{"as_of":"2026-08-21T19:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ebef18d82c73469e0c8d1ef0c46998361fbbd73ca76207105089c19f0a257f64","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:54:56.081085Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2507.12305/citation-record","integrity":"/paper/2507.12305/integrity","json":"/paper/2507.12305/citation-record.json","paper":"/paper/2507.12305"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2012.09823","last_updated":"2020-12-17T18:44:36Z","snapshot_observed_at":"2026-08-16T18:57:41.580980Z","submitted_at":"2020-12-17T18:44:36Z","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09823","snapshot_observed_at":"2026-08-06T16:54:52.024676Z","title":"Continual lifelong learning in natural language processing: A survey.arXiv preprint arXiv:2012.09823,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.024676Z"},"links":{"cited_paper":"/paper/2012.09823","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:8c16bbc5a355290db441ca8115bb178571e194b9ff344b9cec43e1982afe58fa","observation_id":"02fe3d84-5e6b-4b7f-b330-286f3a63ad1e","resolution":{"observed_at":"2026-08-06T16:54:52.024676Z","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":"2026-08-06T16:55:05.241766Z","title":"Class-incremental contin- ual learning into the extended der-verse.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):5497– 5512, 2022","venue":null,"work_id":"185d2eb7-2c32-4c9c-9f76-65f3f3060bab","year":2022},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.099837Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:ecd920213dfceda9957e0e66e7d5150be17ffab3ad4fb983c11421fd3a04208b","observation_id":"c4fdcce1-5551-41a0-98ae-bc377fea26c5","resolution":{"observed_at":"2026-08-06T16:55:05.307441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:52.231724Z","title":"Dark experience for gen- eral continual learning: a strong, simple baseline.Advances in neural information processing systems, 33:15920–15930,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.231724Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:1c02d40695c833e0283e000f95d555d22037e20092f5aabc45abe7dbb7163fb7","observation_id":"ff776772-bc3c-4b86-a433-e6708deda26c","resolution":{"observed_at":"2026-08-06T16:54:52.231724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.05025","last_updated":"2022-05-02T14:16:26Z","snapshot_observed_at":"2026-08-18T10:36:49.871345Z","submitted_at":"2021-04-11T15:19:30Z","title":"New Insights on Reducing Abrupt Representation Change in Online Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.05025","snapshot_observed_at":"2026-08-06T16:54:52.311602Z","title":"New insights on reducing abrupt representation change in online continual learning.arXiv preprint arXiv:2104.05025, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.311602Z"},"links":{"cited_paper":"/paper/2104.05025","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:464a0317a0cbf839f4da099500992b3f598355af8267f1fbe37561f8ab4e99ae","observation_id":"8590d4b5-92fa-48d2-b585-3870a776c775","resolution":{"observed_at":"2026-08-06T16:54:52.311602Z","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":"2026-08-06T16:55:05.132367Z","title":"A continual learning survey: Defying for- getting in classification tasks.IEEE transactions on pattern analysis and machine intelligence, 44(7):3366–3385, 2021","venue":null,"work_id":"c12739d5-a3b0-4761-8187-29f6a934ee76","year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.403519Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:969ffeb6cd6a850beae2b98edb5a2b9743f8cfcee878008f7140b364d1a19311","observation_id":"92477a17-1166-44f4-acca-d7cbb527bcad","resolution":{"observed_at":"2026-08-06T16:55:05.190073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:52.472868Z","title":"A unified continual learn- ing framework with general parameter-efficient tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.472868Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:39b40f5e18a38b60d0f2104a30a37c3365f6afd52d8c766347e0bac02821f8ba","observation_id":"852f3ff0-2ea5-4e8f-92b6-afa8bd30ca47","resolution":{"observed_at":"2026-08-06T16:54:52.472868Z","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":"2026-08-06T16:55:04.987258Z","title":"Consistent prompting for rehearsal-free continual