{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SYZQALW2O2J5X3P6HRS5Z4LSW6","short_pith_number":"pith:SYZQALW2","schema_version":"1.0","canonical_sha256":"9633002eda7693dbedfe3c65dcf172b7b1e8ba913ea3c7ec53db6498a78b31b0","source":{"kind":"arxiv","id":"2206.08492","version":1},"attestation_state":"computed","paper":{"title":"TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Shlizerman, Jinlin Xiang","submitted_at":"2022-06-17T00:20:54Z","abstract_excerpt":"When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a memory of a few exemplars from previously learned tasks, and distilling knowledge from them. However, existing methods struggle to balance the performance across classes since they typically overfit the model to the latest task. In our work, we propose to address these challenges with the introduction of a novel methodology of Tangent Kernel for Incremental"},"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":"2206.08492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T00:20:54Z","cross_cats_sorted":["cs.AI","q-bio.NC","stat.ML"],"title_canon_sha256":"d0c6896037b14826b3cbb2dbb4498e329203f9b0edfb0ee5d6dc9e4060a1957c","abstract_canon_sha256":"a645d67cb90900d9a2735a62fdde72460b5f88df81d87efede53fb9fd1a8596d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:30.263397Z","signature_b64":"KFQWjoHBxYfY96w+Vkdast3qpp3scyzomYE4gLsJjMMs29dOQANxvmU/O/wOf43iSHI6lQz+yyFosvqU6j3JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9633002eda7693dbedfe3c65dcf172b7b1e8ba913ea3c7ec53db6498a78b31b0","last_reissued_at":"2026-07-05T04:32:30.262928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:30.262928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Shlizerman, Jinlin Xiang","submitted_at":"2022-06-17T00:20:54Z","abstract_excerpt":"When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a memory of a few exemplars from previously learned tasks, and distilling knowledge from them. However, existing methods struggle to balance the performance across classes since they typically overfit the model to the latest task. In our work, we propose to address these challenges with the introduction of a novel methodology of Tangent Kernel for Incremental"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08492","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/2206.08492/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":"2206.08492","created_at":"2026-07-05T04:32:30.262985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08492v1","created_at":"2026-07-05T04:32:30.262985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08492","created_at":"2026-07-05T04:32:30.262985+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYZQALW2O2J5","created_at":"2026-07-05T04:32:30.262985+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYZQALW2O2J5X3P6","created_at":"2026-07-05T04:32:30.262985+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYZQALW2","created_at":"2026-07-05T04:32:30.262985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.08109","citing_title":"Advantages of Broadband Metalenses for Generalizable Image Classification","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6","json":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6.json","graph_json":"https://pith.science/api/pith-number/SYZQALW2O2J5X3P6HRS5Z4LSW6/graph.json","events_json":"https://pith.science/api/pith-number/SYZQALW2O2J5X3P6HRS5Z4LSW6/events.json","paper":"https://pith.science/paper/SYZQALW2"},"agent_actions":{"view_html":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6","download_json":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6.json","view_paper":"https://pith.science/paper/SYZQALW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08492&json=true","fetch_graph":"https://pith.science/api/pith-number/SYZQALW2O2J5X3P6HRS5Z4LSW6/graph.json","fetch_events":"https://pith.science/api/pith-number/SYZQALW2O2J5X3P6HRS5Z4LSW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6/action/storage_attestation","attest_author":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6/action/author_attestation","sign_citation":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6/action/citation_signature","submit_replication":"https://pith.science/pith/SYZQALW2O2J5X3P6HRS5Z4LSW6/action/replication_record"}},"created_at":"2026-07-05T04:32:30.262985+00:00","updated_at":"2026-07-05T04:32:30.262985+00:00"}