{"as_of":"2026-08-07T11:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6be8c301286f5660c4ea840e7e1ebbee92c1e08f6a60708b5cec86ea276cd224","coverage":[{"denominator":78,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":78,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:00:20.685475Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T20:23:10.477286Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.09471","snapshot_observed_at":"2026-08-02T20:23:10.477286Z","title":"Ckaa: Cross-subspace knowledge alignment and aggregation for robust continual learning.arXiv preprint arXiv:2507.09471,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00191","last_updated":"2026-05-24T03:29:33Z","snapshot_observed_at":"2026-08-06T16:35:35.437208Z","submitted_at":"2026-02-27T02:31:00Z","title":"Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning","version":4},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T20:23:10.477286Z"},"links":{"cited_paper":"/paper/2507.09471","citing_paper":"/paper/2603.00191"},"observation_digest":"sha256:aab33186125cac3217a905aaa82ed72ecbd03bb0e408ab02e1c2e37d30c2f418","observation_id":"40b5e893-167b-4dca-ac95-263d1aa08c99","resolution":{"observed_at":"2026-08-02T20:23:10.477286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.09471","snapshot_observed_at":"2026-08-02T05:13:44.024856Z","title":"arXiv preprint arXiv:2507.09471 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13452","last_updated":"2026-07-15T05:21:23Z","snapshot_observed_at":"2026-08-03T13:46:50.813887Z","submitted_at":"2026-07-15T05:21:23Z","title":"Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-02T05:13:44.024856Z"},"links":{"cited_paper":"/paper/2507.09471","citing_paper":"/paper/2607.13452"},"observation_digest":"sha256:2a03ddb7d55dd42e7dd3bd1d37d7d5fd09ad1ffd25abcd518628446e8d30d421","observation_id":"70eddb3d-9030-4951-bb0f-a1c0e08d6bfe","resolution":{"observed_at":"2026-08-02T05:13:44.024856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.09471/citation-record","integrity":"/paper/2507.09471/integrity","json":"/paper/2507.09471/citation-record.json","paper":"/paper/2507.09471"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:19.428410Z","title":"icarl: Incremental classifier and representation learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:19.428410Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:6e4ceaac907cfa2df0fb66124bf23903763f221da54e5723f1499f9b4d475da1","observation_id":"fb57d1de-9975-4814-b192-851b3bd01e00","resolution":{"observed_at":"2026-08-06T18:00:19.428410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:19.533866Z","title":"Semantically- shifted incremental adapter-tuning is a continual vitransformer,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:19.533866Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:0ce956d8a2fa23c12b78921ccae0c65fbb6ca734a75e8043f83f2164cfd97547","observation_id":"a023e71a-fea0-4dc4-ae0e-7dc03d092c1c","resolution":{"observed_at":"2026-08-06T18:00:19.533866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05658","last_updated":"2024-10-26T08:33:20Z","snapshot_observed_at":"2026-08-06T20:31:26.367679Z","submitted_at":"2024-06-09T05:57:40Z","title":"Visual Prompt Tuning in Null Space for Continual Learning","version":4},"cited_work":{"arxiv_id":"2406.05658","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.05658","snapshot_observed_at":"2026-08-06T18:00:20.946620Z","title":"Visual Prompt Tuning in Null Space for Continual Learning","venue":"cs.CV","work_id":"7238d46b-39fb-49b4-9866-063c4da4e79d","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:19.716996Z"},"links":{"cited_paper":"/paper/2406.05658","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:6e949c8b809157819a0df603e6aa1d59d08b90caf94b0c18260838e44883eecb","observation_id":"b0d0593a-b90c-4aea-8a04-def94bde6daa","resolution":{"observed_at":"2026-08-06T18:00:20.949955Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:19.836124Z","title":"Overcoming catastrophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:19.836124Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:c7c0d706ee4ec556e4ff3b6adbbb613af16da6b12f83d79f1e5055eb0a917534","observation_id":"0fe7316a-91ef-4da3-9e09-cd8796966419","resolution":{"observed_at":"2026-08-06T18:00:19.836124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:19.973800Z","title":"Learning without forgetting,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:19.973800Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:464f79cc4518ebb66e366210227d2ffc4c68143c075a1f05c0232c9c8f52e264","observation_id":"1401d9c3-c04a-4008-9ce7-703329f4479c","resolution":{"observed_at":"2026-08-06T18:00:19.973800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.438522Z","title":"Overcoming catastrophic forgetting by incremental moment matching,","venue":null,"work_id":"5b21549b-0d24-406b-a3ac-55eb23167b1c","year":2017},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.146460Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:80f9ddf28aaea2d82c95481e2ca3da6c8d6d52ab2593f6034d9a438616766807","observation_id":"a3b11118-72f9-4b81-8ed2-0290d83b1a7b","resolution":{"observed_at":"2026-08-06T18:00:21.442005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.278760Z","title":"Catastrophic interference in connec- tionist networks: The sequential learning