learning","venue":null,"work_id":"8536ec18-f22f-4ad1-abc6-73cdf1d70f97","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.582687Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:ae05b262e8cce206030082c94615983ff367db731f6712d69d6c5b70b01dd4f1","observation_id":"e79483d1-f947-4cbb-bf84-efcbdce72d4a","resolution":{"observed_at":"2026-08-06T16:55:05.031229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.842927Z","title":"Not just selection, but exploration: Online class-incremental contin- ual learning via dual view consistency","venue":null,"work_id":"c8fac3d9-ea7e-4693-95d2-fe1201a93691","year":2022},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.651575Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:92eb6fa5275a1f600f820c54ed86c14fe94b7cf6a6e0738c3340b6a14753ee08","observation_id":"df829f8d-6aa2-46d8-8df7-bb594f8b2cc8","resolution":{"observed_at":"2026-08-06T16:55:04.920110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.713379Z","title":"Online continual learning through mutual information maximization","venue":null,"work_id":"11833d5c-075b-4c26-bfdc-1471ce99cf37","year":2022},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.708330Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:7af2f0e56b34551de36c532dde30abd36c38052b15e9ed3bf04210a6da088b9d","observation_id":"6d272201-ff7c-42bd-888c-417f489e3ce0","resolution":{"observed_at":"2026-08-06T16:55:04.757008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.567188Z","title":"Dealing with cross-task class discrimination in online continual learning","venue":null,"work_id":"e8941207-ec42-4329-8021-5c8df838e8c2","year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.804903Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:9b76875fc384fa85915ab1834da8cf5a81f9211a1de5e184218d873d44780b22","observation_id":"e4540138-64a5-4244-a765-003e1a79b65e","resolution":{"observed_at":"2026-08-06T16:55:04.646416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.387828Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization.ICCV, 2021","venue":null,"work_id":"6d11009a-80b7-457c-9859-32dbe63edebf","year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.877237Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:7441b2b03bb892ab432e8335400c4418a41f39c354975d7a5171b859f8c8cac8","observation_id":"d0cd66d0-f231-4964-a279-cb86c166eca4","resolution":{"observed_at":"2026-08-06T16:55:04.476763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.236888Z","title":"Natural adversarial examples.CVPR,","venue":null,"work_id":"c3d63329-5cba-4cd2-9f0f-cabfc1b8b110","year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.934369Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:3f0b0db956f3c8e68f8312cb9c15fb0b13cde9872acdfc06900f64cd0f9ba1c1","observation_id":"e31817c4-a617-48e8-af6d-88f84725117d","resolution":{"observed_at":"2026-08-06T16:55:04.323344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:04.117363Z","title":"Non-exemplar online class-incremental con- tinual learning via dual-prototype self-augment and refine- ment","venue":null,"work_id":"10512270-e1be-4e24-8e4b-766ae21567b4","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:52.985339Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:315d9829130d41ddb1840d00c12be5ec95bc396bf22c979eff87ca58f55e184f","observation_id":"6c26ba6e-b3bb-4514-be14-58b0c165a209","resolution":{"observed_at":"2026-08-06T16:55:04.146499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07548","last_updated":"2024-03-13T02:31:47Z","snapshot_observed_at":"2026-08-16T14:10:36.959280Z","submitted_at":"2024-03-12T11:33:48Z","title":"Online Continual Learning For Interactive Instruction Following Agents","version":2},"cited_work":{"arxiv_id":"2403.07548","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.07548","snapshot_observed_at":"2026-08-06T16:54:56.295344Z","title":"Online Continual Learning For Interactive Instruction Following Agents","venue":"cs.AI","work_id":"a9bca1a7-d11a-48f4-a2b8-00379b2b9859","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.083826Z"},"links":{"cited_paper":"/paper/2403.07548","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:529a8c399da51651720dc8cad1ae5e4d475d12191f0bd15866d7c2ca358ba2aa","observation_id":"be07e703-573f-4b1c-af24-de1db28b7084","resolution":{"observed_at":"2026-08-06T16:54:56.352279Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.10031","last_updated":"2022-03-21T08:03:20Z","snapshot_observed_at":"2026-08-20T19:30:29.674224Z","submitted_at":"2021-10-19T14:59:48Z","title":"Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.10031","snapshot_observed_at":"2026-08-06T16:54:53.168194Z","title":"Online