{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3VTDJFTSZ7WNALDEGI54FMKSYK","short_pith_number":"pith:3VTDJFTS","schema_version":"1.0","canonical_sha256":"dd66349672cfecd02c64323bc2b152c2a358c86c794d4e0c4a21fbb277223c32","source":{"kind":"arxiv","id":"2002.06715","version":2},"attestation_state":"computed","paper":{"title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dustin Tran, Jimmy Ba, Yeming Wen","submitted_at":"2020-02-17T00:00:59Z","abstract_excerpt":"Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an ensemble's cost for both training and testing increases linearly with the number of networks, which quickly becomes untenable.\n  In this paper, we propose BatchEnsemble, an ensemble method whose computational and memory costs are significantly lower than typical ensembles. BatchEnsemble achieves this by defining each weight matrix to be the Hadamard product"},"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":"2002.06715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T00:00:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4fbcd10e614b5614c0cce4adca4be521c61f2a4d961012064761322993a40dae","abstract_canon_sha256":"806d2b4fd40eb3f7c91ae5bde096aadbb60d0da271bb461a1cbbf66116da50f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:34.472279Z","signature_b64":"1sR8x28dpL7STlqBfia3m4uH60MLBNzbFOS/F9LFyAudISMoxPA7KkV7T/z5teQwbbzyxQra0OA8gR1EN4QNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd66349672cfecd02c64323bc2b152c2a358c86c794d4e0c4a21fbb277223c32","last_reissued_at":"2026-07-05T00:42:34.471871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:34.471871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dustin Tran, Jimmy Ba, Yeming Wen","submitted_at":"2020-02-17T00:00:59Z","abstract_excerpt":"Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an ensemble's cost for both training and testing increases linearly with the number of networks, which quickly becomes untenable.\n  In this paper, we propose BatchEnsemble, an ensemble method whose computational and memory costs are significantly lower than typical ensembles. BatchEnsemble achieves this by defining each weight matrix to be the Hadamard product"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06715","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.06715/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":"2002.06715","created_at":"2026-07-05T00:42:34.471923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06715v2","created_at":"2026-07-05T00:42:34.471923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06715","created_at":"2026-07-05T00:42:34.471923+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VTDJFTSZ7WN","created_at":"2026-07-05T00:42:34.471923+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VTDJFTSZ7WNALDE","created_at":"2026-07-05T00:42:34.471923+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VTDJFTS","created_at":"2026-07-05T00:42:34.471923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12961","citing_title":"Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12961","citing_title":"Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK","json":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK.json","graph_json":"https://pith.science/api/pith-number/3VTDJFTSZ7WNALDEGI54FMKSYK/graph.json","events_json":"https://pith.science/api/pith-number/3VTDJFTSZ7WNALDEGI54FMKSYK/events.json","paper":"https://pith.science/paper/3VTDJFTS"},"agent_actions":{"view_html":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK","download_json":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK.json","view_paper":"https://pith.science/paper/3VTDJFTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06715&json=true","fetch_graph":"https://pith.science/api/pith-number/3VTDJFTSZ7WNALDEGI54FMKSYK/graph.json","fetch_events":"https://pith.science/api/pith-number/3VTDJFTSZ7WNALDEGI54FMKSYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK/action/storage_attestation","attest_author":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK/action/author_attestation","sign_citation":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK/action/citation_signature","submit_replication":"https://pith.science/pith/3VTDJFTSZ7WNALDEGI54FMKSYK/action/replication_record"}},"created_at":"2026-07-05T00:42:34.471923+00:00","updated_at":"2026-07-05T00:42:34.471923+00:00"}