{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TCGW5W2BFHNUUESFEF343HFQ3E","short_pith_number":"pith:TCGW5W2B","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"},"canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","source":{"kind":"arxiv","id":"2110.10804","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10804","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10804v2","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10804","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"TCGW5W2BFHNU","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"TCGW5W2BFHNUUESF","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"TCGW5W2B","created_at":"2026-07-05T10:49:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TCGW5W2BFHNUUESFEF343HFQ3E","target":"record","payload":{"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"},"canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","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"},"source_kind":"arxiv","source_id":"2110.10804","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eenHzZs15li04XCDjiICPip7z5jVq3FZrxNxoCXCO1bMh0bmNJBcf+nunSs2ma0gVwJydyPTL+iYt2PPESuDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:35:20.476983Z"},"content_sha256":"260a57251ad934276f49d95a264de40faac54d591fa0d418f0cb30fe93611bfb","schema_version":"1.0","event_id":"sha256:260a57251ad934276f49d95a264de40faac54d591fa0d418f0cb30fe93611bfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TCGW5W2BFHNUUESFEF343HFQ3E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lt5cD1lZq0p/fcHUxIR1OCxEIBE+Zs/fpchPKumOuH626dTUCc7gipnSRBe9I9O8ipQqjIl94cUVn8p0rLaABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:35:20.477505Z"},"content_sha256":"c4de9bd13f8de8e2e1d25b6e7722fb9e942cd34b0837ec3d044d08f61e4a6ebe","schema_version":"1.0","event_id":"sha256:c4de9bd13f8de8e2e1d25b6e7722fb9e942cd34b0837ec3d044d08f61e4a6ebe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/bundle.json","state_url":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCGW5W2BFHNUUESFEF343HFQ3E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:35:20Z","links":{"resolver":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E","bundle":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/bundle.json","state":"https://pith.science/pith/TCGW5W2BFHNUUESFEF343HFQ3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCGW5W2BFHNUUESFEF343HFQ3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TCGW5W2BFHNUUESFEF343HFQ3E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2cfd27f90959772c05c11fc4d65084cbd92599d8c60896068046832fe9125b2f","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-20T22:11:33Z","title_canon_sha256":"1e8a2e8057feb7fc2c73289faf9bdf02c49f477f32271139d0069af9867657bf"},"schema_version":"1.0","source":{"id":"2110.10804","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10804","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10804v2","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10804","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"TCGW5W2BFHNU","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"TCGW5W2BFHNUUESF","created_at":"2026-07-05T10:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"TCGW5W2B","created_at":"2026-07-05T10:49:01Z"}],"graph_snapshots":[{"event_id":"sha256:c4de9bd13f8de8e2e1d25b6e7722fb9e942cd34b0837ec3d044d08f61e4a6ebe","target":"graph","created_at":"2026-07-05T10:49:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.10804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David M. Blei, Dhanya Sridhar, Gemma E. Moran, Yixin Wang","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-20T22:11:33Z","title":"Identifiable Deep Generative Models via Sparse Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10804","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:260a57251ad934276f49d95a264de40faac54d591fa0d418f0cb30fe93611bfb","target":"record","created_at":"2026-07-05T10:49:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2cfd27f90959772c05c11fc4d65084cbd92599d8c60896068046832fe9125b2f","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-20T22:11:33Z","title_canon_sha256":"1e8a2e8057feb7fc2c73289faf9bdf02c49f477f32271139d0069af9867657bf"},"schema_version":"1.0","source":{"id":"2110.10804","kind":"arxiv","version":2}},"canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"988d6edb4129db4a12452177cd9cb0d92a21b54ac55275520318aab6866f3883","first_computed_at":"2026-07-05T10:49:01.581233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:01.581233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4urm6dnJ4Jvc/YF7CEoPasnnjoeL06SU2FLkfd2FTWO1xg51TvlMNINx6YTvuZdw156d35yrcUQqxxEzDwQXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:01.581741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10804","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:260a57251ad934276f49d95a264de40faac54d591fa0d418f0cb30fe93611bfb","sha256:c4de9bd13f8de8e2e1d25b6e7722fb9e942cd34b0837ec3d044d08f61e4a6ebe"],"state_sha256":"996362ac60965b7f0f4900cba39052ca6defbfcac1cd5b3afe0d92df9c885f23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osJ9bZyVCuwWl+2gHle1DYcZvAQFV3Wl3o/irEjgI+s80KnBRokwV6PZ5Yh4jCSzMYqadZ+ZpCVpGWj906PaDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:35:20.483250Z","bundle_sha256":"95bced2e61d785e0dd70930491d1c25f5359d0a33d79934a370f419a25a487a8"}}