{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LTSGT37XDAJC6VJQIW3S2XHONM","short_pith_number":"pith:LTSGT37X","schema_version":"1.0","canonical_sha256":"5ce469eff718122f553045b72d5cee6b1f98a267e908c20a1582990a470a28d9","source":{"kind":"arxiv","id":"2412.12654","version":1},"attestation_state":"computed","paper":{"title":"CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyan Liu, Fan Lyu, Fuyuan Hu, Kaile Du, Linglan Zhao, Tao Zhou","submitted_at":"2024-12-17T08:21:46Z","abstract_excerpt":"Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples. Due to data scarcity, existing FSCIL methods resort to training a backbone with abundant base data and then keeping it frozen afterward. However, the above operation often causes the backbone to overfit to base classes while overlooking the novel ones, leading to severe confusion between them. To address this issue, we propose Class-Aware Logit Adapter (CALA). Our method involves a lightweight adapter that learns t"},"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":"2412.12654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T08:21:46Z","cross_cats_sorted":[],"title_canon_sha256":"e89f2d95df61edf97f78844a5f13a75864096e589c5bd028c93c3b449dbccdfd","abstract_canon_sha256":"39721469214e84fd73afd2463f33a56b8401f55c064168c00e2f1ed19b0a864b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:18.676250Z","signature_b64":"ZfSqbH4BAmOlndyAf/MxJ5GyO97nGstQ8BgRrO0t4iH/loJnEdEfeTSA0ePRtyrVMUS92GFOjLHeEMzbPd2HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce469eff718122f553045b72d5cee6b1f98a267e908c20a1582990a470a28d9","last_reissued_at":"2026-07-05T09:50:18.675788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:18.675788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyan Liu, Fan Lyu, Fuyuan Hu, Kaile Du, Linglan Zhao, Tao Zhou","submitted_at":"2024-12-17T08:21:46Z","abstract_excerpt":"Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples. Due to data scarcity, existing FSCIL methods resort to training a backbone with abundant base data and then keeping it frozen afterward. However, the above operation often causes the backbone to overfit to base classes while overlooking the novel ones, leading to severe confusion between them. To address this issue, we propose Class-Aware Logit Adapter (CALA). Our method involves a lightweight adapter that learns t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12654","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/2412.12654/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":"2412.12654","created_at":"2026-07-05T09:50:18.675853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12654v1","created_at":"2026-07-05T09:50:18.675853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12654","created_at":"2026-07-05T09:50:18.675853+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTSGT37XDAJC","created_at":"2026-07-05T09:50:18.675853+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTSGT37XDAJC6VJQ","created_at":"2026-07-05T09:50:18.675853+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTSGT37X","created_at":"2026-07-05T09:50:18.675853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23237","citing_title":"Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM","json":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM.json","graph_json":"https://pith.science/api/pith-number/LTSGT37XDAJC6VJQIW3S2XHONM/graph.json","events_json":"https://pith.science/api/pith-number/LTSGT37XDAJC6VJQIW3S2XHONM/events.json","paper":"https://pith.science/paper/LTSGT37X"},"agent_actions":{"view_html":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM","download_json":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM.json","view_paper":"https://pith.science/paper/LTSGT37X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12654&json=true","fetch_graph":"https://pith.science/api/pith-number/LTSGT37XDAJC6VJQIW3S2XHONM/graph.json","fetch_events":"https://pith.science/api/pith-number/LTSGT37XDAJC6VJQIW3S2XHONM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM/action/storage_attestation","attest_author":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM/action/author_attestation","sign_citation":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM/action/citation_signature","submit_replication":"https://pith.science/pith/LTSGT37XDAJC6VJQIW3S2XHONM/action/replication_record"}},"created_at":"2026-07-05T09:50:18.675853+00:00","updated_at":"2026-07-05T09:50:18.675853+00:00"}