{"as_of":"2026-08-18T19:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4097c81969037466a6a93cf632ae118e224dc5b40f64f61c993a3d452cd0a180","coverage":[{"denominator":175,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:01:30.424989Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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":"2026-08-03T03:50:59.444442Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T08:04:28.959690Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"cited_work":{"arxiv_id":"2504.13822","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.13822","snapshot_observed_at":"2026-07-22T01:23:30.189453Z","title":"arXiv:2504.13822 [cs]","venue":null,"work_id":"4f326759-0737-45c2-a6e5-1ae78d20e235","year":null},"citing_paper":{"arxiv_id":"2606.30266","last_updated":"2026-06-29T13:14:57Z","snapshot_observed_at":"2026-08-14T09:36:49.494066Z","submitted_at":"2026-06-29T13:14:57Z","title":"Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-30T07:36:50.034451Z"},"links":{"cited_paper":"/paper/2504.13822","citing_paper":"/paper/2606.30266"},"observation_digest":"sha256:aebadab49756b9505fb15a73368a2b87ec9f4fe40052dd569a985d6bda691529","observation_id":"fc5ff43f-3029-4360-8f34-5d2f638a3dbf","resolution":{"observed_at":"2026-07-22T01:23:30.189453Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13822","snapshot_observed_at":"2026-08-03T03:50:59.444442Z","title":"arXiv preprint arXiv:2504.13822 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.29601","last_updated":"2026-07-31T16:33:18Z","snapshot_observed_at":"2026-08-15T05:01:41.829094Z","submitted_at":"2026-07-31T16:33:18Z","title":"The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-03T03:50:59.444442Z"},"links":{"cited_paper":"/paper/2504.13822","citing_paper":"/paper/2607.29601"},"observation_digest":"sha256:c7da5aacf164507547a31a809f1aa68ddad8e1e7747de2c03b3f11c35f776227","observation_id":"94b7a491-dda5-4163-a5d8-1d6599ff2bed","resolution":{"observed_at":"2026-08-03T03:50:59.444442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2504.13822/citation-record","integrity":"/paper/2504.13822/integrity","json":"/paper/2504.13822/citation-record.json","paper":"/paper/2504.13822"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","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":"2026-08-16T12:01:29.973569Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.973569Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0b9210758b123993fcf290f2e3946660f44d2c4c9715a85e334615f99fdd4fb2","observation_id":"7bd3882e-2f68-448d-8d2e-37dfbae842c0","resolution":{"observed_at":"2026-08-16T12:01:29.973569Z","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":"2026-08-16T12:01:29.979393Z","title":"Memory aware synapses: Learning what (not) to forget","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.979393Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0e358662bfef58653e12fe0dc332cdc59dd73aac8590f7a5fd95609f1618ef1f","observation_id":"fb50f802-2c8f-41c1-bb7b-f0da7704ba11","resolution":{"observed_at":"2026-08-16T12:01:29.979393Z","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":"2026-08-16T12:01:29.983903Z","title":"Expert gate: Lifelong learning with a network of experts","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.983903Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:2f752b889e554571c93265c910efa12e651ac4e6c9387241ee37e94bd6e8078e","observation_id":"2a192b34-40ac-450c-8207-0276f06ce401","resolution":{"observed_at":"2026-08-16T12:01:29.983903Z","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":"2026-08-16T12:01:29.988615Z","title":"Task-free con- tinual learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.988615Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:2447649d036a6f94565524235bfe327b28e9cb9dc1492234389c1cc759c5fd3d","observation_id":"b676cd6c-b06b-49bb-b02a-b7ea496284b7","resolution":{"observed_at":"2026-08-16T12:01:29.988615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.14307","last_updated":"2022-08-30T14:44:41Z","snapshot_observed_at":"2026-08-16T16:35:56.189394Z","submitted_at":"2022-08-30T14:44:41Z","title":"Beyond Supervised Continual Learning: a Review","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.14307","snapshot_observed_at":"2026-08-16T12:01:29.993185Z","title":"Beyond su- pervised continual learning: a