problem,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.278760Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:5892611ee85b23ed116739d44eb658eeede589fd7cf2c0cf6f4e560cc4831414","observation_id":"88a5730c-3b32-4941-bb95-bff3c6be9c26","resolution":{"observed_at":"2026-08-06T18:00:20.278760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.11930","last_updated":"2024-05-28T11:44:03Z","snapshot_observed_at":"2026-07-06T11:21:51.454687Z","submitted_at":"2021-06-22T17:03:15Z","title":"On the importance of cross-task features for class-incremental learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.11930","snapshot_observed_at":"2026-08-06T18:00:20.373134Z","title":"On the importance of cross-task features for class-incremental learn- ing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.373134Z"},"links":{"cited_paper":"/paper/2106.11930","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:1a6a5e3e2eda92a759d584f9b2ac508d650b821f75bd27b48a51d6a09ea0dd2a","observation_id":"ad107e93-c55f-47b4-ae95-c94b2c9865d7","resolution":{"observed_at":"2026-08-06T18:00:20.373134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.459047Z","title":"A comprehensive survey of continual learning: theory, method and application,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.459047Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:4d62cc6d313ac1d0bbf7ab14c8657ad0db7ff876f3fa50c5d267e7a2da359ca3","observation_id":"9fbeada2-2852-4adf-b756-2235677526a5","resolution":{"observed_at":"2026-08-06T18:00:20.459047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.462558Z","title":"Dark experience for general continual learning: a strong, simple baseline,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.462558Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:f3c6c245e028ba9619b181b8319914b09d5ef67a28d5db0b0d611102f7df7941","observation_id":"025780a5-e889-488b-b6c4-9585a7275619","resolution":{"observed_at":"2026-08-06T18:00:20.462558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.466097Z","title":"Class-incremental learning: survey and performance evaluation on image classification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.466097Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:75727af333a24fba658b621e2ea909f25e9b781a5f1de4ebcb1f85b73cda2e67","observation_id":"c991a21c-09d8-4dbc-b94b-48280b953e7b","resolution":{"observed_at":"2026-08-06T18:00:20.466097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T18:00:20.469338Z","title":"Lora: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.469338Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:932b0655ee1025c037e3221202965daf6bbeba343555ae2ef3258fcda109db81","observation_id":"5132cfd4-83c8-4197-b184-d7e05936aab0","resolution":{"observed_at":"2026-08-06T18:00:20.469338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.407662Z","title":"Adaptformer: Adapting vision transformers for scalable visual recogni- tion,","venue":null,"work_id":"063cf459-e5ce-46f2-9a8d-5f320bdd479e","year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.473158Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:2c2336455b6034ed9e25a23a59fd68d732ac71fd21fff7cac922f79e5e6e8bc3","observation_id":"cbc180a3-e9cf-49c1-80e8-5ee9a1ac1790","resolution":{"observed_at":"2026-08-06T18:00:21.411524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.398183Z","title":"The power of scale for parameter-efficient prompt tuning,","venue":null,"work_id":"39dab640-af08-43f0-a61e-1dec3bccc8a8","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.476095Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:27555865147fd7bf57c95c66dfba5a6ceaba86fd01a2500085c8b29c37b21c95","observation_id":"3f5c1bd4-ea57-4d55-91ba-78284bf344c8","resolution":{"observed_at":"2026-08-06T18:00:21.401997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.479594Z","title":"Scaling & shifting your features: A new baseline for efficient model tuning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.479594Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:d8e38a4d009838fcc52e4b11880b690c045567817f55c8e866249b62a31bff43","observation_id":"828793d4-83be-43a3-be29-39ce4c4658d9","resolution":{"observed_at":"2026-08-06T18:00:20.479594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.482755Z","title":"Learning to prompt for continual learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.482755Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:cb80ea08f40b3ab7df91ee80c37d312c7dd182ead63e0aa3f7866f46e81bfc7b","observation_id":"6db227bf-72ae-4660-89f5-720b79f915db","resolution":{"observed_at":"2026-08-06T18:00:20.482755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.485640Z","title":"Inflora: Interference-free low-rank adaptation for continual learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.485640Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:1823034e0a773a77ba360418bb4e9163f6172867bfa0c24b679fae872adeee36","observation_id":"7e8d8df7-fcf8-4a59-b44b-10cd3815a2b6","resolution":{"observed_at":"2026-08-06T18:00:20.485640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10281","last_updated":"2024-07-14T17:40:40Z","snapshot_observed_at":"2026-08-03T19:41:13.594443Z","submitted_at":"2024-07-14T17:40:40Z","title":"Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning","version":1},"cited_work":{"arxiv_id":"2407.10281","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.10281","snapshot_observed_at":"2026-08-06T18:00:20.916593Z","title":"Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning","venue":"cs.CV","work_id":"0a2043ed-f133-468a-a9fa-210f20567e0a","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.488455Z"},"links":{"cited_paper":"/paper/2407.10281","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:644deff26b431ccee53c074d9d47e3ef8888e013abf019511f8995bb3bb9c885","observation_id":"f26a3dbe-49e8-4a14-9e5e-3e1db638417b","resolution":{"observed_at":"2026-08-06T18:00:20.920735Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.492092Z","title":"Dualprompt: Complementary prompting for rehearsal-free continual learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.492092Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:d0dc08e6fb3f037e8a96e5b3aec37ebe7fffd43b9a4557c35dc23bf8d90e118c","observation_id":"436726e0-afce-41c3-882f-a816532a0d33","resolution":{"observed_at":"2026-08-06T18:00:20.492092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.495156Z","title":"Coda-prompt: Contin- ual decomposed attention-based prompting for rehearsal-free continual learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.495156Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:0b86f26697be962b6667ffe19e2f62e34e2274d5a0da9c15264961c5a72d1dd6","observation_id":"6b86fc41-fbad-409d-b921-b570b1c6de3f","resolution":{"observed_at":"2026-08-06T18:00:20.495156Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.364800Z","title":"Expandable subspace ensemble for pre-trained model-based class-incremental learning,","venue":null,"work_id":"c0cba45b-e23e-4652-b03b-6a4f74165117","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.498251Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:6c2138aae33a7addbbda77b577b09c067e761f016e5e125a9849fd70d190717e","observation_id":"132bd5e4-86ec-439c-b188-e556461cbbdf","resolution":{"observed_at":"2026-08-06T18:00:21.367739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.355662Z","title":"Class-incremental unsupervised domain adaptation via pseudo-label distillation,","venue":null,"work_id":"d75e3a1b-f01d-4515-9e06-6f4a426e6b66","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.501136Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:da725847aa00b5a803d0be56e4e6838cb4893894198b2d738cf65ae186ad2b55","observation_id":"3d670f67-122b-4a1f-9057-e296d9406e96","resolution":{"observed_at":"2026-08-06T18:00:21.359383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.346710Z","title":"On the effectiveness of lipschitz-driven rehearsal in continual learn- ing,","venue":null,"work_id":"e7c024fc-1df3-4574-be6a-93d6013e11cc","year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.504408Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:653adfd0ad3aad1d31c67e33624e6fd154a07aed4520023f13d93d9e8f2554b8","observation_id":"b6bab81f-92b2-4e44-b7ad-6887a12bd654","resolution":{"observed_at":"2026-08-06T18:00:21.349701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.337927Z","title":"Online continual learning with maximal interfered retrieval,","venue":null,"work_id":"a56e240b-6a6a-4b9e-b7b4-9a1796c731b1","year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.507749Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:4d54b36c6da9cbc22e24605ddde30ebb94a4d14bb9fb34b81284a135d6fcaf03","observation_id":"f0cdd97c-1f94-4f4f-b93d-90f809e7ccb2","resolution":{"observed_at":"2026-08-06T18:00:21.340989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.329037Z","title":"Gradient based sample IEEE TRANSACTIONS ON IMAGE PROCESSING 12 selection for online continual learning,","venue":null,"work_id":"32900d5f-a36d-4dcb-8535-b8edd16914fb","year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.510682Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:8d797cea41b8f3cd023bc53053975390c61d7fa610881296706a926f45a2134d","observation_id":"f168bca6-e424-4435-9393-707997f80943","resolution":{"observed_at":"2026-08-06T18:00:21.332183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.320157Z","title":"Balanced destruction- reconstruction dynamics for memory-replay class incremental learning,","venue":null,"work_id":"b6c792c3-dcb1-4dec-b17d-aef77a2e7f48","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.513831Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:88bcf1dfe98d28796d62975b4805d8d0f1a503295d9f6566b8b3d1bb939c0353","observation_id":"f2b0b540-7ef9-46ce-9442-9023d3d58fdb","resolution":{"observed_at":"2026-08-06T18:00:21.323072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.311322Z","title":"Continual learning with node- importance based adaptive group sparse regularization,","venue":null,"work_id":"5ba6d32f-4821-4f1c-b8d7-b72dda5ec665","year":2020},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.517621Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:f979461406fe6a1cf83c1eba77e1d231b44a9b09e55b822643f05cad5c203735","observation_id":"b8f750bb-e0ac-4164-9b30-731ca2b41761","resolution":{"observed_at":"2026-08-06T18:00:21.314957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.302918Z","title":"Continual learning through synaptic