{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TSOYFVKST7OAN27ARIQPNIUSMW","short_pith_number":"pith:TSOYFVKS","schema_version":"1.0","canonical_sha256":"9c9d82d5529fdc06ebe08a20f6a292659d06ca22ff3871743c77b43b60eff1d4","source":{"kind":"arxiv","id":"1807.08919","version":1},"attestation_state":"computed","paper":{"title":"The Variational Homoencoder: Learning to learn high capacity generative models from few examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreea Gane, Joshua B. Tenenbaum, Luke B. Hewitt, Maxwell I. Nye, Tommi Jaakkola","submitted_at":"2018-07-24T06:05:43Z","abstract_excerpt":"Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class. This technique, which we call a Variational Homoencoder (VHE), produces a hier"},"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":"1807.08919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T06:05:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f75b9e4bc0db158eb679c7423ecf984615c5ddf1c02eb9be6b17f1b6d8122c10","abstract_canon_sha256":"b68de26f9eaa7aaabe830fdbf23734ad4236d244f0adffb7aa6233806925e9f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:57.417930Z","signature_b64":"OPAlHHT0xPWTsCcfEUDA/eHUuhrXh2b3xo9VflABEZdgPhlfmW/6a27c+0jY83Wb6lVKTxgkSnzYV2/QeaRiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9d82d5529fdc06ebe08a20f6a292659d06ca22ff3871743c77b43b60eff1d4","last_reissued_at":"2026-05-18T00:09:57.417214Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:57.417214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Variational Homoencoder: Learning to learn high capacity generative models from few examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreea Gane, Joshua B. Tenenbaum, Luke B. Hewitt, Maxwell I. Nye, Tommi Jaakkola","submitted_at":"2018-07-24T06:05:43Z","abstract_excerpt":"Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class. This technique, which we call a Variational Homoencoder (VHE), produces a hier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.08919","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.08919","created_at":"2026-05-18T00:09:57.417329+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.08919v1","created_at":"2026-05-18T00:09:57.417329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.08919","created_at":"2026-05-18T00:09:57.417329+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSOYFVKST7OA","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSOYFVKST7OAN27A","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSOYFVKS","created_at":"2026-05-18T12:32:56.356000+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/TSOYFVKST7OAN27ARIQPNIUSMW","json":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW.json","graph_json":"https://pith.science/api/pith-number/TSOYFVKST7OAN27ARIQPNIUSMW/graph.json","events_json":"https://pith.science/api/pith-number/TSOYFVKST7OAN27ARIQPNIUSMW/events.json","paper":"https://pith.science/paper/TSOYFVKS"},"agent_actions":{"view_html":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW","download_json":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW.json","view_paper":"https://pith.science/paper/TSOYFVKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.08919&json=true","fetch_graph":"https://pith.science/api/pith-number/TSOYFVKST7OAN27ARIQPNIUSMW/graph.json","fetch_events":"https://pith.science/api/pith-number/TSOYFVKST7OAN27ARIQPNIUSMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW/action/storage_attestation","attest_author":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW/action/author_attestation","sign_citation":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW/action/citation_signature","submit_replication":"https://pith.science/pith/TSOYFVKST7OAN27ARIQPNIUSMW/action/replication_record"}},"created_at":"2026-05-18T00:09:57.417329+00:00","updated_at":"2026-05-18T00:09:57.417329+00:00"}