{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QZTIUTAL6JNIOY3OP7PZUQCE2V","short_pith_number":"pith:QZTIUTAL","schema_version":"1.0","canonical_sha256":"86668a4c0bf25a87636e7fdf9a4044d56d8cc6ec1af50b898a28fd25193db31e","source":{"kind":"arxiv","id":"2302.03004","version":1},"attestation_state":"computed","paper":{"title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Haobo Yuan, Philip Torr, Xiangtai Li, Yibo Yang, Zhouchen Lin","submitted_at":"2023-02-06T18:39:40Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier prototypes trained in the prior sessions would inevitably cause a misalignment between the feature and classifier of old classes, which explains the well-known catastrophic forgetting problem. In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same clas"},"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":"2302.03004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T18:39:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"317fb4ee1edcc60e27618110f11bcaa4f739a511fb1fb92f363a9c94deee6c7e","abstract_canon_sha256":"37d875d56e428b24d46c27de5604df0871c2d99d5a40b5e4c1c3ce521b2d7684"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:09.031891Z","signature_b64":"TQIltMzbKjc99LzgfZm4eVlCoA0a5i5iwJVz88LH2E+iQG28nl1HFWsIN9v4DwTC6ok/wxOrQIXubBwSpLKiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86668a4c0bf25a87636e7fdf9a4044d56d8cc6ec1af50b898a28fd25193db31e","last_reissued_at":"2026-07-05T05:39:09.031348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:09.031348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Haobo Yuan, Philip Torr, Xiangtai Li, Yibo Yang, Zhouchen Lin","submitted_at":"2023-02-06T18:39:40Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier prototypes trained in the prior sessions would inevitably cause a misalignment between the feature and classifier of old classes, which explains the well-known catastrophic forgetting problem. In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03004","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/2302.03004/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":"2302.03004","created_at":"2026-07-05T05:39:09.031425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03004v1","created_at":"2026-07-05T05:39:09.031425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03004","created_at":"2026-07-05T05:39:09.031425+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZTIUTAL6JNI","created_at":"2026-07-05T05:39:09.031425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZTIUTAL6JNIOY3O","created_at":"2026-07-05T05:39:09.031425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZTIUTAL","created_at":"2026-07-05T05:39:09.031425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11904","citing_title":"Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V","json":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V.json","graph_json":"https://pith.science/api/pith-number/QZTIUTAL6JNIOY3OP7PZUQCE2V/graph.json","events_json":"https://pith.science/api/pith-number/QZTIUTAL6JNIOY3OP7PZUQCE2V/events.json","paper":"https://pith.science/paper/QZTIUTAL"},"agent_actions":{"view_html":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V","download_json":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V.json","view_paper":"https://pith.science/paper/QZTIUTAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03004&json=true","fetch_graph":"https://pith.science/api/pith-number/QZTIUTAL6JNIOY3OP7PZUQCE2V/graph.json","fetch_events":"https://pith.science/api/pith-number/QZTIUTAL6JNIOY3OP7PZUQCE2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V/action/storage_attestation","attest_author":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V/action/author_attestation","sign_citation":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V/action/citation_signature","submit_replication":"https://pith.science/pith/QZTIUTAL6JNIOY3OP7PZUQCE2V/action/replication_record"}},"created_at":"2026-07-05T05:39:09.031425+00:00","updated_at":"2026-07-05T05:39:09.031425+00:00"}