review","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.993185Z"},"links":{"cited_paper":"/paper/2208.14307","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:5614ea0b2bd621e52934379e0d0f3b01336cc99391e4463e9b329ab62f179b19","observation_id":"618daa37-f563-4f58-828c-f3ead0e8d43b","resolution":{"observed_at":"2026-08-16T12:01:29.993185Z","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":"2026-08-16T12:01:29.998154Z","title":"Rainbow memory: Continual learning with a memory of diverse samples, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:29.998154Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9c595dea84e1b0a07f318190b65163cd84d6c618822f9ae84db11e914fc40d1a","observation_id":"3cca64fc-b20d-4ddd-8be7-f04f04f5d8b4","resolution":{"observed_at":"2026-08-16T12:01:29.998154Z","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":"2026-08-16T12:01:30.003405Z","title":"Stanley, Jeff Clune, and Nick Cheney","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.003405Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:4238382e7764b33c7db6dccf02cb597b16504175b7e1f89c5b63813347f236e7","observation_id":"d5aaf295-d80d-4377-989b-5462fbc8bd98","resolution":{"observed_at":"2026-08-16T12:01:30.003405Z","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":"2026-08-16T12:01:30.008042Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.008042Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:38c7548e89c680c73746127d47783e9fd376b26d5f3457f0728e0c1bfd1457db","observation_id":"1be1a0a0-b1b6-4f53-b10a-308b39a41470","resolution":{"observed_at":"2026-08-16T12:01:30.008042Z","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":"2026-08-16T12:01:30.012857Z","title":"New insights on reducing abrupt rep- resentation change in online continual learning, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.012857Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:193f2f5c64ed39585ff4d96f5de716f54bf6e40602f8483d544be28e93089390","observation_id":"b3b3782d-f2a1-4506-ba28-b1dc27282383","resolution":{"observed_at":"2026-08-16T12:01:30.012857Z","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":"2026-08-16T12:01:30.017255Z","title":"Online fast adaptation and knowl- edge accumulation: a new approach to continual learning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.017255Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:f01ea014c814f487246dc9851a32c6e197149c541fc24c2106839c7f24733479","observation_id":"3da96010-cb47-43fe-a5e9-f842adcf08bf","resolution":{"observed_at":"2026-08-16T12:01:30.017255Z","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":"2026-08-16T12:01:30.021876Z","title":"Riemannian walk for incremental learning: Understanding forgetting and intransigence","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.021876Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:19a0e935904cf0df19ab6bd8e46883aef706487a8e1514b7f78d4e8744f8b7dc","observation_id":"15ebc679-77d8-4731-9216-7ff485ec79c7","resolution":{"observed_at":"2026-08-16T12:01:30.021876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00420","last_updated":"2019-01-09T11:11:47Z","snapshot_observed_at":"2026-08-15T06:05:04.839393Z","submitted_at":"2018-12-02T16:39:19Z","title":"Efficient Lifelong Learning with A-GEM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00420","snapshot_observed_at":"2026-08-16T12:01:30.026542Z","title":"Efficient lifelong learning with a-gem","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.026542Z"},"links":{"cited_paper":"/paper/1812.00420","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:1f2226d6ee5dd29379f83b5b940c6d303f11ece97d15ca27da3ae6cf3a2c3d8c","observation_id":"298cea90-2a46-41c7-99cd-3f84c6e5f254","resolution":{"observed_at":"2026-08-16T12:01:30.026542Z","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":"2026-08-16T12:01:30.031384Z","title":"Efficient lifelong learning with a-gem, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.031384Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:126320988303ec53de738b7788b97475b30378791633cdf40a93a2632035a412","observation_id":"73a88a2f-5e89-420f-974d-7c909f7b5cd3","resolution":{"observed_at":"2026-08-16T12:01:30.031384Z","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":"2026-08-16T12:01:30.035975Z","title":"Dual low-rank adaptation for continual learning with pre-trained models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.035975Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0ba2164938fb256c023671d69cf302e8bf71dc768d3225fbebcd0edd101a597b","observation_id":"13b2c5ea-f60c-45df-b541-f9568e4d9797","resolution":{"observed_at":"2026-08-16T12:01:30.035975Z","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":"2026-08-16T12:01:30.040764Z","title":"Cat: Continual adapter tuning for aspect sentiment classification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.040764Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:b97faf1ec05407b36757b28dbef2478f9060861758c0d5b55f38f83a8a502e8a","observation_id":"5dbf9c21-fdce-4b39-8bdc-effd40966c34","resolution":{"observed_at":"2026-08-16T12:01:30.040764Z","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":"2026-08-16T12:01:30.045808Z","title":"Adaptformer: Adapting vision transformers for scalable visual recognition, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.045808Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:6e998910ff5386bde89dbe1971b909a79f6adeea9005647941c669346b734632","observation_id":"32ea2656-1ada-4ed2-bf73-1ad6b77b85e4","resolution":{"observed_at":"2026-08-16T12:01:30.045808Z","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":"2026-08-16T12:01:30.050602Z","title":"Semi-supervised and unsupervised deep visual learning: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.050602Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:1cb6904db780cc4ecba63629a8dd0ca21fb77166aef8cb6d9b15eb6aad1877f1","observation_id":"2781e6ac-5c65-440e-8ab4-4e6e57102cab","resolution":{"observed_at":"2026-08-16T12:01:30.050602Z","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":"2026-08-16T12:01:30.054898Z","title":"Lifelong machine learning , volume 1","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.054898Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:134accceb4dc6e93d0820839ca21f322bee78898792ca36990db14bd8cd5b579","observation_id":"c6958315-f06f-4b1b-8800-d4d1fdd7896f","resolution":{"observed_at":"2026-08-16T12:01:30.054898Z","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":"2026-08-16T12:01:30.059605Z","title":"Task arithmetic with loRA for continual learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.059605Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0a2381c7e23a0a683698aa1063d010433717cb00df60b8908559cec679592ee6","observation_id":"0ee2d831-dedd-4e29-b539-419f463aa050","resolution":{"observed_at":"2026-08-16T12:01:30.059605Z","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":"2026-08-16T12:01:30.063797Z","title":"Adaptive LoRA merging for efficient domain incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.063797Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9d2a78d405f8facada67f03dfcc4f408792f212eae3cf8bc4c50881d928f749d","observation_id":"ba74b198-2a74-48cb-a83e-09532de0df68","resolution":{"observed_at":"2026-08-16T12:01:30.063797Z","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":"2026-08-16T12:01:30.068284Z","title":"Flattening sharpness for dynamic gradient projection memory benefits continual learning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.068284Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:c2633bb2815233cc7b99237b077646d7ad8997aa9d9a4ee3a5d9f22b502f216b","observation_id":"7c199123-22ef-47c1-ad61-9ca1972da076","resolution":{"observed_at":"2026-08-16T12:01:30.068284Z","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":"2026-08-16T12:01:30.077044Z","title":"Qlora: Efficient finetuning of quantized llms, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.077044Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:90dbf7c18941c1184fa5df0e147673bd5cf70680722c16669fbafb7771665536","observation_id":"4caa91ad-40e2-4ff5-8dc9-ac6e6ccac0eb","resolution":{"observed_at":"2026-08-16T12:01:30.077044Z","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":"2026-08-16T12:01:30.081310Z","title":"Bert: Pre-training of deep bidirectional transformers for language under- standing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.081310Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:83336936fb6ec0de313aabf51d3ab8cdf20b076b9ab6c2912c68c461b0724589","observation_id":"d1d69b2a-70aa-4b1a-b259-e83496c536e6","resolution":{"observed_at":"2026-08-16T12:01:30.081310Z","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":"2026-08-16T12:01:30.085886Z","title":"Learning without memorizing, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.085886Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:d7a1496336bc638e0c89678bf9d7cc90438ced82257287c660db084ecc53bf96","observation_id":"87010c15-3277-437c-87a0-4389b7c7c900","resolution":{"observed_at":"2026-08-16T12:01:30.085886Z","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":"2026-08-16T12:01:30.090323Z","title":"Learning