{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:Z6GRZY2R26DV35J5ALHBBHS54Q","short_pith_number":"pith:Z6GRZY2R","schema_version":"1.0","canonical_sha256":"cf8d1ce351d7875df53d02ce109e5de428ad7bbcde3c47a12f497683574c14b5","source":{"kind":"arxiv","id":"1401.4082","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Backpropagation and Approximate Inference in Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Daan Wierstra, Danilo Jimenez Rezende, Shakir Mohamed","submitted_at":"2014-01-16T16:33:23Z","abstract_excerpt":"We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as a stochastic encoder of the data. We develop stochastic back-propagation -- rules for back-propagation through stochastic variables -- and use this to develop an algorithm that allows for joint optimisation of the parameters of both the generative and recognition model. We demon"},"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":"1401.4082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-01-16T16:33:23Z","cross_cats_sorted":["cs.AI","cs.LG","stat.CO","stat.ME"],"title_canon_sha256":"09173ac70b6dc9cc3aa914d02fd1604754ab90532416983cae5ffd956c87ed65","abstract_canon_sha256":"5c49591e0fbbd260527d7cd09d25cc3ecd0ff1c7aecd1a7112cc95a162974847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:50.296722Z","signature_b64":"PsRLLHVTpiAPS9pg9DT0+hyapZunF7YUtBVgFrK9QamrD8PHM0zhqUMvftqjnSXVxcune6ZEJBEzFhFkIgzrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf8d1ce351d7875df53d02ce109e5de428ad7bbcde3c47a12f497683574c14b5","last_reissued_at":"2026-05-18T02:50:50.296105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:50.296105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Backpropagation and Approximate Inference in Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Daan Wierstra, Danilo Jimenez Rezende, Shakir Mohamed","submitted_at":"2014-01-16T16:33:23Z","abstract_excerpt":"We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as a stochastic encoder of the data. We develop stochastic back-propagation -- rules for back-propagation through stochastic variables -- and use this to develop an algorithm that allows for joint optimisation of the parameters of both the generative and recognition model. We demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.4082","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":""},"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":"1401.4082","created_at":"2026-05-18T02:50:50.296201+00:00"},{"alias_kind":"arxiv_version","alias_value":"1401.4082v3","created_at":"2026-05-18T02:50:50.296201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.4082","created_at":"2026-05-18T02:50:50.296201+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6GRZY2R26DV","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6GRZY2R26DV35J5","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6GRZY2R","created_at":"2026-05-18T12:28:59.999130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.08972","citing_title":"A Deep Generative Model for Code-Switched Text","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08040","citing_title":"Convolutional Reservoir Computing for World Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02502","citing_title":"Denoising Diffusion Implicit Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15451","citing_title":"Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1410.8516","citing_title":"NICE: Non-linear Independent Components Estimation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11870","citing_title":"Information theoretic underpinning of self-supervised learning by clustering","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"1406.2661","citing_title":"Generative Adversarial Networks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"1611.01144","citing_title":"Categorical Reparameterization with Gumbel-Softmax","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11653","citing_title":"GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2308.00352","citing_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06100","citing_title":"CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q","json":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q.json","graph_json":"https://pith.science/api/pith-number/Z6GRZY2R26DV35J5ALHBBHS54Q/graph.json","events_json":"https://pith.science/api/pith-number/Z6GRZY2R26DV35J5ALHBBHS54Q/events.json","paper":"https://pith.science/paper/Z6GRZY2R"},"agent_actions":{"view_html":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q","download_json":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q.json","view_paper":"https://pith.science/paper/Z6GRZY2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1401.4082&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6GRZY2R26DV35J5ALHBBHS54Q/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6GRZY2R26DV35J5ALHBBHS54Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q/action/storage_attestation","attest_author":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q/action/author_attestation","sign_citation":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q/action/citation_signature","submit_replication":"https://pith.science/pith/Z6GRZY2R26DV35J5ALHBBHS54Q/action/replication_record"}},"created_at":"2026-05-18T02:50:50.296201+00:00","updated_at":"2026-05-18T02:50:50.296201+00:00"}