continual learning on class incremental blurry task configuration with anytime inference.arXiv preprint arXiv:2110.10031, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.168194Z"},"links":{"cited_paper":"/paper/2110.10031","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:738ef210b7a91a13b94eb6f9b191b965119c60cffeac8950e21b23b844261332","observation_id":"5e613dd9-b2e7-44b4-bcbe-5aedd45dcc76","resolution":{"observed_at":"2026-08-06T16:54:53.168194Z","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":"2026-08-06T16:55:03.964070Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"60020087-46f0-4e36-b0d9-a3e36b72984c","year":2009},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.260390Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:45fe0f9dcc95a7532c3ee754f0333eee4be16a93dd57aad049dcf715ba0a1c6f","observation_id":"4e896fde-5934-414a-862a-262db6982002","resolution":{"observed_at":"2026-08-06T16:55:04.028014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:03.836627Z","title":"Evolv- ing parameterized prompt memory for continual learning","venue":null,"work_id":"1923deff-24da-415e-a8dc-0253a1e0806c","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.354843Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:c2a492287ecf1a40d2f1cb3bc5e55b62718bea83cd1be52edb06fde0f1d16e36","observation_id":"5a01e903-85ad-47e0-9ef1-4a4ed4a1f11e","resolution":{"observed_at":"2026-08-06T16:55:03.892071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-16T20:01:36.160048Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-06T16:54:53.449471Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.449471Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:6aecbb97a2e6c1a96cc2e01d8cbad4a6ef6ffbc7c488d559b6011b4d9432232a","observation_id":"e249c0a1-82ba-43ef-b8a4-1831782853b3","resolution":{"observed_at":"2026-08-06T16:54:53.449471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-21T16:24:51.670091Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-06T16:54:53.554639Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation.arXiv preprint arXiv:2101.00190, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.554639Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:7bdc82edba69a1e79b3951ad0027517f6f8a6f5f0027251520f4c4917a794428","observation_id":"a20fe72a-6bc6-4e33-9d11-8b232a17f687","resolution":{"observed_at":"2026-08-06T16:54:53.554639Z","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":"2026-08-06T16:55:03.702113Z","title":"Inflora: Interference-free low-rank adaptation for continual learning","venue":null,"work_id":"1e1801d3-1061-4337-a7c1-fa4d9246b990","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.649436Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:8b6d4d9b43b190b173234c69d6cdfe29eb5625e41b7caed2ba31246b5b263405","observation_id":"3b052d58-f911-4635-9054-6c02216ec446","resolution":{"observed_at":"2026-08-06T16:55:03.769908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:03.530261Z","title":"Incremental learning with neural networks for computer vision: a survey.Artificial intelligence review, 56 (5):4557–4589, 2023","venue":null,"work_id":"24fb01c4-af88-493a-9a49-53a513609845","year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.729884Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:2a820df6f0db70094cf0b6ff09e11cfacfebe7ddeae64d3799645503a1730ff4","observation_id":"8fe690ca-e56f-4712-bab4-b60015509345","resolution":{"observed_at":"2026-08-06T16:55:03.607975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:03.263581Z","title":"Ranpac: Ran- dom projections and pre-trained models for continual learn- ing.Advances in Neural Information Processing Systems, 36:12022–12053, 2023","venue":null,"work_id":"0ee26cf3-e585-4b57-b185-b4ca104fd405","year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.822487Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:03415728c54832c05aecf3bccf54dd727cf30b50761f1c34349c8c711c50e3a6","observation_id":"af0d4132-50ab-4e1a-badf-51eb52a00e50","resolution":{"observed_at":"2026-08-06T16:55:03.341974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:03.086013Z","title":"Rethinking momentum knowledge distillation in online continual