intelligence,","venue":null,"work_id":"91d829b8-a569-47e6-a40f-793d60fff9c1","year":2017},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.520672Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:ca271ce709d443b34f2218c7f5ffc54c97ebfc9cefba6f0f6b3b2a41e1b63dcd","observation_id":"e3a18d52-e229-423a-b434-ca303e47b414","resolution":{"observed_at":"2026-08-06T18:00:21.306339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.293749Z","title":"Pamk: Prototype augmented multi-teacher knowledge transfer network for continual zero-shot learning,","venue":null,"work_id":"2ded542b-28a1-454f-8ec7-cf7c91a0b91c","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.524027Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:32128dd59420664f41b443166023083ceccfe0a8ee70cac572e3f2f07a8eca0b","observation_id":"02b86db3-6ef5-41a4-8615-3e2645d62e2e","resolution":{"observed_at":"2026-08-06T18:00:21.297756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.284599Z","title":"Geodesic-aligned gradient projection for continual task learning,","venue":null,"work_id":"921aa4cf-38a2-4a5e-af9c-30a70e9c6575","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.527585Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:4f996844d2cd4d89e357e6c0b2d079f4d363bd89f2bedaf63fee497521317f24","observation_id":"96fee797-bea8-482f-a38d-0f298ed4fbe3","resolution":{"observed_at":"2026-08-06T18:00:21.287663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.276032Z","title":"Compacting, picking and growing for unforgetting continual learning,","venue":null,"work_id":"12db2eff-a53c-4584-b759-6e4ed2d13cb1","year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.530550Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:60ed7244c63e1483c9787392c7e9dffa8baa4d9976758eb8aca264ffea428e4f","observation_id":"f7cacb03-5faa-4b63-89c1-00c0c4e03cbe","resolution":{"observed_at":"2026-08-06T18:00:21.279032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.267038Z","title":"Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting,","venue":null,"work_id":"666b868f-2947-4c10-84e2-9ed81f65218c","year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.533560Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:863c38ac504bf26f845bf0a4f867ce3b9b1419a1e462c812e0c9340e7cb1ebb5","observation_id":"0bd1afd8-1358-4bfc-af0d-cc4da536f8fa","resolution":{"observed_at":"2026-08-06T18:00:21.270722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.257562Z","title":"Der: Dynamically expandable representation for class incremental learning,","venue":null,"work_id":"73b54a93-f8a5-4cd7-a6ba-a658818f4271","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.536453Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:2d3fd1915114becd3eaf59786583f5e6f6f04b32ebc8f6970d5bd60e82038e38","observation_id":"9bfd2bec-fc81-4a06-973d-34a45f5787e7","resolution":{"observed_at":"2026-08-06T18:00:21.261490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.243015Z","title":"Model attention expansion for few-shot class-incremental learning,","venue":null,"work_id":"efeeba7f-4308-486e-aa6b-ece3f9a6c495","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.539607Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:d9b66e9f74e3302ffc819204cff1705a44dbc7b2ebc55af604054d129c5d4a34","observation_id":"665205dc-575d-4ba6-86c0-51ccdeb32962","resolution":{"observed_at":"2026-08-06T18:00:21.250915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.232879Z","title":"Memory efficient continual learning with transformers,","venue":null,"work_id":"1e961794-d860-4af4-918b-bf4da1d070ff","year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.542743Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:192867fa7e600b7366052ae24e036638b803e7caf70ec7120440bbbd2b34642c","observation_id":"9a059658-deac-4c5e-851a-4b3d5f0e0118","resolution":{"observed_at":"2026-08-06T18:00:21.235894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12351","last_updated":"2025-06-14T05:19:58Z","snapshot_observed_at":"2026-08-07T00:49:42.838730Z","submitted_at":"2025-06-14T05:19:58Z","title":"EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning","version":1},"cited_work":{"arxiv_id":"2506.12351","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.12351","snapshot_observed_at":"2026-08-06T18:00:20.903916Z","title":"EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning","venue":"cs.CV","work_id":"36fb7852-1e89-44a4-a789-7fa99723c29f","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.545676Z"},"links":{"cited_paper":"/paper/2506.12351","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:7bea043ba34a74181293b3e530308517f2ce23f22321e6141fb25ea8f61f0442","observation_id":"06eb12d8-c336-4b59-bd34-5584a031f6b3","resolution":{"observed_at":"2026-08-06T18:00:20.907354Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.13997","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.890229Z","title":"Stpr: Spatiotemporal preservation and routing for exemplar-free video class-incremental learning,","venue":null,"work_id":"02ec187b-63a2-4b51-b09e-3a47440a2e03","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.549368Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:07c43cd96441e4d9e137c24f9bd67de5b76dcd7bdd413f4eedbe8c002e249506","observation_id":"b2aaefc1-8fc1-41bf-9f4f-f2aaab1ee43a","resolution":{"observed_at":"2026-08-06T18:00:20.894867Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15469","last_updated":"2026-07-25T02:34:20Z","snapshot_observed_at":"2026-08-06T20:30:28.421431Z","submitted_at":"2024-11-23T06:36:16Z","title":"Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15469","snapshot_observed_at":"2026-08-06T18:00:20.552546Z","title":"Mamba-cl: Optimizing selective state space model in null space for continual learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.552546Z"},"links":{"cited_paper":"/paper/2411.15469","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:0752f41fabc71223d9cef3b5862603f26ef25b5f613a489ab7a58458e4ce9ec0","observation_id":"59f49a11-c205-41f3-9828-56b3021ff082","resolution":{"observed_at":"2026-08-06T18:00:20.552546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.222786Z","title":"Transfer without for- getting,","venue":null,"work_id":"7620f439-9b21-4380-84aa-6a9ae8ecaef6","year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.555790Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:1b19881b7ae8075daf8d58130660599b92b62bf459bd3bcd6e20ea00abc5c3b1","observation_id":"8b723059-1cca-4b1f-9753-1c38537d508e","resolution":{"observed_at":"2026-08-06T18:00:21.226337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.212812Z","title":"Slca: Slow learner with classifier alignment for continual learning on a pre-trained model,","venue":null,"work_id":"c139998f-24ac-4efa-9758-aaae9cebdfa3","year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.559690Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:102c6b11128a0addbecc53d3e098ddc041358e19f30b42af6f44a8474a03366b","observation_id":"3aa2d8bb-a3e4-4b05-8f99-d8bd8b30f263","resolution":{"observed_at":"2026-08-06T18:00:21.216101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.203524Z","title":"Consistent prompting for rehearsal- free continual learning,","venue":null,"work_id":"24ffc3b5-cba0-4761-bd81-a66656c43d9a","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.563107Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:c6a39f753c954303f42a98125c8ca11a68f975d54792de62ed3f57a957dcb49a","observation_id":"58278e56-2d18-4358-91d6-abb716810e28","resolution":{"observed_at":"2026-08-06T18:00:21.206837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.193352Z","title":"Prompt gradient projection for continual learning,","venue":null,"work_id":"327c445d-b6ba-46e2-aca5-7493e263ddcc","year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.565942Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:3f8bf71cdc792d042afe8abcaf4ff458b69c99b57c9eb7fd77c05ade65ac6aa5","observation_id":"4f7e2bb3-e76a-4742-8361-a74caa71874f","resolution":{"observed_at":"2026-08-06T18:00:21.197375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.569355Z","title":"Parameter-efficient transfer learning for nlp,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.569355Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:bd29322ca7b346ce0029a60dfd6bd660a45c2bab34e4a70e31a810b09c2b0960","observation_id":"c0367bc6-71e5-41d0-8c84-4b170eb6c9a8","resolution":{"observed_at":"2026-08-06T18:00:20.569355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.178659Z","title":"Prefix-tuning: Optimizing continuous prompts for generation,","venue":null,"work_id":"064982ba-fbba-42f2-b97d-02b30f2d5d34","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.572195Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:15c4eb8d304687562c51f05bc8d9581ac228ba351f27e4acc26a332b0017f60a","observation_id":"de4e722c-c38f-42bf-8ad9-0810bd04fb61","resolution":{"observed_at":"2026-08-06T18:00:21.182499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.575530Z","title":"Visual prompt tuning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.575530Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:e0c8796ccf7a2c1e1d9c9bde3546945fecc201244790e55cdc9dc3eeb4b71e00","observation_id":"3350b597-3594-4aaf-bf62-a81c001febcd","resolution":{"observed_at":"2026-08-06T18:00:20.575530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.163896Z","title":"Disentangled prompt representation for domain generalization,","venue":null,"work_id":"6027f5ec-e593-42b1-b59d-2e5a171fdcea","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.578200Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:f68a948f1b3821f9bb858d9334254dbb2fa359d779f1d2955a7a90722cbebdfd","observation_id":"503f9d25-4cdf-49e7-9d50-33389c4c8f95","resolution":{"observed_at":"2026-08-06T18:00:21.167457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.154409Z","title":"Adversarial domain prompt tuning and generation for single domain generalization,","venue":null,"work_id":"e16154a9-9640-4743-a9ab-479e930d7b99","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.581260Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:b76d02bf71e328de15c6ae340a3d90b0417f022540e81aaa58d159e9a2b075a3","observation_id":"a1ddbc63-aa3e-44e6-97ab-7dd0f5011ae6","resolution":{"observed_at":"2026-08-06T18:00:21.158010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.145738Z","title":"Learning domain invariant prompt for vision-language models,","venue":null,"work_id":"fd4d81ce-af25-4355-b9c1-67afdfcc1d7c","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.584340Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:e9a8234195f1d5753f84c955be99e3bb8fada002d75505feced9f0d257ac8792","observation_id":"48c67155-756b-4b4d-a6b1-dc16ae6b11f3","resolution":{"observed_at":"2026-08-06T18:00:21.148851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.136551Z","title":"Adapting vision-language