{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IRSQTMUOKZXIRZRMLMXTRMJRHY","short_pith_number":"pith:IRSQTMUO","schema_version":"1.0","canonical_sha256":"446509b28e566e88e62c5b2f38b1313e3c5e67ebe47d16deb72eb67bb0bb4069","source":{"kind":"arxiv","id":"2309.15048","version":4},"attestation_state":"computed","paper":{"title":"Class Incremental Learning via Likelihood Ratio Based Task Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bing Liu, Haowei Lin, Ningxin Pan, Weinan Qian, Yiduo Guo, Yijia Shao","submitted_at":"2023-09-26T16:25:57Z","abstract_excerpt":"Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time. Predicting the task-id for each test sample is a challenging problem. An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting. The model for each task is an out-of-distribut"},"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":"2309.15048","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T16:25:57Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ec1844e177c4a2daef8d0e86ff42f1477a8721f9b241a43e3d29509647ab75c3","abstract_canon_sha256":"aa5a3d57e3a68467435030fea6b2b70b8e0d0eadbf268e520922d869f9f2ede3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:24.665768Z","signature_b64":"RNF7s/Zz/RjTWCZs91Y6M9Hd4UZTwJU7PFYeVbO0cQL0Ma/iA+0qSfyBdAafksg1hBk2MSVsh4L4+cwb8j4TDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446509b28e566e88e62c5b2f38b1313e3c5e67ebe47d16deb72eb67bb0bb4069","last_reissued_at":"2026-07-05T07:55:24.665398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:24.665398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class Incremental Learning via Likelihood Ratio Based Task Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bing Liu, Haowei Lin, Ningxin Pan, Weinan Qian, Yiduo Guo, Yijia Shao","submitted_at":"2023-09-26T16:25:57Z","abstract_excerpt":"Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time. Predicting the task-id for each test sample is a challenging problem. An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting. The model for each task is an out-of-distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15048","kind":"arxiv","version":4},"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/2309.15048/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":"2309.15048","created_at":"2026-07-05T07:55:24.665461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15048v4","created_at":"2026-07-05T07:55:24.665461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15048","created_at":"2026-07-05T07:55:24.665461+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRSQTMUOKZXI","created_at":"2026-07-05T07:55:24.665461+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRSQTMUOKZXIRZRM","created_at":"2026-07-05T07:55:24.665461+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRSQTMUO","created_at":"2026-07-05T07:55:24.665461+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/IRSQTMUOKZXIRZRMLMXTRMJRHY","json":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY.json","graph_json":"https://pith.science/api/pith-number/IRSQTMUOKZXIRZRMLMXTRMJRHY/graph.json","events_json":"https://pith.science/api/pith-number/IRSQTMUOKZXIRZRMLMXTRMJRHY/events.json","paper":"https://pith.science/paper/IRSQTMUO"},"agent_actions":{"view_html":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY","download_json":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY.json","view_paper":"https://pith.science/paper/IRSQTMUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15048&json=true","fetch_graph":"https://pith.science/api/pith-number/IRSQTMUOKZXIRZRMLMXTRMJRHY/graph.json","fetch_events":"https://pith.science/api/pith-number/IRSQTMUOKZXIRZRMLMXTRMJRHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY/action/storage_attestation","attest_author":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY/action/author_attestation","sign_citation":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY/action/citation_signature","submit_replication":"https://pith.science/pith/IRSQTMUOKZXIRZRMLMXTRMJRHY/action/replication_record"}},"created_at":"2026-07-05T07:55:24.665461+00:00","updated_at":"2026-07-05T07:55:24.665461+00:00"}