learning","venue":null,"work_id":"b51657ee-083d-450b-bd3a-7cd5c2ca52bd","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.884852Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:262d29ce36b99c25a11d0a7191e3479cd0bda7a5bf5dbcdf64b5e150187df698","observation_id":"858dab6c-53e7-48d2-9458-73af679db46a","resolution":{"observed_at":"2026-08-06T16:55:03.163930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:02.889722Z","title":"Gdumb: A simple approach that questions our progress in continual learning","venue":null,"work_id":"187f6af2-aff2-422b-9607-e843272a26cb","year":2020},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:53.975691Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:e4808742dfa389ffa62b0ee77473693ef1424eab8d0f8c9722e8efb3125fada4","observation_id":"b2816fb8-8a5a-4bbd-823b-b4c97526ac95","resolution":{"observed_at":"2026-08-06T16:55:02.983966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:01.975426Z","title":"Ran- dumb: Random representations outperform online continu- ally learned representations.Advances in Neural Informa- tion Processing Systems, 37:37988–38006, 2024","venue":null,"work_id":"0692638b-cb52-4b0a-9bba-d41ac25112b5","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.078978Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:e163d9361907d820b5e49d84c5085d8bd0da81f2c0297319df23c11276494c90","observation_id":"ab4ea987-a77a-474c-a383-e8764a9cd256","resolution":{"observed_at":"2026-08-06T16:55:02.495583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:01.601438Z","title":"icarl: Incremental classifier and representation learning","venue":null,"work_id":"a6b87b2a-7dd5-40c4-abff-ab5aa9d0fd64","year":2001},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.147434Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:bad09a31c172ef67f094854bae969c2b98510c39832d049fbf9084d81c27377a","observation_id":"d2698876-a54e-44eb-a33f-2d550201a472","resolution":{"observed_at":"2026-08-06T16:55:01.797389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.11910","last_updated":"2019-05-03T03:32:40Z","snapshot_observed_at":"2026-08-20T19:51:19.699450Z","submitted_at":"2018-10-29T00:13:50Z","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.11910","snapshot_observed_at":"2026-08-06T16:54:54.227972Z","title":"Learning to learn without forgetting by maximizing transfer and minimizing interference.arXiv preprint arXiv:1810.11910, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.227972Z"},"links":{"cited_paper":"/paper/1810.11910","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:fae0ffdc76a9e83e1aee2194a4a104b805059cff82b2f8ce0e425553e8314e61","observation_id":"b4de9cd8-178a-4145-9864-4c72fcd5da6a","resolution":{"observed_at":"2026-08-06T16:54:54.227972Z","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":"2026-08-06T16:55:01.238714Z","title":"Convolutional prompting meets language models for continual learning","venue":null,"work_id":"c4965902-c8c8-41da-9a15-cddfbb055356","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.277610Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:7b5913b6bb49ec012844953277a3e00c4169c8cc10f86d159fb152f71510df20","observation_id":"57e8ec49-c1da-4683-9595-71d50b92738a","resolution":{"observed_at":"2026-08-06T16:55:01.383975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:00.956812Z","title":"Learning equi-angular repre- sentations for online continual learning","venue":null,"work_id":"72e242f6-932c-4bf8-9455-e0df4411fa4b","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.352805Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:221d0f9cc179b6bfa93ac0b239c3cb4e6adea819dcc4502e18cf205bbfa0fafe","observation_id":"4428fbc0-b08f-46d3-9919-841d927ac54f","resolution":{"observed_at":"2026-08-06T16:55:01.089074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:00.654529Z","title":"Bud- geted online continual learning by adaptive layer freezing and frequency-based sampling","venue":null,"work_id":"cdb6110e-baf2-4285-9ae0-20157072ba33","year":2025},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.431053Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:61cc3ae9659e01ef79385d8c3df30261eb3541ee032862facdd6e550b3d51782","observation_id":"801c93c4-f5d1-44e1-93df-64631e1f9773","resolution":{"observed_at":"2026-08-06T16:55:00.803064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:55:00.335452Z","title":"Continual learning for real-world autonomous systems: Algorithms, challenges and frameworks.Journal of Intelligent & Robotic Systems, 105 (1):9, 