models via learning to inject knowledge,","venue":null,"work_id":"cfadf707-961f-4ae2-825c-98a7be6e9a0e","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.588282Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:b1c9ebf80daefc9245f0428b39285a3084bd722eaeb5622631fec9487d04952f","observation_id":"68655a66-1294-4eae-bdd1-850baba67f1b","resolution":{"observed_at":"2026-08-06T18:00:21.140185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.591491Z","title":"Adaptive mixtures of local experts,","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.591491Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:eb0d275f316d0495eab9e65b838cc91691f1c697dc87c8124c424b8bcdf20ddf","observation_id":"683f64c5-eeb6-4163-81db-07a074f8252a","resolution":{"observed_at":"2026-08-06T18:00:20.591491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-06T18:00:20.594541Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.594541Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:53bdb952b973265ee00a0178e30a5d81400c727ba2e57c944c75d708c7499f28","observation_id":"94f81bdb-7fbe-4f48-932a-3968714329fc","resolution":{"observed_at":"2026-08-06T18:00:20.594541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.122024Z","title":"Training networks in null space of feature covariance for continual learning,","venue":null,"work_id":"8c26ec9e-e325-486b-b8f1-a72ef8dcdc2c","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.597435Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:f1ca8910855879619d6af37deef6f41a760a7c0cd2d5371bc02d6e94f001c1f3","observation_id":"538e16bb-c5fc-40f4-8fa5-72fc893b689e","resolution":{"observed_at":"2026-08-06T18:00:21.125270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.112351Z","title":"A unified continual learning framework with general parameter-efficient tuning,","venue":null,"work_id":"2206aa71-5298-4655-915c-f1e1ae312334","year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.601120Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:3eef538ae96a8a8b1da50dc1857ea150faf624464f534466e2bde856abf93ec8","observation_id":"eb60f1f6-d6ab-432a-8a8a-73a843f72a97","resolution":{"observed_at":"2026-08-06T18:00:21.116292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.103039Z","title":"Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need,","venue":null,"work_id":"369673bc-df45-47a1-bee9-4827f121cfeb","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.604233Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:440d446203fa27eb2fd55dc5cd149542701161a8629ed45e96660981e5e957b7","observation_id":"f603701a-b42b-446d-8d38-b4925e2f3e46","resolution":{"observed_at":"2026-08-06T18:00:21.106186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14143","last_updated":"2024-07-19T09:20:33Z","snapshot_observed_at":"2026-07-06T18:48:53.833921Z","submitted_at":"2024-07-19T09:20:33Z","title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","version":1},"cited_work":{"arxiv_id":"2407.14143","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.14143","snapshot_observed_at":"2026-08-06T18:00:20.754679Z","title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","venue":"cs.CV","work_id":"3e4d1945-6ce3-4382-b216-d4796b1bb3e0","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.608028Z"},"links":{"cited_paper":"/paper/2407.14143","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:0af2dee7f2e60ec6ea0081586b3eccce9aa028356c3bcaf45cd712353e46e236","observation_id":"ea949f9a-9421-470f-a83e-d39380381142","resolution":{"observed_at":"2026-08-06T18:00:20.758617Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20444","last_updated":"2025-07-20T07:34:37Z","snapshot_observed_at":"2026-07-06T19:40:21.797132Z","submitted_at":"2024-10-27T13:43:53Z","title":"Vector Quantization Prompting for Continual Learning","version":2},"cited_work":{"arxiv_id":"2410.20444","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.20444","snapshot_observed_at":"2026-08-06T18:00:20.739947Z","title":"Vector Quantization Prompting for Continual Learning","venue":"cs.LG","work_id":"70ba4739-4f64-4700-a0cb-f2e15f05ea8f","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.611313Z"},"links":{"cited_paper":"/paper/2410.20444","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:8d10faf7a89931de5112b53a2f4be5b649dfb11fb09b9817d8f43a0a3116210c","observation_id":"10548cbe-a526-48c5-9a4c-83a2d9105ed4","resolution":{"observed_at":"2026-08-06T18:00:20.745455Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.094295Z","title":"Dynamic integration of task-specific adapters for class incremental learning,","venue":null,"work_id":"8d604c13-aaab-4f5f-ae90-4d93064db30a","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.615339Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:95bfa0d947be1b292c486fe541023c591d2f1fa3ed54f35afe48acfc3330bf3a","observation_id":"ad1f79df-506c-44fb-b5f3-ff2e3f405716","resolution":{"observed_at":"2026-08-06T18:00:21.097571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.618236Z","title":"Adapter merging with centroid prototype mapping for scalable class-incremental learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.618236Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:13bc63b0890f8e83160e1154433ff5b4976aa784b5fc03a2b61f9c54662fd9cc","observation_id":"20f9ca7c-e152-406f-b85b-f4bea537ccd5","resolution":{"observed_at":"2026-08-06T18:00:20.618236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.080290Z","title":"Self-expansion