{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3NQW5A3KQSJTKNEIA4V6OID7LX","short_pith_number":"pith:3NQW5A3K","schema_version":"1.0","canonical_sha256":"db616e836a8493353488072be7207f5dd84acd732ef34a4ac5c8bbee2f78d2ed","source":{"kind":"arxiv","id":"2412.10900","version":2},"attestation_state":"computed","paper":{"title":"PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hui Xue, Pengfei Fang, Yongchun Qin","submitted_at":"2024-12-14T17:13:30Z","abstract_excerpt":"Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. 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":"2412.10900","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T17:13:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5e806ced0399b6aec3d445aca9f7885db19c0bd3691818eefad33df98904ad00","abstract_canon_sha256":"5c4c86199d0e68df472ec80bb3d9a71b50efacb6a0c2fe49a6dcffd71ff66b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:06.559728Z","signature_b64":"lXZTJnTurAkvoGUCw0HP/au2t6bHrVlpASCAv3sVJ5nUG+mN1sm4hCE+NbVJB4XG5QzT4ubMBsEAkiLVpMIxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db616e836a8493353488072be7207f5dd84acd732ef34a4ac5c8bbee2f78d2ed","last_reissued_at":"2026-07-05T09:54:06.559229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:06.559229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hui Xue, Pengfei Fang, Yongchun Qin","submitted_at":"2024-12-14T17:13:30Z","abstract_excerpt":"Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10900","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/2412.10900/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":"2412.10900","created_at":"2026-07-05T09:54:06.559293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10900v2","created_at":"2026-07-05T09:54:06.559293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10900","created_at":"2026-07-05T09:54:06.559293+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NQW5A3KQSJT","created_at":"2026-07-05T09:54:06.559293+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NQW5A3KQSJTKNEI","created_at":"2026-07-05T09:54:06.559293+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NQW5A3K","created_at":"2026-07-05T09:54:06.559293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01533","citing_title":"Forward-Only Continual Learning","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX","json":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX.json","graph_json":"https://pith.science/api/pith-number/3NQW5A3KQSJTKNEIA4V6OID7LX/graph.json","events_json":"https://pith.science/api/pith-number/3NQW5A3KQSJTKNEIA4V6OID7LX/events.json","paper":"https://pith.science/paper/3NQW5A3K"},"agent_actions":{"view_html":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX","download_json":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX.json","view_paper":"https://pith.science/paper/3NQW5A3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10900&json=true","fetch_graph":"https://pith.science/api/pith-number/3NQW5A3KQSJTKNEIA4V6OID7LX/graph.json","fetch_events":"https://pith.science/api/pith-number/3NQW5A3KQSJTKNEIA4V6OID7LX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX/action/storage_attestation","attest_author":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX/action/author_attestation","sign_citation":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX/action/citation_signature","submit_replication":"https://pith.science/pith/3NQW5A3KQSJTKNEIA4V6OID7LX/action/replication_record"}},"created_at":"2026-07-05T09:54:06.559293+00:00","updated_at":"2026-07-05T09:54:06.559293+00:00"}