without memorizing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.090323Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:c74f76750d6bde8cd51c4e9577c651c9fd8a1cc7c1f71247ca3771b2f4d10905","observation_id":"6258f71b-53bf-4db2-bbc6-a20d92db174e","resolution":{"observed_at":"2026-08-16T12:01:30.090323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.13166","last_updated":"2018-10-31T09:15:02Z","snapshot_observed_at":"2026-08-17T21:40:54.651492Z","submitted_at":"2018-10-31T09:15:02Z","title":"Don't forget, there is more than forgetting: new metrics for Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.13166","snapshot_observed_at":"2026-08-16T12:01:30.094733Z","title":"Don’t forget, there is more than forgetting: new metrics for continual learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.094733Z"},"links":{"cited_paper":"/paper/1810.13166","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:de9ea86c7af7d07fb3c2fc89595d7094142943727b1c462dda92a46b5cefc5ee","observation_id":"a5d385d5-b882-46d3-a9ba-bee681aae4bd","resolution":{"observed_at":"2026-08-16T12:01:30.094733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.11694","last_updated":"2019-04-26T06:52:53Z","snapshot_observed_at":"2026-08-14T16:41:07.281073Z","submitted_at":"2019-04-26T06:52:53Z","title":"Neural Logic Machines","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.11694","snapshot_observed_at":"2026-08-16T12:01:30.099606Z","title":"Neural logic machines","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.099606Z"},"links":{"cited_paper":"/paper/1904.11694","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:b416adb28913a13477c43a4ba552e59b98ac4891d0b9c5cffa8cf19b2dd05d1a","observation_id":"38877ab3-5966-446c-931b-2fe977e7b0d0","resolution":{"observed_at":"2026-08-16T12:01:30.099606Z","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":"2026-08-16T12:01:30.104065Z","title":"An image is worth 16x16 words: Transformers for image recog- nition at scale, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.104065Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:07080564b4303d1ee504460e34e4e36295dcbbb7404a53a4b89a41603343ee87","observation_id":"a04f395d-b438-47f8-aeee-69a9d406d4d4","resolution":{"observed_at":"2026-08-16T12:01:30.104065Z","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":"2026-08-16T12:01:30.108675Z","title":"Podnet: Pooled outputs distillation for small-tasks incre- mental learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.108675Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:5d0ee2eb83bd8da9ba8751746f95707965546fc3cb19d315b8c1fc76a21eab68","observation_id":"66ae09ab-62d6-43fa-baec-d4b9c4784df5","resolution":{"observed_at":"2026-08-16T12:01:30.108675Z","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":"2026-08-16T12:01:30.113038Z","title":"Hat-cl: A hard-attention-to-the-task pytorch library for continual learning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.113038Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:b618a49c143a8b7343c451cf24c6a3bdd33600a06837b3fae65dc874d5f88e68","observation_id":"a7cef481-f864-4d40-b67a-864dc6931b51","resolution":{"observed_at":"2026-08-16T12:01:30.113038Z","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":"2026-08-16T12:01:30.117285Z","title":"Orthogonal gradient descent for continual learning, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.117285Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:7b2f551a75bb9eb836517aaa9df0c40935fd7abdc0a3effefa9c50f8308d5fa6","observation_id":"1a2d8146-aa7d-4d36-b4b5-bcdf70ec68b3","resolution":{"observed_at":"2026-08-16T12:01:30.117285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.08734","last_updated":"2017-01-30T18:06:07Z","snapshot_observed_at":"2026-08-14T21:18:51.601049Z","submitted_at":"2017-01-30T18:06:07Z","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.08734","snapshot_observed_at":"2026-08-16T12:01:30.121770Z","title":"Pathnet: Evo- lution channels gradient descent in super neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.121770Z"},"links":{"cited_paper":"/paper/1701.08734","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:e3f7df0c3adb5fec60f27b2410bce43ba9ff498335e564329928988e35b311e5","observation_id":"097ca61c-dbb5-489f-89db-40c39cbf3dbd","resolution":{"observed_at":"2026-08-16T12:01:30.121770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-14T19:37:43.556604Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-16T12:01:30.126584Z","title":"The