{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UB3O3KAWJBOTEEA4HRF3ZMVDVC","short_pith_number":"pith:UB3O3KAW","schema_version":"1.0","canonical_sha256":"a076eda816485d32101c3c4bbcb2a3a8ae10ca3ff4440960da5e24efb0f9b507","source":{"kind":"arxiv","id":"2510.16077","version":2},"attestation_state":"computed","paper":{"title":"Continual Knowledge Consolidation LORA for Domain Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ary Shiddiqi, Jimmy Cao, Mahardhika Pratama, Naeem Paeedeh, Ryszard Kowalczyk, Weiping Ding, Wolfgang Mayer","submitted_at":"2025-10-17T11:16:08Z","abstract_excerpt":"Domain Incremental Learning (DIL) is a sub-branch of continual learning that aims to address the never-ending arrival of new domains without catastrophic forgetting. Despite the advent of parameter-efficient fine-tuning (PEFT) approaches, prior works create task-specific LoRAs that overlook shared knowledge across tasks. Inaccurate selection of task-specific LoRAs during inference leads to significant drops in accuracy, while existing works rely on linear or prototype-based classifiers, which have suboptimal generalization powers. Our paper proposes continual knowledge consolidation low-rank a"},"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":"2510.16077","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-17T11:16:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e319d4b5956f6c55033dc196445fae860bae1968e9d1a272d93e8676cb6f3088","abstract_canon_sha256":"ee75ac0f7e133f2458e33f728331e305b3529f3520ce68a00ef04a02c4838227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:26.242127Z","signature_b64":"nEgGtlzlDWMZgKF9+RyGsAqZ2MLq5vCIERP5tnP7LKKTuxgc9v7lcCs1amYP/t2OAappT5oEYsPBPVlHWCNWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a076eda816485d32101c3c4bbcb2a3a8ae10ca3ff4440960da5e24efb0f9b507","last_reissued_at":"2026-07-28T01:23:26.241216Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:26.241216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Knowledge Consolidation LORA for Domain Incremental Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ary Shiddiqi, Jimmy Cao, Mahardhika Pratama, Naeem Paeedeh, Ryszard Kowalczyk, Weiping Ding, Wolfgang Mayer","submitted_at":"2025-10-17T11:16:08Z","abstract_excerpt":"Domain Incremental Learning (DIL) is a sub-branch of continual learning that aims to address the never-ending arrival of new domains without catastrophic forgetting. Despite the advent of parameter-efficient fine-tuning (PEFT) approaches, prior works create task-specific LoRAs that overlook shared knowledge across tasks. Inaccurate selection of task-specific LoRAs during inference leads to significant drops in accuracy, while existing works rely on linear or prototype-based classifiers, which have suboptimal generalization powers. Our paper proposes continual knowledge consolidation low-rank a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16077","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/2510.16077/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":"2510.16077","created_at":"2026-07-28T01:23:26.241637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16077v2","created_at":"2026-07-28T01:23:26.241637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16077","created_at":"2026-07-28T01:23:26.241637+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB3O3KAWJBOT","created_at":"2026-07-28T01:23:26.241637+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB3O3KAWJBOTEEA4","created_at":"2026-07-28T01:23:26.241637+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB3O3KAW","created_at":"2026-07-28T01:23:26.241637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30190","citing_title":"Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC","json":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC.json","graph_json":"https://pith.science/api/pith-number/UB3O3KAWJBOTEEA4HRF3ZMVDVC/graph.json","events_json":"https://pith.science/api/pith-number/UB3O3KAWJBOTEEA4HRF3ZMVDVC/events.json","paper":"https://pith.science/paper/UB3O3KAW"},"agent_actions":{"view_html":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC","download_json":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC.json","view_paper":"https://pith.science/paper/UB3O3KAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16077&json=true","fetch_graph":"https://pith.science/api/pith-number/UB3O3KAWJBOTEEA4HRF3ZMVDVC/graph.json","fetch_events":"https://pith.science/api/pith-number/UB3O3KAWJBOTEEA4HRF3ZMVDVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC/action/storage_attestation","attest_author":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC/action/author_attestation","sign_citation":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC/action/citation_signature","submit_replication":"https://pith.science/pith/UB3O3KAWJBOTEEA4HRF3ZMVDVC/action/replication_record"}},"created_at":"2026-07-28T01:23:26.241637+00:00","updated_at":"2026-07-28T01:23:26.241637+00:00"}