{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LBFHN52PLF5APKS5SHBXESSMEJ","short_pith_number":"pith:LBFHN52P","schema_version":"1.0","canonical_sha256":"584a76f74f597a07aa5d91c3724a4c226929efd5bbb0c1ed0f3f0863c2b939ed","source":{"kind":"arxiv","id":"1511.06072","version":1},"attestation_state":"computed","paper":{"title":"Mediated Experts for Deep Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Sebastian Agethen, Winston H. Hsu","submitted_at":"2015-11-19T07:01:36Z","abstract_excerpt":"We present a new supervised architecture termed Mediated Mixture-of-Experts (MMoE) that allows us to improve classification accuracy of Deep Convolutional Networks (DCN). Our architecture achieves this with the help of expert networks: A network is trained on a disjoint subset of a given dataset and then run in parallel to other experts during deployment. A mediator is employed if experts contradict each other. This allows our framework to naturally support incremental learning, as adding new classes requires (re-)training of the new expert only. We also propose two measures to control computa"},"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":"1511.06072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T07:01:36Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"1b3b60326b3fd26346e0c9e8c729ac992b904449ea65098b34a6249610f7a0a7","abstract_canon_sha256":"9e8887d3dc70deff54a791a8c93d2f1bd0c7b1e0d2e4cdf61ed80fd58657b375"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:26.326744Z","signature_b64":"TZ9NJ6jtXIkefotj81uK5/ZdTtz5FIey5oZUaAXNmDk6b9R5M2PTQdU3/YSMCbao8Diq8eI7xOmcwFfoaTYqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584a76f74f597a07aa5d91c3724a4c226929efd5bbb0c1ed0f3f0863c2b939ed","last_reissued_at":"2026-05-18T01:26:26.326390Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:26.326390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mediated Experts for Deep Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Sebastian Agethen, Winston H. Hsu","submitted_at":"2015-11-19T07:01:36Z","abstract_excerpt":"We present a new supervised architecture termed Mediated Mixture-of-Experts (MMoE) that allows us to improve classification accuracy of Deep Convolutional Networks (DCN). Our architecture achieves this with the help of expert networks: A network is trained on a disjoint subset of a given dataset and then run in parallel to other experts during deployment. A mediator is employed if experts contradict each other. This allows our framework to naturally support incremental learning, as adding new classes requires (re-)training of the new expert only. We also propose two measures to control computa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06072","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":"1511.06072","created_at":"2026-05-18T01:26:26.326446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06072v1","created_at":"2026-05-18T01:26:26.326446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06072","created_at":"2026-05-18T01:26:26.326446+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBFHN52PLF5A","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBFHN52PLF5APKS5","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBFHN52P","created_at":"2026-05-18T12:29:29.992203+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/LBFHN52PLF5APKS5SHBXESSMEJ","json":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ.json","graph_json":"https://pith.science/api/pith-number/LBFHN52PLF5APKS5SHBXESSMEJ/graph.json","events_json":"https://pith.science/api/pith-number/LBFHN52PLF5APKS5SHBXESSMEJ/events.json","paper":"https://pith.science/paper/LBFHN52P"},"agent_actions":{"view_html":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ","download_json":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ.json","view_paper":"https://pith.science/paper/LBFHN52P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06072&json=true","fetch_graph":"https://pith.science/api/pith-number/LBFHN52PLF5APKS5SHBXESSMEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LBFHN52PLF5APKS5SHBXESSMEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ/action/storage_attestation","attest_author":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ/action/author_attestation","sign_citation":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ/action/citation_signature","submit_replication":"https://pith.science/pith/LBFHN52PLF5APKS5SHBXESSMEJ/action/replication_record"}},"created_at":"2026-05-18T01:26:26.326446+00:00","updated_at":"2026-05-18T01:26:26.326446+00:00"}