2022","venue":null,"work_id":"7322770d-4b68-43c7-8697-0882fd92988f","year":2022},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.567836Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:28be1e28ad57c0872e1f953f4d6ac6a7ab3c65bba53efca6b5014db823a521a6","observation_id":"3aa56c9c-7e6a-4120-85db-b61babf02dd6","resolution":{"observed_at":"2026-08-06T16:55:00.475186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06027","last_updated":"2024-05-02T17:43:34Z","snapshot_observed_at":"2026-08-16T15:40:54.833688Z","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":"2026-08-06T16:54:54.662756Z","title":"Continual dif- fusion: Continual customization of text-to-image diffusion with c-lora.arXiv preprint arXiv:2304.06027, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.662756Z"},"links":{"cited_paper":"/paper/2304.06027","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:3071dd491e534292929e0cfc38efc5055d91fb5805ed20279602d5d7049480c0","observation_id":"d3059f3d-5446-45d0-beb7-cb43a16d4d2a","resolution":{"observed_at":"2026-08-06T16:54:54.662756Z","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":"2026-08-06T16:54:59.950898Z","title":"Coda-prompt: Contin- ual decomposed attention-based prompting for rehearsal-free continual learning","venue":null,"work_id":"bcc60215-7712-422c-bb38-947a8ad3bee6","year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.756414Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:dbcc2274c1424cfe0c84494b7aaddb2e64aff4cff113313a004eeabdc0a0d46a","observation_id":"7044ec8c-f167-452a-94a8-aa0bc10987e5","resolution":{"observed_at":"2026-08-06T16:55:00.133441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09441","last_updated":"2025-06-18T06:21:19Z","snapshot_observed_at":"2026-08-16T13:00:08.712315Z","submitted_at":"2024-12-12T16:57:20Z","title":"MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09441","snapshot_observed_at":"2026-08-06T16:54:54.853897Z","title":"Mos: Model surgery for pre-trained model-based class-incremental learning.arXiv preprint arXiv:2412.09441, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.853897Z"},"links":{"cited_paper":"/paper/2412.09441","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:4c12513bd0a57f908a7f5fa9a5eb0a8556ac2a768720fc8d8d8833915a056649","observation_id":"07c6469a-9bf9-4564-be11-7180c764cdbb","resolution":{"observed_at":"2026-08-06T16:54:54.853897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06330","last_updated":"2024-02-09T11:09:52Z","snapshot_observed_at":"2026-08-19T16:26:40.416255Z","submitted_at":"2024-02-09T11:09:52Z","title":"Continual Learning on Graphs: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06330","snapshot_observed_at":"2026-08-06T16:54:54.925776Z","title":"Con- tinual learning on graphs: A survey.arXiv preprint arXiv:2402.06330, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.925776Z"},"links":{"cited_paper":"/paper/2402.06330","citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:40a93b15668ea547c0cc57f12f0713fa8ffbce4bd8ceeaf55fd9f26a44dc8b9e","observation_id":"41cc0d96-55af-44b1-80a9-3746f38a039b","resolution":{"observed_at":"2026-08-06T16:54:54.925776Z","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":"2026-08-06T16:54:59.690345Z","title":"The caltech-ucsd birds-200-2011 dataset","venue":null,"work_id":"e5cff67c-571e-4e86-8695-3e41d9f87cdc","year":2011},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:54.988289Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:631c20c299cb0da0f522417e378c2ecf969c83711f72f9bc9cd3afefcd9bd85c","observation_id":"302794ef-25a6-4ff2-bfda-37d8e79779b2","resolution":{"observed_at":"2026-08-06T16:54:59.816446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:59.412585Z","title":"Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub- optimality.Advances in Neural Information Processing Sys- tems, 36, 2024","venue":null,"work_id":"46f33cb8-69fd-4fc1-925b-f3c1ac98cf87","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.041435Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:23a52b97ac95e06aa9e3fb239ed2c31f9f272529dd58e0b484143c8d3f976961","observation_id":"6a23f9cd-72cc-4151-abb5-49ce5d6c94c7","resolution":{"observed_at":"2026-08-06T16:54:59.515272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:59.178818Z","title":"A comprehensive survey of continual learning: theory, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":"27a31b45-48b4-43f7-9ed1-c5e65ca1f3a9","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.081934Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:4de4620d658ce64cd84fc970507fc3ce5715cd2743fea67f71e406ebaf93aecf","observation_id":"ae0de4ff-c0a8-4f26-882e-3b2b7aad1874","resolution":{"observed_at":"2026-08-06T16:54:59.293371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:58.976772Z","title":"Dealing with synthetic data contamination in on- line continual learning","venue":null,"work_id":"be332ab8-3fb0-42d6-a86f-df1733557a78","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.141376Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:e30a73000060e0b149cb7e9fe8e759eff2920f6c93401e6d278d685f815a72e3","observation_id":"0559e2fb-ad40-440e-981d-11685fba272f","resolution":{"observed_at":"2026-08-06T16:54:59.083714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:58.713396Z","title":"Improving plasticity in online continual learning via collaborative learning","venue":null,"work_id":"ae9c4ead-8163-48ec-ae55-71dea76c9fbb","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.295648Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:68323db6b47781af7d61609edb8273bbd4674a23a15c8f6de63ac8644cd3a567","observation_id":"a336dc6e-2497-42eb-8fda-1e23794a4743","resolution":{"observed_at":"2026-08-06T16:54:58.829594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:58.505510Z","title":"S-prompts learning with pre-trained transformers: An occam’s razor for domain incremental learning.Advances in Neural Informa- tion Processing Systems, 35:5682–5695, 2022","venue":null,"work_id":"adac4c60-bc86-4ea8-9891-110cadb66e91","year":2022},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.339577Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:3e3ac1942342f0b348759129c8ae622b336baa508bf10da7eca9d385efea8371","observation_id":"a7393544-c556-4154-8376-c5ca5784ec10","resolution":{"observed_at":"2026-08-06T16:54:58.599459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:55.399790Z","title":"Dualprompt: Complementary prompting for rehearsal-free continual learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.399790Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:15da70a94769a42b089f812ff01e8de129cd14ceb0292cbbdf9fc4f08edc7331","observation_id":"f73676c4-f19e-4290-927b-e717c1b90058","resolution":{"observed_at":"2026-08-06T16:54:55.399790Z","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":"2026-08-06T16:54:55.532267Z","title":"Learning to prompt for continual learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.532267Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:25816ca21712f3849a02c47c03c376689f0477629d65230d9cf6c3d5b592c8bc","observation_id":"d1c8631f-de7f-4206-b09b-a68651c21aba","resolution":{"observed_at":"2026-08-06T16:54:55.532267Z","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":"2026-08-06T16:54:58.022332Z","title":"Online prototype learning for online con- tinual learning","venue":null,"work_id":"f0731edb-ef2c-494a-a480-64876b6c9b84","year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.657437Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:e9b21d6273e903d23a1f34ab336b118cb216071a83668915cc224d958d64964e","observation_id":"e6ea4554-f167-47b4-9e1c-a56d102fc962","resolution":{"observed_at":"2026-08-06T16:54:58.132003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:55.613976Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.613976Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:9eacaf9d4ac2197245ede8e9172b5944fdeddefee0d04b1cd263b3c54e4b71dc","observation_id":"4fd9ace0-3c15-4081-b5da-6c6d1f12ca1c","resolution":{"observed_at":"2026-08-06T16:54:55.613976Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-08-06T16:54:57.546509Z","title":"Mitigating catastrophic forget- ting in online continual learning by modeling previous task interrelations via pareto optimization","venue":null,"work_id":"e7d2ca8d-889f-4446-baef-3ed2713d3a63","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.795417Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:3145a2f1f148d741bcafc129c60bebe080f600e715fcb65ffa85060197d0574a","observation_id":"19881535-fea8-4733-9657-8007a9d34a10","resolution":{"observed_at":"2026-08-06T16:54:57.669190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:57.783995Z","title":"Large scale in- cremental