lottery ticket hypoth- esis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.126584Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:3afc9e22a2079264076cbcf768eb3a94774345b8fa9c20bdc590eba273fab995","observation_id":"c69816cd-d2f0-4a97-aea5-44bedfd4928a","resolution":{"observed_at":"2026-08-16T12:01:30.126584Z","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":"2026-08-16T12:01:30.131128Z","title":"On the effectiveness of parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.131128Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:37d2b9c71f00a0d08d3d6458fab153ccf4270cc4f7c298185088602c4bed5420","observation_id":"30e73050-be12-4748-ab8f-8fc15e37755d","resolution":{"observed_at":"2026-08-16T12:01:30.131128Z","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":"2026-08-16T12:01:30.135492Z","title":"A unified continual learning framework with general parameter-efficient tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.135492Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:7a59528ae76296b6609e116bfef8233092e1117b02054b69fd7bbc90c717c451","observation_id":"5b9b7d9e-e881-4f9b-a3c4-ef9bb781a2bd","resolution":{"observed_at":"2026-08-16T12:01:30.135492Z","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":"2026-08-16T12:01:30.139966Z","title":"Beyond prompt learning: Continual adapter for efficient rehearsal-free continual learning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.139966Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:af9a40f67d47f1cc68e129d3270f1b600cfa242925429a5d61beac63e2fded13","observation_id":"480e2198-8b63-4bfe-b427-6fc9504c0a15","resolution":{"observed_at":"2026-08-16T12:01:30.139966Z","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":"2026-08-16T12:01:30.144593Z","title":"Continual learning via neural pruning, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.144593Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:ee78e1de7d3df486b0fcc0f2f92f9bb8930d76d345211fe6acc0acc546a9de2d","observation_id":"93e5c1d3-f2ff-4208-a864-e21084684535","resolution":{"observed_at":"2026-08-16T12:01:30.144593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02094","last_updated":"2024-07-15T10:59:38Z","snapshot_observed_at":"2026-08-16T14:29:56.119982Z","submitted_at":"2024-01-04T06:46:19Z","title":"PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02094","snapshot_observed_at":"2026-08-16T12:01:30.148766Z","title":"Federated class-incremental learning with prototype guided transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.148766Z"},"links":{"cited_paper":"/paper/2401.02094","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:50f68eb6da3a3c6354895175d160c5beba62486dc98acfa489b1087fa9c9f9b1","observation_id":"08367e71-7b09-44a9-986d-2145c8897164","resolution":{"observed_at":"2026-08-16T12:01:30.148766Z","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":"2026-08-16T12:01:30.153593Z","title":"On the domain adaptation and generalization of pretrained language models: A survey, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.153593Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:76409000f1581639fea01c9944b7f46411eef0cacf8f84d053be93a8e2aa518b","observation_id":"da8e130d-8409-4af2-b8c5-461e167341ba","resolution":{"observed_at":"2026-08-16T12:01:30.153593Z","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":"2026-08-16T12:01:30.158235Z","title":"La-maml: Look-ahead meta learning for continual learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.158235Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:350426e6b2cc43b3593748b6c44afe8cca9fceaf19781faddd0bb276435cbe2c","observation_id":"23038c2a-8f65-4b99-bd1c-ea0006c76283","resolution":{"observed_at":"2026-08-16T12:01:30.158235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-18T09:21:01.141614Z","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04366","snapshot_observed_at":"2026-08-16T12:01:30.162467Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.162467Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:faf900a3a5940034fe200a36627bf775d5300561a208fd104d79a50624c163d9","observation_id":"2a6fe847-5268-4825-9dca-596a1484b2c1","resolution":{"observed_at":"2026-08-16T12:01:30.162467Z","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":"2026-08-16T12:01:30.166914Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.166914Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:97c4dc934d5451824eed2c3f7cd90a50fd7ab3c613c9ec67004e6d6ebd43f8e9","observation_id":"5ba47475-b036-4c22-9a40-397e8187c198","resolution":{"observed_at":"2026-08-16T12:01:30.166914Z","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":"2026-08-16T12:01:30.171268Z","title":"Mera: