{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N7D6ULFVHURKVUT7O7MB4EKQFL","short_pith_number":"pith:N7D6ULFV","schema_version":"1.0","canonical_sha256":"6fc7ea2cb53d22aad27f77d81e11502ae7ed586df5f3248a381a79ec519b3c0a","source":{"kind":"arxiv","id":"1812.05069","version":1},"attestation_state":"computed","paper":{"title":"Recent Advances in Autoencoder-Based Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario Lucic, Michael Tschannen, Olivier Bachem","submitted_at":"2018-12-12T18:13:41Z","abstract_excerpt":"Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize these results we make use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features. In particular, we uncover three main mechanisms to enforce such properties, namely (i) regularizing the (approximate or aggregate) posterior distribution, (ii) factorizing the encoding and decoding distribution, or "},"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":"1812.05069","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T18:13:41Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3f39a28679da72e871427a715eeb3640e7d2f75588576ecd4d8c6e5c91f07724","abstract_canon_sha256":"34986ec235603d6290c0717af7b5b718988f17246e1f3cd3c2743f4297bf1ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:26.526988Z","signature_b64":"GCDMORs2T5DTiSjjehbIqkFww63ujed6o0UAntC2yBkr4DzBe9uh2qFL3+LHjHrIooRFjtiSDM+Wmt8zgdBPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc7ea2cb53d22aad27f77d81e11502ae7ed586df5f3248a381a79ec519b3c0a","last_reissued_at":"2026-05-17T23:58:26.526286Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:26.526286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent Advances in Autoencoder-Based Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario Lucic, Michael Tschannen, Olivier Bachem","submitted_at":"2018-12-12T18:13:41Z","abstract_excerpt":"Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize these results we make use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features. In particular, we uncover three main mechanisms to enforce such properties, namely (i) regularizing the (approximate or aggregate) posterior distribution, (ii) factorizing the encoding and decoding distribution, or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05069","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":"1812.05069","created_at":"2026-05-17T23:58:26.526412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05069v1","created_at":"2026-05-17T23:58:26.526412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05069","created_at":"2026-05-17T23:58:26.526412+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7D6ULFVHURK","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7D6ULFVHURKVUT7","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7D6ULFV","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.08652","citing_title":"Disentangling Influence: Using Disentangled Representations to Audit Model Predictions","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2510.26782","citing_title":"Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1910.04867","citing_title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05165","citing_title":"Interests Burn-down Diffusion Process for Personalized Collaborative Filtering","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL","json":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL.json","graph_json":"https://pith.science/api/pith-number/N7D6ULFVHURKVUT7O7MB4EKQFL/graph.json","events_json":"https://pith.science/api/pith-number/N7D6ULFVHURKVUT7O7MB4EKQFL/events.json","paper":"https://pith.science/paper/N7D6ULFV"},"agent_actions":{"view_html":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL","download_json":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL.json","view_paper":"https://pith.science/paper/N7D6ULFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05069&json=true","fetch_graph":"https://pith.science/api/pith-number/N7D6ULFVHURKVUT7O7MB4EKQFL/graph.json","fetch_events":"https://pith.science/api/pith-number/N7D6ULFVHURKVUT7O7MB4EKQFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL/action/storage_attestation","attest_author":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL/action/author_attestation","sign_citation":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL/action/citation_signature","submit_replication":"https://pith.science/pith/N7D6ULFVHURKVUT7O7MB4EKQFL/action/replication_record"}},"created_at":"2026-05-17T23:58:26.526412+00:00","updated_at":"2026-05-17T23:58:26.526412+00:00"}