{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WPBIVG3Q5VRMW76XV3QA2T6VAX","short_pith_number":"pith:WPBIVG3Q","schema_version":"1.0","canonical_sha256":"b3c28a9b70ed62cb7fd7aee00d4fd505fc5396ac87aac5ff6dff0ff40c8573f6","source":{"kind":"arxiv","id":"1812.10539","version":3},"attestation_state":"computed","paper":{"title":"Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Aditya Grover, Stefano Ermon","submitted_at":"2018-12-26T21:14:06Z","abstract_excerpt":"Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional projections as noisy latent representations of an autoencoder and directly learn both the acquisition (i.e., encoding) and amortized recovery (i.e., decoding) procedures. Our learning objective optimizes for a tractable variational lower bound to the mutual information between th"},"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":"1812.10539","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-26T21:14:06Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e3c22192b68417f5a6359671fb5f09fefe74d81b8311b5302a3b2321b3fd4c71","abstract_canon_sha256":"b7cf69761f601229a0b05745ca3e6d3290b6eba7a98e01575d6626a73b993fe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:45.266335Z","signature_b64":"EY8F5CcBijAan7bjDAM9bZUlyDG+fnARWMa3APTfOksOEkdfl2yOjm5eUXQNlFHr7vkZOp8hAUFo6DJfEqfbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3c28a9b70ed62cb7fd7aee00d4fd505fc5396ac87aac5ff6dff0ff40c8573f6","last_reissued_at":"2026-05-17T23:48:45.265850Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:45.265850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Aditya Grover, Stefano Ermon","submitted_at":"2018-12-26T21:14:06Z","abstract_excerpt":"Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional projections as noisy latent representations of an autoencoder and directly learn both the acquisition (i.e., encoding) and amortized recovery (i.e., decoding) procedures. Our learning objective optimizes for a tractable variational lower bound to the mutual information between th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10539","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":"1812.10539","created_at":"2026-05-17T23:48:45.265924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10539v3","created_at":"2026-05-17T23:48:45.265924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10539","created_at":"2026-05-17T23:48:45.265924+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPBIVG3Q5VRM","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPBIVG3Q5VRMW76X","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPBIVG3Q","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":239,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX","json":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX.json","graph_json":"https://pith.science/api/pith-number/WPBIVG3Q5VRMW76XV3QA2T6VAX/graph.json","events_json":"https://pith.science/api/pith-number/WPBIVG3Q5VRMW76XV3QA2T6VAX/events.json","paper":"https://pith.science/paper/WPBIVG3Q"},"agent_actions":{"view_html":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX","download_json":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX.json","view_paper":"https://pith.science/paper/WPBIVG3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10539&json=true","fetch_graph":"https://pith.science/api/pith-number/WPBIVG3Q5VRMW76XV3QA2T6VAX/graph.json","fetch_events":"https://pith.science/api/pith-number/WPBIVG3Q5VRMW76XV3QA2T6VAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX/action/storage_attestation","attest_author":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX/action/author_attestation","sign_citation":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX/action/citation_signature","submit_replication":"https://pith.science/pith/WPBIVG3Q5VRMW76XV3QA2T6VAX/action/replication_record"}},"created_at":"2026-05-17T23:48:45.265924+00:00","updated_at":"2026-05-17T23:48:45.265924+00:00"}