"},"agent_actions":{"view_html":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM","download_json":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM.json","view_paper":"https://pith.science/paper/SEWW3H2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05132&json=true","fetch_graph":"https://pith.science/api/pith-number/SEWW3H2LOUGZDPE7FV2HPYLPZM/graph.json","fetch_events":"https://pith.science/api/pith-number/SEWW3H2LOUGZDPE7FV2HPYLPZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM/action/storage_attestation","attest_author":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM/action/author_attestation","sign_citation":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM/action/citation_signature","submit_replication":"https://pith.science/pith/SEWW3H2LOUGZDPE7FV2HPYLPZM/action/replication_record"}},"created_at":"2026-07-05T02:14:15.330436+00:00","updated_at":"2026-07-05T02:14:15.330436+00:00"}