{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PRGLMJPGUSCJHWOSENBJ7UN2ZY","short_pith_number":"pith:PRGLMJPG","schema_version":"1.0","canonical_sha256":"7c4cb625e6a48493d9d223429fd1bace34ffa7bf0525de9c694b38d44bb94121","source":{"kind":"arxiv","id":"2106.13746","version":2},"attestation_state":"computed","paper":{"title":"On Incorporating Inductive Biases into VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emile Mathieu, Ning Miao, N. Siddharth, Tom Rainforth, Yee Whye Teh","submitted_at":"2021-06-25T16:34:05Z","abstract_excerpt":"We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs). InteL-VAEs use an intermediary set of latent variables to control the stochasticity of the encoding process, before mapping these in turn to the latent representation using a parametric function that encapsulates our desired inductive bias(es). This allows us to impose properties like sparsity or clustering on learned representations, and incorporate human knowl"},"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":"2106.13746","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-25T16:34:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c6de465de7bf674e21577ff68554b547f0a1f5a4ab1ea35f89212287dca1570","abstract_canon_sha256":"2afee74a012106495b7733e725f846419556afe67ae409e53f409a60f675ab17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:47.433676Z","signature_b64":"B7owp3+67uT3WkZswPC1uksTLXeASP/sQFEMe4A9xtzD+9S/+VCfUHuM4zBVe6ZQylfek2dHh77a3Jw3N8CYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c4cb625e6a48493d9d223429fd1bace34ffa7bf0525de9c694b38d44bb94121","last_reissued_at":"2026-07-05T03:56:47.433160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:47.433160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Incorporating Inductive Biases into VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emile Mathieu, Ning Miao, N. Siddharth, Tom Rainforth, Yee Whye Teh","submitted_at":"2021-06-25T16:34:05Z","abstract_excerpt":"We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs). InteL-VAEs use an intermediary set of latent variables to control the stochasticity of the encoding process, before mapping these in turn to the latent representation using a parametric function that encapsulates our desired inductive bias(es). This allows us to impose properties like sparsity or clustering on learned representations, and incorporate human knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13746","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/2106.13746/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":"2106.13746","created_at":"2026-07-05T03:56:47.433216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13746v2","created_at":"2026-07-05T03:56:47.433216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13746","created_at":"2026-07-05T03:56:47.433216+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRGLMJPGUSCJ","created_at":"2026-07-05T03:56:47.433216+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRGLMJPGUSCJHWOS","created_at":"2026-07-05T03:56:47.433216+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRGLMJPG","created_at":"2026-07-05T03:56:47.433216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07682","citing_title":"Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":195,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY","json":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY.json","graph_json":"https://pith.science/api/pith-number/PRGLMJPGUSCJHWOSENBJ7UN2ZY/graph.json","events_json":"https://pith.science/api/pith-number/PRGLMJPGUSCJHWOSENBJ7UN2ZY/events.json","paper":"https://pith.science/paper/PRGLMJPG"},"agent_actions":{"view_html":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY","download_json":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY.json","view_paper":"https://pith.science/paper/PRGLMJPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13746&json=true","fetch_graph":"https://pith.science/api/pith-number/PRGLMJPGUSCJHWOSENBJ7UN2ZY/graph.json","fetch_events":"https://pith.science/api/pith-number/PRGLMJPGUSCJHWOSENBJ7UN2ZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY/action/storage_attestation","attest_author":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY/action/author_attestation","sign_citation":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY/action/citation_signature","submit_replication":"https://pith.science/pith/PRGLMJPGUSCJHWOSENBJ7UN2ZY/action/replication_record"}},"created_at":"2026-07-05T03:56:47.433216+00:00","updated_at":"2026-07-05T03:56:47.433216+00:00"}