{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:56JBURRKNSUK24H4DEMZRSCB6B","short_pith_number":"pith:56JBURRK","schema_version":"1.0","canonical_sha256":"ef921a462a6ca8ad70fc191998c841f072b0b3fb9a94974910daaf540cf81aa8","source":{"kind":"arxiv","id":"2402.05797","version":2},"attestation_state":"computed","paper":{"title":"TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Linjie Li, Yang Ji, Zhenyu Wu","submitted_at":"2024-02-08T16:37:04Z","abstract_excerpt":"Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task, overlooking real-world long-tailed distributions. Therefore, Long-Tailed Class-Incremental Learning has been introduced, which trains on data where head classes have more samples than tail classes. Existing methods mainly focus on preserving representative samples from previous classes to combat catastrophic forgetting. Recently, dynamic network algorithms fr"},"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":"2402.05797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T16:37:04Z","cross_cats_sorted":[],"title_canon_sha256":"e45c37a359ba1259b2850a50b4e4b8beff809b8c24a77220ac7b535de0ae6794","abstract_canon_sha256":"b3510353a10c309d12a84ac3e15747bef500422a42d787e9c3cebd1510e3441f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:05.517065Z","signature_b64":"e2XfWPozcJQ/02zg0zoweugVmC4u9uHarNosx4lwAHgmWlcxJ8dhlAARbJ63wNbHDBNzfTE4m6wlh5SFwdVzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef921a462a6ca8ad70fc191998c841f072b0b3fb9a94974910daaf540cf81aa8","last_reissued_at":"2026-07-05T09:32:05.516599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:05.516599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Linjie Li, Yang Ji, Zhenyu Wu","submitted_at":"2024-02-08T16:37:04Z","abstract_excerpt":"Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task, overlooking real-world long-tailed distributions. Therefore, Long-Tailed Class-Incremental Learning has been introduced, which trains on data where head classes have more samples than tail classes. Existing methods mainly focus on preserving representative samples from previous classes to combat catastrophic forgetting. Recently, dynamic network algorithms fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05797","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/2402.05797/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":"2402.05797","created_at":"2026-07-05T09:32:05.516657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05797v2","created_at":"2026-07-05T09:32:05.516657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05797","created_at":"2026-07-05T09:32:05.516657+00:00"},{"alias_kind":"pith_short_12","alias_value":"56JBURRKNSUK","created_at":"2026-07-05T09:32:05.516657+00:00"},{"alias_kind":"pith_short_16","alias_value":"56JBURRKNSUK24H4","created_at":"2026-07-05T09:32:05.516657+00:00"},{"alias_kind":"pith_short_8","alias_value":"56JBURRK","created_at":"2026-07-05T09:32:05.516657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11091","citing_title":"LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B","json":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B.json","graph_json":"https://pith.science/api/pith-number/56JBURRKNSUK24H4DEMZRSCB6B/graph.json","events_json":"https://pith.science/api/pith-number/56JBURRKNSUK24H4DEMZRSCB6B/events.json","paper":"https://pith.science/paper/56JBURRK"},"agent_actions":{"view_html":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B","download_json":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B.json","view_paper":"https://pith.science/paper/56JBURRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05797&json=true","fetch_graph":"https://pith.science/api/pith-number/56JBURRKNSUK24H4DEMZRSCB6B/graph.json","fetch_events":"https://pith.science/api/pith-number/56JBURRKNSUK24H4DEMZRSCB6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B/action/storage_attestation","attest_author":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B/action/author_attestation","sign_citation":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B/action/citation_signature","submit_replication":"https://pith.science/pith/56JBURRKNSUK24H4DEMZRSCB6B/action/replication_record"}},"created_at":"2026-07-05T09:32:05.516657+00:00","updated_at":"2026-07-05T09:32:05.516657+00:00"}