{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IHIWY2USYAEYZFDV5C3CB5BRV3","short_pith_number":"pith:IHIWY2US","schema_version":"1.0","canonical_sha256":"41d16c6a92c0098c9475e8b620f431aed72504d21596c8a3134e443cbe846f37","source":{"kind":"arxiv","id":"1606.05908","version":3},"attestation_state":"computed","paper":{"title":"Tutorial on Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl Doersch","submitted_at":"2016-06-19T21:02:30Z","abstract_excerpt":"In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, and predicting the future from static images. This tutorial introduces the intuitions behind VAEs, e"},"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":"1606.05908","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-19T21:02:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe22541345b1bc6e67cb4892178752c07ed72da2266824b453fb7d142749021a","abstract_canon_sha256":"b43d818cf301981b880b59e1c323bd257df72747d3ec7b6f991aae0faa220121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:00.779100Z","signature_b64":"Zpl4+fxYY8L+GbWXM9/MylPpAxb3Dd4B7ylRY7M1ki7uulcn7lHNTtS2jc/E2/UC7O2JVzCSS+oefevVd/77DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41d16c6a92c0098c9475e8b620f431aed72504d21596c8a3134e443cbe846f37","last_reissued_at":"2026-07-05T02:04:00.778723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:00.778723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tutorial on Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Carl Doersch","submitted_at":"2016-06-19T21:02:30Z","abstract_excerpt":"In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, and predicting the future from static images. This tutorial introduces the intuitions behind VAEs, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05908","kind":"arxiv","version":3},"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/1606.05908/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":"1606.05908","created_at":"2026-07-05T02:04:00.778780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05908v3","created_at":"2026-07-05T02:04:00.778780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05908","created_at":"2026-07-05T02:04:00.778780+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHIWY2USYAEY","created_at":"2026-07-05T02:04:00.778780+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHIWY2USYAEYZFDV","created_at":"2026-07-05T02:04:00.778780+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHIWY2US","created_at":"2026-07-05T02:04:00.778780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05870","citing_title":"Cross-scale spatially-aware generative modeling of transcriptomic programs underlying neurodegenerative brain organization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05652","citing_title":"CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27562","citing_title":"A Semi-Supervised Variational Autoencoder for Generating Neutron Star Equations of State","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18931","citing_title":"Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06501","citing_title":"Enhancing Malware Detection with Generative AI: Using Variational Autoencoders to Boost Machine Learning Classifiers' Performance","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29105","citing_title":"Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"1906.09925","citing_title":"To each route its own ETA: A generative modeling framework for ETA prediction","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"1907.08259","citing_title":"WriterForcing: Generating more interesting story endings","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"1907.09574","citing_title":"LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17653","citing_title":"Drivetrain simulation using variational autoencoders","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18262","citing_title":"On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18931","citing_title":"Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17511","citing_title":"Study of jet-induced hydro response in high-energy heavy-ion collisions with a flow-matching generative model","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12642","citing_title":"Auto-encoder model for faster generation of effective one-body gravitational waveform approximations","ref_index":72,"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":164,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01066","citing_title":"A dimensional R2 regression metric","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18210","citing_title":"TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09331","citing_title":"Stability Enhanced Gaussian Process Variational Autoencoders","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2308.00352","citing_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13128","citing_title":"Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02589","citing_title":"Representation learning from OCT images","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3","json":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3.json","graph_json":"https://pith.science/api/pith-number/IHIWY2USYAEYZFDV5C3CB5BRV3/graph.json","events_json":"https://pith.science/api/pith-number/IHIWY2USYAEYZFDV5C3CB5BRV3/events.json","paper":"https://pith.science/paper/IHIWY2US"},"agent_actions":{"view_html":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3","download_json":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3.json","view_paper":"https://pith.science/paper/IHIWY2US","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05908&json=true","fetch_graph":"https://pith.science/api/pith-number/IHIWY2USYAEYZFDV5C3CB5BRV3/graph.json","fetch_events":"https://pith.science/api/pith-number/IHIWY2USYAEYZFDV5C3CB5BRV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3/action/storage_attestation","attest_author":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3/action/author_attestation","sign_citation":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3/action/citation_signature","submit_replication":"https://pith.science/pith/IHIWY2USYAEYZFDV5C3CB5BRV3/action/replication_record"}},"created_at":"2026-07-05T02:04:00.778780+00:00","updated_at":"2026-07-05T02:04:00.778780+00:00"}