{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N47FITKV3FFHSX6BLZY7WLWBRE","short_pith_number":"pith:N47FITKV","schema_version":"1.0","canonical_sha256":"6f3e544d55d94a795fc15e71fb2ec1891cc429d223c443f6695915035ee1f7dc","source":{"kind":"arxiv","id":"1806.01531","version":3},"attestation_state":"computed","paper":{"title":"Deep Mixture of Experts via Shallow Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azalia Mirhoseini, Fisher Yu, Joseph E. Gonzalez, Lisa Dunlap, Ruth Wang, Trevor Darrell, Xin Wang, Yi-An Ma","submitted_at":"2018-06-05T07:41:04Z","abstract_excerpt":"Larger networks generally have greater representational power at the cost of increased computational complexity. Sparsifying such networks has been an active area of research but has been generally limited to static regularization or dynamic approaches using reinforcement learning. We explore a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis. Our novel DeepMoE architecture increases the representational power of standard convolutional networks by adaptively sparsifying and recalibrating channel-wise features in ea"},"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":"1806.01531","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-05T07:41:04Z","cross_cats_sorted":[],"title_canon_sha256":"5988cb085c073206a7c1b9933d332c4c2e0ce65e54bd5d4dd861e66492fa67c4","abstract_canon_sha256":"87cce1dc4e9dac30302c17f5a349f43d68ab093463c2cd98cc536bd15541e462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:45.797774Z","signature_b64":"W9sRlFgTZpc8cwJsORcH6FmLX5SOgsuLipDEo2Hzqus1mEXjsb37HkZot4oLUCfnd9gN02Dww2fixEiO/c58DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3e544d55d94a795fc15e71fb2ec1891cc429d223c443f6695915035ee1f7dc","last_reissued_at":"2026-05-17T23:48:45.797305Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:45.797305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Mixture of Experts via Shallow Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azalia Mirhoseini, Fisher Yu, Joseph E. Gonzalez, Lisa Dunlap, Ruth Wang, Trevor Darrell, Xin Wang, Yi-An Ma","submitted_at":"2018-06-05T07:41:04Z","abstract_excerpt":"Larger networks generally have greater representational power at the cost of increased computational complexity. Sparsifying such networks has been an active area of research but has been generally limited to static regularization or dynamic approaches using reinforcement learning. We explore a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis. Our novel DeepMoE architecture increases the representational power of standard convolutional networks by adaptively sparsifying and recalibrating channel-wise features in ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01531","kind":"arxiv","version":3},"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":"1806.01531","created_at":"2026-05-17T23:48:45.797389+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01531v3","created_at":"2026-05-17T23:48:45.797389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01531","created_at":"2026-05-17T23:48:45.797389+00:00"},{"alias_kind":"pith_short_12","alias_value":"N47FITKV3FFH","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N47FITKV3FFHSX6B","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N47FITKV","created_at":"2026-05-18T12:32:40.477152+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/N47FITKV3FFHSX6BLZY7WLWBRE","json":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE.json","graph_json":"https://pith.science/api/pith-number/N47FITKV3FFHSX6BLZY7WLWBRE/graph.json","events_json":"https://pith.science/api/pith-number/N47FITKV3FFHSX6BLZY7WLWBRE/events.json","paper":"https://pith.science/paper/N47FITKV"},"agent_actions":{"view_html":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE","download_json":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE.json","view_paper":"https://pith.science/paper/N47FITKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01531&json=true","fetch_graph":"https://pith.science/api/pith-number/N47FITKV3FFHSX6BLZY7WLWBRE/graph.json","fetch_events":"https://pith.science/api/pith-number/N47FITKV3FFHSX6BLZY7WLWBRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE/action/storage_attestation","attest_author":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE/action/author_attestation","sign_citation":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE/action/citation_signature","submit_replication":"https://pith.science/pith/N47FITKV3FFHSX6BLZY7WLWBRE/action/replication_record"}},"created_at":"2026-05-17T23:48:45.797389+00:00","updated_at":"2026-05-17T23:48:45.797389+00:00"}