{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ROCWLGIUWSSL26R36OHCE7IUL7","short_pith_number":"pith:ROCWLGIU","schema_version":"1.0","canonical_sha256":"8b85659914b4a4bd7a3bf38e227d145fdd12e1fd96e1e08e7302ffc334b24e32","source":{"kind":"arxiv","id":"2001.01578","version":2},"attestation_state":"computed","paper":{"title":"Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daeyoung Kim, Giang Nguyen, Ho-Jin Choi, Shuan Chen, Tae Joon Jun, Thao Do","submitted_at":"2020-01-06T13:49:32Z","abstract_excerpt":"Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect catastrophic forgetting in continual learning. A new method to deal with catastrophic forgetting named critical freezing is also introduced upon investigating the dilemma by Auto DeepVis. Experiments on a captioning model meticulously present how catastrophic forgetting happens, p"},"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":"2001.01578","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-01-06T13:49:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"40bf77c6541a38069382e7a2fedb6cd19e00a71ed73a3a60778a1ec1148cf102","abstract_canon_sha256":"2dce19c915c1884a185522c0d029aef3cda8a2b84f89ee11ec6f5ba3c0d13a9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:30:40.527861Z","signature_b64":"bRSxij4vGwPUyKBUzOhb7+ETJ6c76qxjLTopF7akQjbexvFzsT6IlwkXuTZ1mzjpUsOROW8bfmT6Bs7hLQWRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b85659914b4a4bd7a3bf38e227d145fdd12e1fd96e1e08e7302ffc334b24e32","last_reissued_at":"2026-07-05T00:30:40.527402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:30:40.527402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daeyoung Kim, Giang Nguyen, Ho-Jin Choi, Shuan Chen, Tae Joon Jun, Thao Do","submitted_at":"2020-01-06T13:49:32Z","abstract_excerpt":"Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect catastrophic forgetting in continual learning. A new method to deal with catastrophic forgetting named critical freezing is also introduced upon investigating the dilemma by Auto DeepVis. Experiments on a captioning model meticulously present how catastrophic forgetting happens, p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01578","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/2001.01578/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":"2001.01578","created_at":"2026-07-05T00:30:40.527460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.01578v2","created_at":"2026-07-05T00:30:40.527460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01578","created_at":"2026-07-05T00:30:40.527460+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROCWLGIUWSSL","created_at":"2026-07-05T00:30:40.527460+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROCWLGIUWSSL26R3","created_at":"2026-07-05T00:30:40.527460+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROCWLGIU","created_at":"2026-07-05T00:30:40.527460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18653","citing_title":"Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7","json":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7.json","graph_json":"https://pith.science/api/pith-number/ROCWLGIUWSSL26R36OHCE7IUL7/graph.json","events_json":"https://pith.science/api/pith-number/ROCWLGIUWSSL26R36OHCE7IUL7/events.json","paper":"https://pith.science/paper/ROCWLGIU"},"agent_actions":{"view_html":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7","download_json":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7.json","view_paper":"https://pith.science/paper/ROCWLGIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.01578&json=true","fetch_graph":"https://pith.science/api/pith-number/ROCWLGIUWSSL26R36OHCE7IUL7/graph.json","fetch_events":"https://pith.science/api/pith-number/ROCWLGIUWSSL26R36OHCE7IUL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7/action/storage_attestation","attest_author":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7/action/author_attestation","sign_citation":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7/action/citation_signature","submit_replication":"https://pith.science/pith/ROCWLGIUWSSL26R36OHCE7IUL7/action/replication_record"}},"created_at":"2026-07-05T00:30:40.527460+00:00","updated_at":"2026-07-05T00:30:40.527460+00:00"}