of pre-trained models with mixture of adapters for continual learning,","venue":null,"work_id":"09907e5f-8c3c-4510-897a-ec2bdad32a6c","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.621299Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:a10beb4ca351991c35995c0405f6668ba2a6b7e9456749e9f51b80a61385aaaa","observation_id":"5ac12892-c13f-4792-b60d-96cc4a4fd09d","resolution":{"observed_at":"2026-08-06T18:00:21.083371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.624313Z","title":"Lora subtraction for drift-resistant space in exemplar-free continual learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.624313Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:95a030c391f5472fc1ed443deea58f0c3119620967fcb7b2334b63581484b1eb","observation_id":"eec83e78-4fd2-471b-9b22-f17b6c4a529e","resolution":{"observed_at":"2026-08-06T18:00:20.624313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.065489Z","title":"Cl-lora: Continual low-rank adaptation for rehearsal-free class-incremental learning,","venue":null,"work_id":"cdae4385-f00d-4241-b9b8-514bb1aaaf45","year":2025},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.628298Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:b732af5bee63530a8a36a84799c8f0f89005bc58d4e397d6b21b426ad951f3a9","observation_id":"6ab36ab1-b5f1-4c15-bfc2-057660871d2f","resolution":{"observed_at":"2026-08-06T18:00:21.069100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.056284Z","title":"OVOR: Oneprompt with virtual outlier regularization for rehearsal-free class-incremental learning,","venue":null,"work_id":"4b17c963-2537-49e2-b497-a5653bce3570","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.632338Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:a6c30ab382ccf75c77f5275205bf75bea60f5514cd3d299831e4e9f87d3fdb45","observation_id":"fd3aff02-26bb-4eaf-a574-295acc17943d","resolution":{"observed_at":"2026-08-06T18:00:21.059734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.046497Z","title":"Convolutional prompting meets language models for continual learning,","venue":null,"work_id":"83f67c4e-b519-4764-b906-f00d5a5c3546","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.635933Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:4ba09d7188fcf0afbe582bf88f68958c58bdc87fc6f7efc55b94638fee58fc4f","observation_id":"97376b10-c7ee-495b-b7a6-4bdc9fdc04a0","resolution":{"observed_at":"2026-08-06T18:00:21.050276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.037210Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization,","venue":null,"work_id":"16945173-65f0-45b4-b48b-8e0566602338","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.639807Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:f97786acc883fc6f969ee14efb78dbc8f2c5792f13de501f1b61149004db2723","observation_id":"9d782eb4-bf89-4e2c-a7c1-1f081ae7ab6d","resolution":{"observed_at":"2026-08-06T18:00:21.040374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.028309Z","title":"Natural adversarial examples,","venue":null,"work_id":"ca1ecc62-3a9f-4797-a357-ff1fe1871b27","year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.642887Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:e6e7816de9172bb655df1bec3b098289ddcaf5468b988a811a2742391621a94f","observation_id":"6f94a993-6c31-431b-b359-51054616b845","resolution":{"observed_at":"2026-08-06T18:00:21.031598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.646499Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.646499Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:b0d08d1a4aea566847629a63e5060cc3daf9219abdab41fdaeac978d5f56594d","observation_id":"489a70dd-f546-4818-b48d-b001c781e579","resolution":{"observed_at":"2026-08-06T18:00:20.646499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.650073Z","title":"Moment matching for multi-source domain adaptation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.650073Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:7cff38883c58f237b9ea2f19ba8f1dcb8daecc6a3de20fb0f080c18c9413ee5c","observation_id":"fff02998-5190-4683-9420-5edff5ce08c6","resolution":{"observed_at":"2026-08-06T18:00:20.650073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:21.007031Z","title":"Imagenet large IEEE TRANSACTIONS ON IMAGE PROCESSING 13 scale visual recognition challenge,","venue":null,"work_id":"e34a6869-90a4-4f85-af45-ba831361b0d0","year":2015},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.654293Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:27c4122f0b4f9d571ee57681f4029408302d2326f1d0d0881ee91b9949dc1767","observation_id":"5fe9e5f5-4688-4a0c-819a-fadf01b333d6","resolution":{"observed_at":"2026-08-06T18:00:21.010951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.657243Z","title":"Isolation and impartial aggregation: A paradigm of incremental learning without interference,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.657243Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:0bc83f8b1999626d286046f12cbaa093815ee40f813945f8be282634cd680e7e","observation_id":"26df7d25-d3c4-4fae-bf67-c29519565b2d","resolution":{"observed_at":"2026-08-06T18:00:20.657243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08977","last_updated":"2024-12-11T16:18:16Z","snapshot_observed_at":"2026-07-06T17:01:44.940193Z","submitted_at":"2023-12-14T14:26:57Z","title":"Weighted