{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJMSWVCUKI6257GFZZGRASHFAV","short_pith_number":"pith:ZJMSWVCU","schema_version":"1.0","canonical_sha256":"ca592b5454523daefcc5ce4d1048e50565ab7c159087ee30d1a7a8b557b68b7d","source":{"kind":"arxiv","id":"2404.02954","version":2},"attestation_state":"computed","paper":{"title":"Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony L. Caterini, Brendan Leigh Ross, Gabriel Loaiza-Ganem, Jesse C. Cresswell, Rasa Hosseinzadeh","submitted_at":"2024-04-03T18:00:00Z","abstract_excerpt":"In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-used DGMs succeed or fail at learning distributions supported on unknown low-dimensional manifolds, as well as developing new models explicitly designed to account for manifold-supported data. This manifold lens provides both clarity as to why some DGMs (e.g. diffusion models and some generative adversarial networks) empirically surpass others (e.g. likelihood-based models such"},"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":"2404.02954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-03T18:00:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a37cc2403bb8d9f605db2ce5d8ce3e230a601a3094439cff85b9a1fd830cd13b","abstract_canon_sha256":"ab76caaac79f6f0d379f77b660dd8b61a4001c246d5eb6cda0e37be03095fc8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:46.911252Z","signature_b64":"w1Bd9EQRwk7Fnqf1GRKXHt/GUvATN2diqOXy6IHB+h9qeJ8Zn6zpOzc48B2bty07iP7/EOuE+3M+XhdTnz3lCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca592b5454523daefcc5ce4d1048e50565ab7c159087ee30d1a7a8b557b68b7d","last_reissued_at":"2026-07-05T09:11:46.910716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:46.910716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony L. Caterini, Brendan Leigh Ross, Gabriel Loaiza-Ganem, Jesse C. Cresswell, Rasa Hosseinzadeh","submitted_at":"2024-04-03T18:00:00Z","abstract_excerpt":"In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-used DGMs succeed or fail at learning distributions supported on unknown low-dimensional manifolds, as well as developing new models explicitly designed to account for manifold-supported data. This manifold lens provides both clarity as to why some DGMs (e.g. diffusion models and some generative adversarial networks) empirically surpass others (e.g. likelihood-based models such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02954","kind":"arxiv","version":2},"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/2404.02954/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":"2404.02954","created_at":"2026-07-05T09:11:46.910775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02954v2","created_at":"2026-07-05T09:11:46.910775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02954","created_at":"2026-07-05T09:11:46.910775+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJMSWVCUKI62","created_at":"2026-07-05T09:11:46.910775+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJMSWVCUKI6257GF","created_at":"2026-07-05T09:11:46.910775+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJMSWVCU","created_at":"2026-07-05T09:11:46.910775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26756","citing_title":"Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13934","citing_title":"Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06701","citing_title":"Bi-Lipschitz Autoencoder With Injectivity Guarantee","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV","json":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV.json","graph_json":"https://pith.science/api/pith-number/ZJMSWVCUKI6257GFZZGRASHFAV/graph.json","events_json":"https://pith.science/api/pith-number/ZJMSWVCUKI6257GFZZGRASHFAV/events.json","paper":"https://pith.science/paper/ZJMSWVCU"},"agent_actions":{"view_html":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV","download_json":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV.json","view_paper":"https://pith.science/paper/ZJMSWVCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02954&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJMSWVCUKI6257GFZZGRASHFAV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJMSWVCUKI6257GFZZGRASHFAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV/action/storage_attestation","attest_author":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV/action/author_attestation","sign_citation":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV/action/citation_signature","submit_replication":"https://pith.science/pith/ZJMSWVCUKI6257GFZZGRASHFAV/action/replication_record"}},"created_at":"2026-07-05T09:11:46.910775+00:00","updated_at":"2026-07-05T09:11:46.910775+00:00"}