{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TCGW5W2BFHNUUESFEF343HFQ3E","short_pith_number":"pith:TCGW5W2B","schema_version":"1.0","canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","source":{"kind":"arxiv","id":"2110.10804","version":2},"attestation_state":"computed","paper":{"title":"Identifiable Deep Generative Models via Sparse Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"David M. Blei, Dhanya Sridhar, Gemma E. Moran, Yixin Wang","submitted_at":"2021-10-20T22:11:33Z","abstract_excerpt":"We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying model is sparse in that each observed feature (i.e. each dimension of the data) depends on a small subset of the latent factors. As examples, in ratings data each movie is only described by a few genres; in text data each word is only applicable to a few topics; in genomics, each gene is active in only a few biological processes. We prove such sparse deep genera"},"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":"2110.10804","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-20T22:11:33Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"1e8a2e8057feb7fc2c73289faf9bdf02c49f477f32271139d0069af9867657bf","abstract_canon_sha256":"2cfd27f90959772c05c11fc4d65084cbd92599d8c60896068046832fe9125b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:01.581741Z","signature_b64":"4urm6dnJ4Jvc/YF7CEoPasnnjoeL06SU2FLkfd2FTWO1xg51TvlMNINx6YTvuZdw156d35yrcUQqxxEzDwQXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","last_reissued_at":"2026-07-05T10:49:01.581233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:01.581233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifiable Deep Generative Models via Sparse Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"David M. Blei, Dhanya Sridhar, Gemma E. Moran, Yixin Wang","submitted_at":"2021-10-20T22:11:33Z","abstract_excerpt":"We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying model is sparse in that each observed feature (i.e. each dimension of the data) depends on a small subset of the latent factors. As examples, in ratings data each movie is only described by a few genres; in text data each word is only applicable to a few topics; in genomics, each gene is active in only a few biological processes. We prove such sparse deep genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10804","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/2110.10804/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":"2110.10804","created_at":"2026-07-05T10:49:01.581298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10804v2","created_at":"2026-07-05T10:49:01.581298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10804","created_at":"2026-07-05T10:49:01.581298+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCGW5W2BFHNU","created_at":"2026-07-05T10:49:01.581298+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCGW5W2BFHNUUESF","created_at":"2026-07-05T10:49:01.581298+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCGW5W2B","created_at":"2026-07-05T10:49:01.581298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22196","citing_title":"Mechanistic Independence: A Principle for Identifiable Disentangled Representations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12733","citing_title":"From Generalist to Specialist Representation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2311.03658","citing_title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17568","citing_title":"Diverse Dictionary Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E","json":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E.json","graph_json":"https://pith.science/api/pith-number/TCGW5W2BFHNUUESFEF343HFQ3E/graph.json","events_json":"https://pith.science/api/pith-number/TCGW5W2BFHNUUESFEF343HFQ3E/events.json","paper":"https://pith.science/paper/TCGW5W2B"},"agent_actions":{"view_html":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E","download_json":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E.json","view_paper":"https://pith.science/paper/TCGW5W2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10804&json=true","fetch_graph":"https://pith.science/api/pith-number/TCGW5W2BFHNUUESFEF343HFQ3E/graph.json","fetch_events":"https://pith.science/api/pith-number/TCGW5W2BFHNUUESFEF343HFQ3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/action/storage_attestation","attest_author":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/action/author_attestation","sign_citation":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/action/citation_signature","submit_replication":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/action/replication_record"}},"created_at":"2026-07-05T10:49:01.581298+00:00","updated_at":"2026-07-05T10:49:01.581298+00:00"}