learning","venue":null,"work_id":"2f1d6414-2a07-4321-b81a-a5a10002b914","year":2019},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.714142Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:af37f639a557a71007ebe6d82e5bd3a06c43d6554681c1a3dae0a62a2e6849fc","observation_id":"ca444e6b-7b76-4058-b183-e6e0eb60f723","resolution":{"observed_at":"2026-08-06T16:54:57.895325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:57.193809Z","title":"Layerwise proximal replay: a proximal point method for on- line continual learning","venue":null,"work_id":"765f27ce-58b3-4eb1-8417-f890036add07","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.894272Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:53aadb50dd1b8700eb5d9474881fe69243d33db4e8887f1c01e8341263d56b68","observation_id":"39fe83f2-193f-43d8-bbf9-98f8df31a435","resolution":{"observed_at":"2026-08-06T16:54:57.295870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:57.383037Z","title":"Forgetting, ignorance or myopia: Revis- iting key challenges in online continual learning.Advances in Neural Information Processing Systems, 37:58341–58375,","venue":null,"work_id":"9dfff13e-d949-4fbd-bb0b-9711a7cc0ad2","year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.851779Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:f11869862332b77db68df74935126f5c04dc07777bc901723031972c834b60b7","observation_id":"c41ef5b1-5531-4329-b4e7-e4881822c9fa","resolution":{"observed_at":"2026-08-06T16:54:57.457653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:56.733797Z","title":"Safe: Slow and fast parameter- efficient tuning for continual learning with pre-trained mod- els.Advances in Neural Information Processing Systems, 37: 113772–113796, 2025","venue":null,"work_id":"f21504d0-d01e-4e58-aed4-1523456f071f","year":2025},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.986318Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:31729c3a310fe1e8443fbc93af86de04638d6082569c29bce0925cdbc81d8f67","observation_id":"ddc5e72e-fb45-4708-8e9b-7624202d5802","resolution":{"observed_at":"2026-08-06T16:54:56.829312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:56.967538Z","title":"Slca: Slow learner with classifier align- ment for continual learning on a pre-trained model","venue":null,"work_id":"34405a07-6549-4920-9d1f-42cc68128020","year":2023},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.948221Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:7591b22c49ca69ef9232b5fcce93d1e07c20bf87fe4af6fd38879ea0f1f5a69d","observation_id":"41fda3e8-778b-4f15-916c-6d6315e7b072","resolution":{"observed_at":"2026-08-06T16:54:57.037246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:56.463299Z","title":"F-oal: Forward-only online analytic learning with fast training and low memory footprint in class incremental learning","venue":null,"work_id":"8412257c-3f30-4919-82b0-cfec90a17f63","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:56.081085Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:cacd8fcbfb8fa8469dd403535ea47a50ad1c1ae4d0cf367c20ae381dbd92ecf9","observation_id":"cb72b3bb-a5f5-40e9-a86a-3dce3a477ff9","resolution":{"observed_at":"2026-08-06T16:54:56.526416Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:56.637715Z","title":"Expandable subspace ensemble for pre-trained model- based class-incremental learning","venue":null,"work_id":"f0482b73-e740-412c-a439-7d9eb7478678","year":2024},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:56.038008Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:8f0f63ee564c9cd6ce0094aa8fb36ba7c711a7d9d0896d68b5ad60d7a05a4498","observation_id":"bc75ee1f-092a-45b8-b620-5a47a821565b","resolution":{"observed_at":"2026-08-06T16:54:56.704013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-06T16:54:58.261564Z","title":null,"venue":null,"work_id":"d19d1923-878a-4465-8324-0996f6fefec8","year":null},"citing_paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:55.463811Z"},"links":{"citing_paper":"/paper/2507.12305"},"observation_digest":"sha256:ad2cf13887259d75a43f8d12a1d9490d52c0f9d988c31adb2766a6cf8ddbf019","observation_id":"ddf06799-8916-4e6e-b960-de851273072e","resolution":{"observed_at":"2026-08-06T16:54:58.379093Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.12305","last_updated":"2025-07-16T15:04:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T10:38:29.037838Z","submitted_at":"2025-07-16T15:04:46Z","title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":2,"unresolved":13,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":54},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2507.12305."}