{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UDKJVMBEY33TFZORZ7N52SSK5W","short_pith_number":"pith:UDKJVMBE","schema_version":"1.0","canonical_sha256":"a0d49ab024c6f732e5d1cfdbdd4a4aeda9db4834b4d4a28a8b4aafe7c884fac9","source":{"kind":"arxiv","id":"2403.10859","version":1},"attestation_state":"computed","paper":{"title":"Neural-Kernel Conditional Mean Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dino Sejdinovic, Eiki Shimizu, Kenji Fukumizu","submitted_at":"2024-03-16T08:51:02Z","abstract_excerpt":"Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines the strengths of deep learning with CMEs in order to address these challenges. Specifically, our approach leverages the end-to-end neural network (NN) optimization framework using a kernel-based objective. This design circumvents the computationally expensive Gram matrix inversion required by current CME methods. To further enhance performance, we provide eff"},"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":"2403.10859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-16T08:51:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cfbc3c42205bb9100333392fdef41e094588db47a957216ecde884f14a66790d","abstract_canon_sha256":"b010ca51168ee5b3669c472f556c746d4d3f6c2dd8360195b248198fe30d8b52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:08.211474Z","signature_b64":"7GE/8Hq1FW2DTwbNGbUyPWE32xZ/uTKyEYctbh++JQAPiWH3R2g8xuIny0rgVIL88apa3It9c0aDRuW/vHflAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d49ab024c6f732e5d1cfdbdd4a4aeda9db4834b4d4a28a8b4aafe7c884fac9","last_reissued_at":"2026-07-05T07:57:08.211023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:08.211023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Kernel Conditional Mean Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dino Sejdinovic, Eiki Shimizu, Kenji Fukumizu","submitted_at":"2024-03-16T08:51:02Z","abstract_excerpt":"Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines the strengths of deep learning with CMEs in order to address these challenges. Specifically, our approach leverages the end-to-end neural network (NN) optimization framework using a kernel-based objective. This design circumvents the computationally expensive Gram matrix inversion required by current CME methods. To further enhance performance, we provide eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10859","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.10859/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2403.10859","created_at":"2026-07-05T07:57:08.211080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10859v1","created_at":"2026-07-05T07:57:08.211080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10859","created_at":"2026-07-05T07:57:08.211080+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDKJVMBEY33T","created_at":"2026-07-05T07:57:08.211080+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDKJVMBEY33TFZOR","created_at":"2026-07-05T07:57:08.211080+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDKJVMBE","created_at":"2026-07-05T07:57:08.211080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07947","citing_title":"Bayesian Global Fr\\'echet Regression via Weak Conditional Expectations","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W","json":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W.json","graph_json":"https://pith.science/api/pith-number/UDKJVMBEY33TFZORZ7N52SSK5W/graph.json","events_json":"https://pith.science/api/pith-number/UDKJVMBEY33TFZORZ7N52SSK5W/events.json","paper":"https://pith.science/paper/UDKJVMBE"},"agent_actions":{"view_html":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W","download_json":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W.json","view_paper":"https://pith.science/paper/UDKJVMBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10859&json=true","fetch_graph":"https://pith.science/api/pith-number/UDKJVMBEY33TFZORZ7N52SSK5W/graph.json","fetch_events":"https://pith.science/api/pith-number/UDKJVMBEY33TFZORZ7N52SSK5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W/action/storage_attestation","attest_author":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W/action/author_attestation","sign_citation":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W/action/citation_signature","submit_replication":"https://pith.science/pith/UDKJVMBEY33TFZORZ7N52SSK5W/action/replication_record"}},"created_at":"2026-07-05T07:57:08.211080+00:00","updated_at":"2026-07-05T07:57:08.211080+00:00"}