Ensemble Models Are Strong Continual Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08977","snapshot_observed_at":"2026-08-06T18:00:20.660701Z","title":"Weighted ensemble models are strong continual learners,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.660701Z"},"links":{"cited_paper":"/paper/2312.08977","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:b6d77c6d1efb218a800b4c588a455d9de8ee2866436b117f0a512656c29decb5","observation_id":"de520aba-25b8-44ca-a22f-885d4716141d","resolution":{"observed_at":"2026-08-06T18:00:20.660701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.664136Z","title":"The caltech-ucsd birds-200-2011 dataset,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.664136Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:5a75b5ceea402855760cc4c3e0699e621149c65ef5cd85442a515e71e498e82a","observation_id":"3e35cfd7-c697-42f6-bd29-b4d59897d192","resolution":{"observed_at":"2026-08-06T18:00:20.664136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.988161Z","title":"3d object representations for fine-grained categorization,","venue":null,"work_id":"3f995b55-c8da-490d-8b19-e707b059ffba","year":2013},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.666952Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:063dea1618e20857b668b6fb0cf58b2e8c47f2c2c4cdb751f76eb9f47e056678","observation_id":"415d6373-ab0e-4a84-95ed-f461ec1305d2","resolution":{"observed_at":"2026-08-06T18:00:20.991163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.979258Z","title":"Generating instance-level prompts for rehearsal-free continual learning,","venue":null,"work_id":"e34b3c84-ef7e-4c74-a9eb-ab093c4af559","year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.669891Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:7778214952fa5c44e257687b67496c609c04428f6332d8c6692780bb69c7ae1e","observation_id":"276f22cc-f255-4460-bd09-e4dc00a49186","resolution":{"observed_at":"2026-08-06T18:00:20.982320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06027","last_updated":"2024-05-02T17:43:34Z","snapshot_observed_at":"2026-07-06T15:14:59.488000Z","submitted_at":"2023-04-12T17:59:41Z","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06027","snapshot_observed_at":"2026-08-06T18:00:20.672647Z","title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.672647Z"},"links":{"cited_paper":"/paper/2304.06027","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:2d2ba011c0427127e4403c3c7276ddd7c726df18cc463459cc42bab1bba233dd","observation_id":"f790eb41-dcb5-4d9b-8f9c-5b5d827485ee","resolution":{"observed_at":"2026-08-06T18:00:20.672647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.970356Z","title":"Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality,","venue":null,"work_id":"39352436-b3b7-4535-9f3f-9e2cf13b7de4","year":2024},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.676421Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:c4c3d4b8f9578f975e294fc43b6d76645dd7dd884edd486c8ec75804e348355f","observation_id":"460d733d-8c87-4dff-ba6d-fb9c2d3a1664","resolution":{"observed_at":"2026-08-06T18:00:20.973470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.679193Z","title":"Emerging properties in self-supervised vision transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.679193Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:e70014a2c14496f345e831c238b41f1352ea0daff4ae5026b46955620eb18bae","observation_id":"a5843fa5-e32c-40d6-823b-1c2c3dd23825","resolution":{"observed_at":"2026-08-06T18:00:20.679193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07832","last_updated":"2022-01-27T09:20:49Z","snapshot_observed_at":"2026-07-06T12:08:39.149450Z","submitted_at":"2021-11-15T15:18:05Z","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07832","snapshot_observed_at":"2026-08-06T18:00:20.682062Z","title":"ibot: Image bert pre-training with online tokenizer,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.682062Z"},"links":{"cited_paper":"/paper/2111.07832","citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:6844c5a419a5001e38a5230601419da632b2e5492498bceee0cb6b084af29337","observation_id":"eae453d2-279e-47de-94c0-d4c5b1426467","resolution":{"observed_at":"2026-08-06T18:00:20.682062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:00:20.955973Z","title":"Student with the University of Technology Sydney, Australia","venue":null,"work_id":"ec0ed203-ba83-43e9-86f4-825a8c5d4c18","year":2011},"citing_paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-06T18:00:20.685475Z"},"links":{"citing_paper":"/paper/2507.09471"},"observation_digest":"sha256:18e8b8876d9a5609c5ef84c00f3dbffe99adcda426f0f50644e504fbbcd6c86c","observation_id":"671640de-a550-41e2-ae5e-87f990f0b52f","resolution":{"observed_at":"2026-08-06T18:00:20.959374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.09471","last_updated":"2025-07-13T03:11:35Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T20:30:59.363843Z","submitted_at":"2025-07-13T03:11:35Z","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning"},"reference_resolution":{"displayed":78,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":6,"verified_fuzzy":42},"total_outbound_references":78},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 2 inbound Pith citation observations for arXiv:2507.09471."}