{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QNLWAWOSWSFXGCJ5LYFZWXDGG7","short_pith_number":"pith:QNLWAWOS","schema_version":"1.0","canonical_sha256":"83576059d2b48b73093d5e0b9b5c6637d249cd9c5606247522b301314e5a72e6","source":{"kind":"arxiv","id":"1504.00083","version":1},"attestation_state":"computed","paper":{"title":"A Theory of Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brendan van Rooyen, Robert C. Williamson","submitted_at":"2015-04-01T02:31:55Z","abstract_excerpt":"Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking is a theoretical understanding of different feature learning schemes. This work provides a theoretical framework for feature learning and then characterizes when features can be learnt in an unsupervised fashion. We also provide means to judge the quality of features via rate-distortion theory and its generalizations."},"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":"1504.00083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-04-01T02:31:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b0c7936bffbbe25f2e54122b67984132523e015e1c534f0357f1579bf1309f4","abstract_canon_sha256":"5431b254fb8bbe0796277144f185b077243b60beed4bf6cee881f40151026cb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:49.825717Z","signature_b64":"yXNcUHF58mtkHOoPtv/g8CPix2nOrR4izRZo+3jAFzpCmSm1Pt4s0UKbJzmFoVPs/wC63M96eo/4o5OODYG2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83576059d2b48b73093d5e0b9b5c6637d249cd9c5606247522b301314e5a72e6","last_reissued_at":"2026-05-18T02:19:49.825077Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:49.825077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theory of Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brendan van Rooyen, Robert C. Williamson","submitted_at":"2015-04-01T02:31:55Z","abstract_excerpt":"Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking is a theoretical understanding of different feature learning schemes. This work provides a theoretical framework for feature learning and then characterizes when features can be learnt in an unsupervised fashion. We also provide means to judge the quality of features via rate-distortion theory and its generalizations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.00083","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":"1504.00083","created_at":"2026-05-18T02:19:49.825170+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.00083v1","created_at":"2026-05-18T02:19:49.825170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00083","created_at":"2026-05-18T02:19:49.825170+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNLWAWOSWSFX","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNLWAWOSWSFXGCJ5","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNLWAWOS","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7","json":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7.json","graph_json":"https://pith.science/api/pith-number/QNLWAWOSWSFXGCJ5LYFZWXDGG7/graph.json","events_json":"https://pith.science/api/pith-number/QNLWAWOSWSFXGCJ5LYFZWXDGG7/events.json","paper":"https://pith.science/paper/QNLWAWOS"},"agent_actions":{"view_html":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7","download_json":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7.json","view_paper":"https://pith.science/paper/QNLWAWOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.00083&json=true","fetch_graph":"https://pith.science/api/pith-number/QNLWAWOSWSFXGCJ5LYFZWXDGG7/graph.json","fetch_events":"https://pith.science/api/pith-number/QNLWAWOSWSFXGCJ5LYFZWXDGG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7/action/storage_attestation","attest_author":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7/action/author_attestation","sign_citation":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7/action/citation_signature","submit_replication":"https://pith.science/pith/QNLWAWOSWSFXGCJ5LYFZWXDGG7/action/replication_record"}},"created_at":"2026-05-18T02:19:49.825170+00:00","updated_at":"2026-05-18T02:19:49.825170+00:00"}