{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XAF5LBVKU5MJAHJCPE2ORFTGCI","short_pith_number":"pith:XAF5LBVK","schema_version":"1.0","canonical_sha256":"b80bd586aaa758901d227934e89666120d8c3e5f46c1ea1f2531053f06206779","source":{"kind":"arxiv","id":"2207.01036","version":1},"attestation_state":"computed","paper":{"title":"Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzhong He, Jinze Li, Shaoyun Xu, Tao Bai, Xiongkun Linghu, Yan Bai, Yihang Lou","submitted_at":"2022-07-03T13:15:45Z","abstract_excerpt":"Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem. Existing researches mainly utilize the image information, such as storing the image knowledge of previous tasks or limiting classifiers updating. However, they ignore analyzing the informative and less noisy text information of class labels. I"},"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":"2207.01036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-03T13:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"83014ccedfeeee70dd53841913d4ed1f3aef85e12f2f19067ffa2f9c5df509ad","abstract_canon_sha256":"1962eb61a370bcdfcdd77ade423dd396988a695d3dd15d5d2716f09490cae343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:55.300121Z","signature_b64":"SeoX91hk35FtP+Ryu6ulvLtTU2rgL4qkDSxW4vBO+wG3sNIZzQ7Pyo95816YbRSFCfLcuTLLacVxwSi+D+WADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b80bd586aaa758901d227934e89666120d8c3e5f46c1ea1f2531053f06206779","last_reissued_at":"2026-07-05T04:36:55.299772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:55.299772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzhong He, Jinze Li, Shaoyun Xu, Tao Bai, Xiongkun Linghu, Yan Bai, Yihang Lou","submitted_at":"2022-07-03T13:15:45Z","abstract_excerpt":"Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem. Existing researches mainly utilize the image information, such as storing the image knowledge of previous tasks or limiting classifiers updating. However, they ignore analyzing the informative and less noisy text information of class labels. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01036","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/2207.01036/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":"2207.01036","created_at":"2026-07-05T04:36:55.299833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01036v1","created_at":"2026-07-05T04:36:55.299833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01036","created_at":"2026-07-05T04:36:55.299833+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAF5LBVKU5MJ","created_at":"2026-07-05T04:36:55.299833+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAF5LBVKU5MJAHJC","created_at":"2026-07-05T04:36:55.299833+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAF5LBVK","created_at":"2026-07-05T04:36:55.299833+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/XAF5LBVKU5MJAHJCPE2ORFTGCI","json":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI.json","graph_json":"https://pith.science/api/pith-number/XAF5LBVKU5MJAHJCPE2ORFTGCI/graph.json","events_json":"https://pith.science/api/pith-number/XAF5LBVKU5MJAHJCPE2ORFTGCI/events.json","paper":"https://pith.science/paper/XAF5LBVK"},"agent_actions":{"view_html":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI","download_json":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI.json","view_paper":"https://pith.science/paper/XAF5LBVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01036&json=true","fetch_graph":"https://pith.science/api/pith-number/XAF5LBVKU5MJAHJCPE2ORFTGCI/graph.json","fetch_events":"https://pith.science/api/pith-number/XAF5LBVKU5MJAHJCPE2ORFTGCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI/action/storage_attestation","attest_author":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI/action/author_attestation","sign_citation":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI/action/citation_signature","submit_replication":"https://pith.science/pith/XAF5LBVKU5MJAHJCPE2ORFTGCI/action/replication_record"}},"created_at":"2026-07-05T04:36:55.299833+00:00","updated_at":"2026-07-05T04:36:55.299833+00:00"}