{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YHDXJ7PNSWCLSA4RHEHCT27P4H","short_pith_number":"pith:YHDXJ7PN","canonical_record":{"source":{"id":"1812.06190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T22:10:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2d4893d3e64bafe3e69b23b486e18238dea03c43648e9781b73f9d804ce50721","abstract_canon_sha256":"f57f23b855b4581eb7cf75d2d39680e9c4db580a81f59e200abd59523af6609d"},"schema_version":"1.0"},"canonical_sha256":"c1c774fded9584b90391390e29ebefe1c024816751a90ba702d0a192106987b8","source":{"kind":"arxiv","id":"1812.06190","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06190","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06190v1","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06190","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"pith_short_12","alias_value":"YHDXJ7PNSWCL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YHDXJ7PNSWCLSA4R","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YHDXJ7PN","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YHDXJ7PNSWCLSA4RHEHCT27P4H","target":"record","payload":{"canonical_record":{"source":{"id":"1812.06190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T22:10:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2d4893d3e64bafe3e69b23b486e18238dea03c43648e9781b73f9d804ce50721","abstract_canon_sha256":"f57f23b855b4581eb7cf75d2d39680e9c4db580a81f59e200abd59523af6609d"},"schema_version":"1.0"},"canonical_sha256":"c1c774fded9584b90391390e29ebefe1c024816751a90ba702d0a192106987b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:12.919820Z","signature_b64":"h2ZUzPB5qlLIa6mEEbESnI8xbFdhZeaEOVtU3bmUlmbkzUATBpz+Gnjmk8qp4wHEk7ZkyEj4jz/1uEpXHK4IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1c774fded9584b90391390e29ebefe1c024816751a90ba702d0a192106987b8","last_reissued_at":"2026-05-17T23:58:12.919230Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:12.919230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.06190","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1b87DeiVj/hvvMGK0RTFE71MlyRD1W/XqhdmZSxBpFzL2l+IHME4dH3iyskp+9DENuhmdmkECkk/Uj/bZdpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:57:53.780130Z"},"content_sha256":"b397becc8ae32a65f947e35bdae9fa72ef1d9a51a6d425c54378551ceb6cf4b4","schema_version":"1.0","event_id":"sha256:b397becc8ae32a65f947e35bdae9fa72ef1d9a51a6d425c54378551ceb6cf4b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YHDXJ7PNSWCLSA4RHEHCT27P4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Latent Subspaces in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack Klys, Jake Snell, Richard Zemel","submitted_at":"2018-12-14T22:10:50Z","abstract_excerpt":"Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06190","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":""},"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":"2026-05-17T23:58:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7UtImZ/TT9+A1H0WTL7lxN8vZES0jnz2eVP8zmbVbUt7w7CKAMeeriixRWecoBuwOQuG5VZqIP4UfYPSfyXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:57:53.780499Z"},"content_sha256":"91446e662daf6c98e43bcd5facf44255ce6d54751d1b68a5405fbf85d97dc353","schema_version":"1.0","event_id":"sha256:91446e662daf6c98e43bcd5facf44255ce6d54751d1b68a5405fbf85d97dc353"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/bundle.json","state_url":"https://pith.science/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/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":"2026-06-05T10:57:53Z","links":{"resolver":"https://pith.science/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H","bundle":"https://pith.science/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/bundle.json","state":"https://pith.science/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHDXJ7PNSWCLSA4RHEHCT27P4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YHDXJ7PNSWCLSA4RHEHCT27P4H","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":"f57f23b855b4581eb7cf75d2d39680e9c4db580a81f59e200abd59523af6609d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T22:10:50Z","title_canon_sha256":"2d4893d3e64bafe3e69b23b486e18238dea03c43648e9781b73f9d804ce50721"},"schema_version":"1.0","source":{"id":"1812.06190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06190","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06190v1","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06190","created_at":"2026-05-17T23:58:12Z"},{"alias_kind":"pith_short_12","alias_value":"YHDXJ7PNSWCL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YHDXJ7PNSWCLSA4R","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YHDXJ7PN","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:91446e662daf6c98e43bcd5facf44255ce6d54751d1b68a5405fbf85d97dc353","target":"graph","created_at":"2026-05-17T23:58:12Z","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"},"paper":{"abstract_excerpt":"Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a ","authors_text":"Jack Klys, Jake Snell, Richard Zemel","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T22:10:50Z","title":"Learning Latent Subspaces in Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06190","kind":"arxiv","version":1},"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:b397becc8ae32a65f947e35bdae9fa72ef1d9a51a6d425c54378551ceb6cf4b4","target":"record","created_at":"2026-05-17T23:58:12Z","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":"f57f23b855b4581eb7cf75d2d39680e9c4db580a81f59e200abd59523af6609d","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T22:10:50Z","title_canon_sha256":"2d4893d3e64bafe3e69b23b486e18238dea03c43648e9781b73f9d804ce50721"},"schema_version":"1.0","source":{"id":"1812.06190","kind":"arxiv","version":1}},"canonical_sha256":"c1c774fded9584b90391390e29ebefe1c024816751a90ba702d0a192106987b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1c774fded9584b90391390e29ebefe1c024816751a90ba702d0a192106987b8","first_computed_at":"2026-05-17T23:58:12.919230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:12.919230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h2ZUzPB5qlLIa6mEEbESnI8xbFdhZeaEOVtU3bmUlmbkzUATBpz+Gnjmk8qp4wHEk7ZkyEj4jz/1uEpXHK4IBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:12.919820Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.06190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b397becc8ae32a65f947e35bdae9fa72ef1d9a51a6d425c54378551ceb6cf4b4","sha256:91446e662daf6c98e43bcd5facf44255ce6d54751d1b68a5405fbf85d97dc353"],"state_sha256":"ee27fa4520d8c81431328bc3feb382de9579b792a7df771358e5ef02d14ea579"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Wum5IsqUpHaUkcQqUs6Jw6vs+3nA6/fttkVyKYoMnA2zozN/17vOTVX5TuY3DSOW90xGj/6QfiWduNYktEBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T10:57:53.782726Z","bundle_sha256":"8bdd949006f3e85cfcea50c46ae7dbb5edda6552a12b125c7ec2ccc260ae9353"}}