{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M3RLKC3BET7F4ARKUIB3WJ7NTD","short_pith_number":"pith:M3RLKC3B","schema_version":"1.0","canonical_sha256":"66e2b50b6124fe5e022aa203bb27ed98fc0d5a5bd8560755f77605300207ddd6","source":{"kind":"arxiv","id":"2004.00070","version":1},"attestation_state":"computed","paper":{"title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Babak Ehteshami Bejnordi, Davide Abati, Jakub Tomczak, Rita Cucchiara, Simone Calderara, Tijmen Blankevoort","submitted_at":"2020-03-31T19:35:07Z","abstract_excerpt":"Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this work, we introduce a novel framework to tackle this problem with conditional computation. We equip each convolutional layer with task-specific gating modules, selecting which filters to apply on the given input. This way, we achieve two appealing properties. Firstly, the execution patterns of the gates allow to identify and protect important filters, ensurin"},"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":"2004.00070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T19:35:07Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5f769482a2a2b8740267903ef895f8935ca5419a89f20909408ddeb31b8fa11a","abstract_canon_sha256":"68244db5cebcdae7f37471cd6b82595d186c95c419969e70e7830d754f0445b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:55.519463Z","signature_b64":"RPE4Ie5LR5ykNEufK2phTyfpIxIhZinEIKHl0AkuWXDj1D1iB7jile7v3KaB3phpzN6zN3OS+ISYmZGvfSLXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e2b50b6124fe5e022aa203bb27ed98fc0d5a5bd8560755f77605300207ddd6","last_reissued_at":"2026-07-05T00:51:55.519068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:55.519068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Babak Ehteshami Bejnordi, Davide Abati, Jakub Tomczak, Rita Cucchiara, Simone Calderara, Tijmen Blankevoort","submitted_at":"2020-03-31T19:35:07Z","abstract_excerpt":"Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this work, we introduce a novel framework to tackle this problem with conditional computation. We equip each convolutional layer with task-specific gating modules, selecting which filters to apply on the given input. This way, we achieve two appealing properties. Firstly, the execution patterns of the gates allow to identify and protect important filters, ensurin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00070","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/2004.00070/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":"2004.00070","created_at":"2026-07-05T00:51:55.519130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.00070v1","created_at":"2026-07-05T00:51:55.519130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00070","created_at":"2026-07-05T00:51:55.519130+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3RLKC3BET7F","created_at":"2026-07-05T00:51:55.519130+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3RLKC3BET7F4ARK","created_at":"2026-07-05T00:51:55.519130+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3RLKC3B","created_at":"2026-07-05T00:51:55.519130+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/M3RLKC3BET7F4ARKUIB3WJ7NTD","json":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD.json","graph_json":"https://pith.science/api/pith-number/M3RLKC3BET7F4ARKUIB3WJ7NTD/graph.json","events_json":"https://pith.science/api/pith-number/M3RLKC3BET7F4ARKUIB3WJ7NTD/events.json","paper":"https://pith.science/paper/M3RLKC3B"},"agent_actions":{"view_html":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD","download_json":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD.json","view_paper":"https://pith.science/paper/M3RLKC3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.00070&json=true","fetch_graph":"https://pith.science/api/pith-number/M3RLKC3BET7F4ARKUIB3WJ7NTD/graph.json","fetch_events":"https://pith.science/api/pith-number/M3RLKC3BET7F4ARKUIB3WJ7NTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD/action/storage_attestation","attest_author":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD/action/author_attestation","sign_citation":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD/action/citation_signature","submit_replication":"https://pith.science/pith/M3RLKC3BET7F4ARKUIB3WJ7NTD/action/replication_record"}},"created_at":"2026-07-05T00:51:55.519130+00:00","updated_at":"2026-07-05T00:51:55.519130+00:00"}