{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALS6CKECFFOBY2BBRWNSE7S2GC","short_pith_number":"pith:ALS6CKEC","schema_version":"1.0","canonical_sha256":"02e5e12882295c1c68218d9b227e5a308a327b25dac0425f9fda29afa435ab2c","source":{"kind":"arxiv","id":"2507.09471","version":1},"attestation_state":"computed","paper":{"title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De Cheng, Dingwen Zhang, Huaijie Wang, Lingfeng He, Nannan Wang, Xinbo Gao, Zhiheng Ma","submitted_at":"2025-07-13T03:11:35Z","abstract_excerpt":"Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognizer to select the appropriate sub-modules for testing images. However, due to the feature subspace misalignment from independently trained sub-modules, these methods tend to produce ambiguous decisions under misleading task-ids. To address this, we propose Cross-subspace Knowledge "},"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":"2507.09471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T03:11:35Z","cross_cats_sorted":[],"title_canon_sha256":"4158385fc2fab6fdc9feb8c2a69f307dbe5729fac3ec2618ed6952bf0702f5bb","abstract_canon_sha256":"596e66eaff2ee8160ac1ad116fed1a7e0a78237e82e2a1eac3ffa99fdc72c232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:09.611766Z","signature_b64":"PdjnBT6PTYH/d+JvaQ8ZS1OSUOtQn1RB5jv0S/pZe41S+J7vp0mnyp6bITseDf4p9PuO0XT/T2IPlvdcBPYoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02e5e12882295c1c68218d9b227e5a308a327b25dac0425f9fda29afa435ab2c","last_reissued_at":"2026-07-05T11:36:09.611334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:09.611334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De Cheng, Dingwen Zhang, Huaijie Wang, Lingfeng He, Nannan Wang, Xinbo Gao, Zhiheng Ma","submitted_at":"2025-07-13T03:11:35Z","abstract_excerpt":"Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognizer to select the appropriate sub-modules for testing images. However, due to the feature subspace misalignment from independently trained sub-modules, these methods tend to produce ambiguous decisions under misleading task-ids. To address this, we propose Cross-subspace Knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09471","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/2507.09471/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":"2507.09471","created_at":"2026-07-05T11:36:09.611389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09471v1","created_at":"2026-07-05T11:36:09.611389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09471","created_at":"2026-07-05T11:36:09.611389+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALS6CKECFFOB","created_at":"2026-07-05T11:36:09.611389+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALS6CKECFFOBY2BB","created_at":"2026-07-05T11:36:09.611389+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALS6CKEC","created_at":"2026-07-05T11:36:09.611389+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/ALS6CKECFFOBY2BBRWNSE7S2GC","json":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC.json","graph_json":"https://pith.science/api/pith-number/ALS6CKECFFOBY2BBRWNSE7S2GC/graph.json","events_json":"https://pith.science/api/pith-number/ALS6CKECFFOBY2BBRWNSE7S2GC/events.json","paper":"https://pith.science/paper/ALS6CKEC"},"agent_actions":{"view_html":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC","download_json":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC.json","view_paper":"https://pith.science/paper/ALS6CKEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09471&json=true","fetch_graph":"https://pith.science/api/pith-number/ALS6CKECFFOBY2BBRWNSE7S2GC/graph.json","fetch_events":"https://pith.science/api/pith-number/ALS6CKECFFOBY2BBRWNSE7S2GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC/action/storage_attestation","attest_author":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC/action/author_attestation","sign_citation":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC/action/citation_signature","submit_replication":"https://pith.science/pith/ALS6CKECFFOBY2BBRWNSE7S2GC/action/replication_record"}},"created_at":"2026-07-05T11:36:09.611389+00:00","updated_at":"2026-07-05T11:36:09.611389+00:00"}