{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BYTP55TZUOU2ICY32DMVF2JCXC","short_pith_number":"pith:BYTP55TZ","schema_version":"1.0","canonical_sha256":"0e26fef679a3a9a40b1bd0d952e922b89c12ceac1785f7dd400b3d2fc409cda6","source":{"kind":"arxiv","id":"1611.06194","version":2},"attestation_state":"computed","paper":{"title":"Expert Gate: Lifelong Learning with a Network of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Punarjay Chakravarty, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2016-11-18T18:50:15Z","abstract_excerpt":"In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far, relates to the decision which expert to deploy at test time. We introduce a set of gating autoencoders that learn a representation for the task at hand, and, at test time, automatically forward the t"},"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":"1611.06194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-18T18:50:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bbe3a819f1b54084d6d512491e7115bdbc2f42b2a96c927f408d102b47375a7f","abstract_canon_sha256":"70e607defba09b266e8fd3bff6d6ea32efbf0d8e0e7647713729f91e364c188b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:07.841413Z","signature_b64":"GPeH21R3b1qFTvbx0WIzXYLsHmUbJ3j94Y6daVuCVS+0G8QrGXd5GlJeLSMwtsaMAISX5rqGZIWuLOR9KB4MDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e26fef679a3a9a40b1bd0d952e922b89c12ceac1785f7dd400b3d2fc409cda6","last_reissued_at":"2026-05-18T00:46:07.840914Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:07.840914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expert Gate: Lifelong Learning with a Network of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Punarjay Chakravarty, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2016-11-18T18:50:15Z","abstract_excerpt":"In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far, relates to the decision which expert to deploy at test time. We introduce a set of gating autoencoders that learn a representation for the task at hand, and, at test time, automatically forward the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06194","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":"1611.06194","created_at":"2026-05-18T00:46:07.841008+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06194v2","created_at":"2026-05-18T00:46:07.841008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06194","created_at":"2026-05-18T00:46:07.841008+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYTP55TZUOU2","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYTP55TZUOU2ICY3","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYTP55TZ","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1701.06538","citing_title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC","json":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC.json","graph_json":"https://pith.science/api/pith-number/BYTP55TZUOU2ICY32DMVF2JCXC/graph.json","events_json":"https://pith.science/api/pith-number/BYTP55TZUOU2ICY32DMVF2JCXC/events.json","paper":"https://pith.science/paper/BYTP55TZ"},"agent_actions":{"view_html":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC","download_json":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC.json","view_paper":"https://pith.science/paper/BYTP55TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06194&json=true","fetch_graph":"https://pith.science/api/pith-number/BYTP55TZUOU2ICY32DMVF2JCXC/graph.json","fetch_events":"https://pith.science/api/pith-number/BYTP55TZUOU2ICY32DMVF2JCXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC/action/storage_attestation","attest_author":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC/action/author_attestation","sign_citation":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC/action/citation_signature","submit_replication":"https://pith.science/pith/BYTP55TZUOU2ICY32DMVF2JCXC/action/replication_record"}},"created_at":"2026-05-18T00:46:07.841008+00:00","updated_at":"2026-05-18T00:46:07.841008+00:00"}