{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:S6ZCNJLXS5ZBPJGAL2TUU3EHTY","short_pith_number":"pith:S6ZCNJLX","schema_version":"1.0","canonical_sha256":"97b226a577977217a4c05ea74a6c879e2f1a3e306c2a65e87368ba3330cec4da","source":{"kind":"arxiv","id":"1804.03599","version":1},"attestation_state":"computed","paper":{"title":"Understanding disentangling in $\\beta$-VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Lerchner, Arka Pal, Christopher P. Burgess, Guillaume Desjardins, Irina Higgins, Loic Matthey, Nick Watters","submitted_at":"2018-04-10T15:48:18Z","abstract_excerpt":"We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in $\\beta$-VAE, as training progresses. From these insights, we propose a modification to the training regime of $\\beta$-VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robus"},"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":"1804.03599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-10T15:48:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cd831aab552a2b51ac0d24725979ba589b6df6735c02a7e03f8ce62067aa41c4","abstract_canon_sha256":"2d56257c2e65455f2fb70b0ed0e27dfd2e7163d228968c6894a22eb5c00d91f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:47.592014Z","signature_b64":"EZGwOFOhmbac0TwRD448ymU3trmdK3MZtkIpsnclmqw39EwPU2wZE4kJpOePvubHLyhNY4W8+lS8/nIr7FcdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b226a577977217a4c05ea74a6c879e2f1a3e306c2a65e87368ba3330cec4da","last_reissued_at":"2026-05-18T00:18:47.590344Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:47.590344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding disentangling in $\\beta$-VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Lerchner, Arka Pal, Christopher P. Burgess, Guillaume Desjardins, Irina Higgins, Loic Matthey, Nick Watters","submitted_at":"2018-04-10T15:48:18Z","abstract_excerpt":"We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in $\\beta$-VAE, as training progresses. From these insights, we propose a modification to the training regime of $\\beta$-VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03599","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":"1804.03599","created_at":"2026-05-18T00:18:47.590418+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.03599v1","created_at":"2026-05-18T00:18:47.590418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03599","created_at":"2026-05-18T00:18:47.590418+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6ZCNJLXS5ZB","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6ZCNJLXS5ZBPJGA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6ZCNJLX","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2505.05020","citing_title":"Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22691","citing_title":"Posterior Collapse as Automatic Spectral Pruning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22472","citing_title":"Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20732","citing_title":"Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15640","citing_title":"Learning Disentangled Representations for Generalized Multi-view Clustering","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18390","citing_title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2509.25003","citing_title":"Score-based Membership Inference on Diffusion Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08299","citing_title":"Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13933","citing_title":"Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04973","citing_title":"StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2403.19647","citing_title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25289","citing_title":"Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06261","citing_title":"Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01134","citing_title":"To Use AI as Dice of Possibilities with Timing Computation","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07940","citing_title":"A Systematic Framework for Tabular Data Disentanglement","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05513","citing_title":"From Unsupervised to Guided Clustering: A Variational Implementation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16015","citing_title":"Discovering quantum phenomena with Interpretable Machine Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16558","citing_title":"Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY","json":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY.json","graph_json":"https://pith.science/api/pith-number/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/graph.json","events_json":"https://pith.science/api/pith-number/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/events.json","paper":"https://pith.science/paper/S6ZCNJLX"},"agent_actions":{"view_html":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY","download_json":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY.json","view_paper":"https://pith.science/paper/S6ZCNJLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.03599&json=true","fetch_graph":"https://pith.science/api/pith-number/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/graph.json","fetch_events":"https://pith.science/api/pith-number/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/action/storage_attestation","attest_author":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/action/author_attestation","sign_citation":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/action/citation_signature","submit_replication":"https://pith.science/pith/S6ZCNJLXS5ZBPJGAL2TUU3EHTY/action/replication_record"}},"created_at":"2026-05-18T00:18:47.590418+00:00","updated_at":"2026-05-18T00:18:47.590418+00:00"}