{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U7MB3TNGIRCIQRLOOOILVXZQVD","short_pith_number":"pith:U7MB3TNG","schema_version":"1.0","canonical_sha256":"a7d81dcda6444488456e7390badf30a8dfd72aef035757cee509eb2ae9105d18","source":{"kind":"arxiv","id":"2305.12270","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fandong Meng, Jie Zhou, Xiaotian Lin, Yue Zhang, Yun Luo, Zhen Yang","submitted_at":"2023-05-20T19:22:40Z","abstract_excerpt":"Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten for learning new tasks, and the decision boundary is destructed. Previous studies mostly consider how to recover the representations of learned tasks. It is seldom considered to adapt the decision boundary for new representations and in this paper we propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Lear"},"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":"2305.12270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T19:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"1ed00226afe6d1d6a75a4719276dba40f041967085fc7663f443ff23c7627166","abstract_canon_sha256":"77ca382ce19f275abd04cf481f78e218fcf1f7b5aaf35b1ab671fa0c89eec681"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:08.675161Z","signature_b64":"64kCluuizs1lClWere7Jgs7qTy3cfsA+NQuFn7Gv93h/gOx/R8pDe/Bvzae4I9OVAA43eKE7eFaSPjxZhylnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d81dcda6444488456e7390badf30a8dfd72aef035757cee509eb2ae9105d18","last_reissued_at":"2026-07-05T06:12:08.674735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:08.674735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fandong Meng, Jie Zhou, Xiaotian Lin, Yue Zhang, Yun Luo, Zhen Yang","submitted_at":"2023-05-20T19:22:40Z","abstract_excerpt":"Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten for learning new tasks, and the decision boundary is destructed. Previous studies mostly consider how to recover the representations of learned tasks. It is seldom considered to adapt the decision boundary for new representations and in this paper we propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12270","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/2305.12270/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":"2305.12270","created_at":"2026-07-05T06:12:08.674791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12270v1","created_at":"2026-07-05T06:12:08.674791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12270","created_at":"2026-07-05T06:12:08.674791+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7MB3TNGIRCI","created_at":"2026-07-05T06:12:08.674791+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7MB3TNGIRCIQRLO","created_at":"2026-07-05T06:12:08.674791+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7MB3TNG","created_at":"2026-07-05T06:12:08.674791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08747","citing_title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD","json":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD.json","graph_json":"https://pith.science/api/pith-number/U7MB3TNGIRCIQRLOOOILVXZQVD/graph.json","events_json":"https://pith.science/api/pith-number/U7MB3TNGIRCIQRLOOOILVXZQVD/events.json","paper":"https://pith.science/paper/U7MB3TNG"},"agent_actions":{"view_html":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD","download_json":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD.json","view_paper":"https://pith.science/paper/U7MB3TNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12270&json=true","fetch_graph":"https://pith.science/api/pith-number/U7MB3TNGIRCIQRLOOOILVXZQVD/graph.json","fetch_events":"https://pith.science/api/pith-number/U7MB3TNGIRCIQRLOOOILVXZQVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD/action/storage_attestation","attest_author":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD/action/author_attestation","sign_citation":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD/action/citation_signature","submit_replication":"https://pith.science/pith/U7MB3TNGIRCIQRLOOOILVXZQVD/action/replication_record"}},"created_at":"2026-07-05T06:12:08.674791+00:00","updated_at":"2026-07-05T06:12:08.674791+00:00"}