{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MRODKD2567X7BCOYM5TE5XQFV2","short_pith_number":"pith:MRODKD25","schema_version":"1.0","canonical_sha256":"645c350f5df7eff089d867664ede05ae8eb420dadef4cb8530f3434fe58cac9b","source":{"kind":"arxiv","id":"2408.01076","version":2},"attestation_state":"computed","paper":{"title":"Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bart{\\l}omiej Twardowski, Changsheng Xu, Dipam Goswami, Hantao Yao, Joost Van De Weijer, Lu Yu, Zhe Tao","submitted_at":"2024-08-02T07:51:44Z","abstract_excerpt":"Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously learned knowledge. Existing methods mainly rely on visual features, often neglecting the rich semantic information encoded in text. The semantic knowledge available in the label information of the images, offers important semantic information that can be related with previously acquired knowledge of semantic classes. Consequently, effectively leveraging this i"},"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":"2408.01076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T07:51:44Z","cross_cats_sorted":[],"title_canon_sha256":"e3ac0557331179a13793d93f95459ff4804da06b6c9f1282709198a2b2ea61bb","abstract_canon_sha256":"56000f9f0e55c6303600dbd9b531d70ef98d5bdd27d20691440a88f0de411497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:13.607453Z","signature_b64":"eMqxXl2TwF++zpX4R21EeY/Lv8aF9i1f4gfhHyPLmso2ikLiHt0fTQ9JdrrfbAiVcgntTB/ArhPrY+BwcdlNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"645c350f5df7eff089d867664ede05ae8eb420dadef4cb8530f3434fe58cac9b","last_reissued_at":"2026-07-05T11:18:13.606873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:13.606873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bart{\\l}omiej Twardowski, Changsheng Xu, Dipam Goswami, Hantao Yao, Joost Van De Weijer, Lu Yu, Zhe Tao","submitted_at":"2024-08-02T07:51:44Z","abstract_excerpt":"Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously learned knowledge. Existing methods mainly rely on visual features, often neglecting the rich semantic information encoded in text. The semantic knowledge available in the label information of the images, offers important semantic information that can be related with previously acquired knowledge of semantic classes. Consequently, effectively leveraging this i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01076","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/2408.01076/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":"2408.01076","created_at":"2026-07-05T11:18:13.606963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01076v2","created_at":"2026-07-05T11:18:13.606963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01076","created_at":"2026-07-05T11:18:13.606963+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRODKD2567X7","created_at":"2026-07-05T11:18:13.606963+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRODKD2567X7BCOY","created_at":"2026-07-05T11:18:13.606963+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRODKD25","created_at":"2026-07-05T11:18:13.606963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04227","citing_title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18903","citing_title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2","json":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2.json","graph_json":"https://pith.science/api/pith-number/MRODKD2567X7BCOYM5TE5XQFV2/graph.json","events_json":"https://pith.science/api/pith-number/MRODKD2567X7BCOYM5TE5XQFV2/events.json","paper":"https://pith.science/paper/MRODKD25"},"agent_actions":{"view_html":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2","download_json":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2.json","view_paper":"https://pith.science/paper/MRODKD25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01076&json=true","fetch_graph":"https://pith.science/api/pith-number/MRODKD2567X7BCOYM5TE5XQFV2/graph.json","fetch_events":"https://pith.science/api/pith-number/MRODKD2567X7BCOYM5TE5XQFV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2/action/storage_attestation","attest_author":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2/action/author_attestation","sign_citation":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2/action/citation_signature","submit_replication":"https://pith.science/pith/MRODKD2567X7BCOYM5TE5XQFV2/action/replication_record"}},"created_at":"2026-07-05T11:18:13.606963+00:00","updated_at":"2026-07-05T11:18:13.606963+00:00"}