{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ECDDTKEJOW6YAWFXL5ZP7RBEVY","short_pith_number":"pith:ECDDTKEJ","schema_version":"1.0","canonical_sha256":"208639a88975bd8058b75f72ffc424ae3a026c9e7755eba40a10a94e8f3c5d24","source":{"kind":"arxiv","id":"1902.02767","version":2},"attestation_state":"computed","paper":{"title":"Hybrid Models with Deep and Invertible Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Matsukawa, Balaji Lakshminarayanan, Dilan Gorur, Eric Nalisnick, Yee Whye Teh","submitted_at":"2019-02-07T18:49:47Z","abstract_excerpt":"We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets | features), the predictive distribution, can be computed exactly in a single feed-forward pass. We show that our hybrid model, despite the invertibility constraints, achieves similar accuracy to purely predictive models. Moreover the generative component remains a good model of the input features despite the hybrid optimization "},"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":"1902.02767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T18:49:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"055346c221a39f733f1318d318bcc2a8f1c6fa98495ff958091e91d515e5e330","abstract_canon_sha256":"b43cfa713d3dce1007959514f052d2729ab7bae8362b94a99dd6ad210e760f36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.581222Z","signature_b64":"+caGpftP8MUwi/S2hS861TW5jRhlNgw8A0h5w7GIP9BXyVMpm2K01Z9LTvnf29+bs+XRqFe0LS8sZjKNCE9qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208639a88975bd8058b75f72ffc424ae3a026c9e7755eba40a10a94e8f3c5d24","last_reissued_at":"2026-05-17T23:44:47.580639Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.580639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Models with Deep and Invertible Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Matsukawa, Balaji Lakshminarayanan, Dilan Gorur, Eric Nalisnick, Yee Whye Teh","submitted_at":"2019-02-07T18:49:47Z","abstract_excerpt":"We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets | features), the predictive distribution, can be computed exactly in a single feed-forward pass. We show that our hybrid model, despite the invertibility constraints, achieves similar accuracy to purely predictive models. Moreover the generative component remains a good model of the input features despite the hybrid optimization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02767","kind":"arxiv","version":2},"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":"1902.02767","created_at":"2026-05-17T23:44:47.580722+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02767v2","created_at":"2026-05-17T23:44:47.580722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02767","created_at":"2026-05-17T23:44:47.580722+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECDDTKEJOW6Y","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECDDTKEJOW6YAWFX","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECDDTKEJ","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04572","citing_title":"Out-of-Distribution Detection Using Neural Rendering Generative Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY","json":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY.json","graph_json":"https://pith.science/api/pith-number/ECDDTKEJOW6YAWFXL5ZP7RBEVY/graph.json","events_json":"https://pith.science/api/pith-number/ECDDTKEJOW6YAWFXL5ZP7RBEVY/events.json","paper":"https://pith.science/paper/ECDDTKEJ"},"agent_actions":{"view_html":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY","download_json":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY.json","view_paper":"https://pith.science/paper/ECDDTKEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02767&json=true","fetch_graph":"https://pith.science/api/pith-number/ECDDTKEJOW6YAWFXL5ZP7RBEVY/graph.json","fetch_events":"https://pith.science/api/pith-number/ECDDTKEJOW6YAWFXL5ZP7RBEVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY/action/storage_attestation","attest_author":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY/action/author_attestation","sign_citation":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY/action/citation_signature","submit_replication":"https://pith.science/pith/ECDDTKEJOW6YAWFXL5ZP7RBEVY/action/replication_record"}},"created_at":"2026-05-17T23:44:47.580722+00:00","updated_at":"2026-05-17T23:44:47.580722+00:00"}