Merging pretrained adapters for few-shot learning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.171268Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:bbdeb195cfad105b3be2bdbffd540fe2ed0b2d81077d4d5c75fe3bb25aba395c","observation_id":"b0a86a8f-7573-47b2-885a-26f712c64cfa","resolution":{"observed_at":"2026-08-16T12:01:30.171268Z","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":"2026-08-16T12:01:30.175675Z","title":"Class- incremental learning with repetition, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.175675Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9ac83651c0f8d74d60fcfb8a5179ac346b4a7f37840664c1748d8cb49fefc6b7","observation_id":"3d165930-8119-4d5d-b107-caf4d8d5d6c0","resolution":{"observed_at":"2026-08-16T12:01:30.175675Z","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":"2026-08-16T12:01:30.179962Z","title":"Distilling the knowledge in a neural network, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.179962Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:b73f11d5f5bc018a8b5681140cab6335420b4c8f737e061c62ec7211840485c4","observation_id":"67b4cbdf-3cfb-4613-8cb0-7159a6fd4a02","resolution":{"observed_at":"2026-08-16T12:01:30.179962Z","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":"2026-08-16T12:01:30.184363Z","title":"Learning a unified classifier incrementally via rebalancing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.184363Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:890ab5985aa65eb00890a8eb061afcf14b01c3f669606dc273cca51f78bdfe39","observation_id":"776495f8-81b0-4c95-92fc-9b1daa60bb84","resolution":{"observed_at":"2026-08-16T12:01:30.184363Z","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":"2026-08-16T12:01:30.188729Z","title":"Learning a unified classifier incrementally via rebalancing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.188729Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:f9e83083547a09634acce1264e6af99936e4abde47acf3033dc11742998253c0","observation_id":"28614c3b-efd3-4e8a-96ad-40daeebd3703","resolution":{"observed_at":"2026-08-16T12:01:30.188729Z","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":"2026-08-16T12:01:30.193451Z","title":"Parameter-efficient transfer learning for nlp, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.193451Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:64de7e69065ef5b9995fe30abe00052fa7716565180f13e3e31eed6ebd8f59e2","observation_id":"588ecce6-ef48-4d04-bbca-922d05ea4a23","resolution":{"observed_at":"2026-08-16T12:01:30.193451Z","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":"2026-08-16T12:01:30.198037Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.198037Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:ed2a950251f536c1a1466eb6e08330f9f2989826a915110da2d0a420b03b8796","observation_id":"43ba1943-5768-42ed-a0ba-6558516ab343","resolution":{"observed_at":"2026-08-16T12:01:30.198037Z","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":"2026-08-16T12:01:30.202794Z","title":"Universal language model fine- tuning for text classification, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.202794Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:f2fe8d88450e2e1317c9167e0cb3f02425903c4f9207fd816749b786d56debb6","observation_id":"44ea90a2-6f69-4229-b750-9b08d2d0c801","resolution":{"observed_at":"2026-08-16T12:01:30.202794Z","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":"2026-08-16T12:01:30.207389Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.207389Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9776cddcf502c5cd21ec858d7f1e139adb7fff067fc61f1f54586a0f2ad33759","observation_id":"c2533415-9aa6-4784-8e1e-1352e422e2d5","resolution":{"observed_at":"2026-08-16T12:01:30.207389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08200","last_updated":"2023-06-14T02:09:26Z","snapshot_observed_at":"2026-08-16T15:24:07.139978Z","submitted_at":"2023-06-14T02:09:26Z","title":"POP: Prompt Of Prompts for Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08200","snapshot_observed_at":"2026-08-16T12:01:30.211965Z","title":"Pop: Prompt of prompts for continual learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.211965Z"},"links":{"cited_paper":"/paper/2306.08200","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9ac0390bc93f866f82c11093fe29ae3e0e5d7305d20b57073d95bb0177d6373c","observation_id":"528e1909-0ffc-4f79-be98-9dee6402cef1","resolution":{"observed_at":"2026-08-16T12:01:30.211965Z","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":"2026-08-16T12:01:30.216910Z","title":"Expand and merge: Continual learning with the guidance of fixed text embedding space","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.216910Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:aa99bea8e08f97bb33992d0dcbcc9223bcf61c1a009cbd000e2174d9140a0f3b","observation_id":"326d58d3-b7cb-498a-9973-3db0143ae98d","resolution":{"observed_at":"2026-08-16T12:01:30.216910Z","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":"2026-08-16T12:01:30.221286Z","title":"Memory population in con- tinual learning via outlier elimination","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.221286Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:1ed0c87c2dd80bcbc57bca2b1bfab9a6cfa8950edad8049b54875f72e9525cf6","observation_id":"841a5469-3f11-4300-9979-5324b9f96893","resolution":{"observed_at":"2026-08-16T12:01:30.221286Z","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":"2026-08-16T12:01:30.225727Z","title":"Optimizing reusable knowledge for continual learning via metalearning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.225727Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0edf731ba8ab308b44515efa8779b9b43f60b15a11efcbeb6757b2319954f11f","observation_id":"6eceb948-ffeb-4bb2-950b-8d13d5f2cb0d","resolution":{"observed_at":"2026-08-16T12:01:30.225727Z","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":"2026-08-16T12:01:30.230600Z","title":"Continual learning for predictive maintenance: Overview and challenges","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.230600Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:bc7c8ea229fe1f3393afb307a6505683853ad1194d15fe05836319133b2f7aa2","observation_id":"f7c75944-bbdb-48d7-afd2-4e8e25a55be1","resolution":{"observed_at":"2026-08-16T12:01:30.230600Z","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":"2026-08-16T12:01:30.234860Z","title":"Editing models with task arithmetic, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.234860Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:767dbcbb77a00eb07b680fa5ea33760dd0a27e277bbee145d01f451610de3512","observation_id":"b405ea4b-a678-4d7f-956c-9cbe5e279927","resolution":{"observed_at":"2026-08-16T12:01:30.234860Z","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":"2026-08-16T12:01:30.239311Z","title":"Meta-learning representations for continual learning, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.239311Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:342ae960bac31c3fe920084927d79e2f10accbc95a63ff53e5c88f6f8be81b58","observation_id":"be0bef8b-fc22-4d20-a257-af9c71fcf9d3","resolution":{"observed_at":"2026-08-16T12:01:30.239311Z","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":"2026-08-16T12:01:30.243656Z","title":"Helpful or harmful: Inter-task associa- tion in continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.243656Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:ab581d710f1d58983c498641c62355251db22eec8c27c815919ed700fca7db29","observation_id":"b1b9b2fa-4897-42df-bfb9-82f1a34a9ee6","resolution":{"observed_at":"2026-08-16T12:01:30.243656Z","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":"2026-08-16T12:01:30.247892Z","title":"Meta-consolidation for con- tinual learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.247892Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:4ae285d601ac69021d970c516bb38950b4cad0cfb8dcca9a8323e0dd0618a20c","observation_id":"51ca39db-af53-44bf-a992-018de272628d","resolution":{"observed_at":"2026-08-16T12:01:30.247892Z","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":"2026-08-16T12:01:30.252354Z","title":"Con- tinual learning with node-importance based adaptive group sparse regu- larization, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.252354Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:4376b56726448d0b259f9d8be9e9717f9f8e22b9b620a16e5bb37758d7e5f312","observation_id":"8b224125-021c-4ae6-9097-ed77ea946130","resolution":{"observed_at":"2026-08-16T12:01:30.252354Z","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":"2026-08-16T12:01:30.257089Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.257089Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:6fc426c8208d3e15e80a40a1c491b1bffdba97e0c4fe4833c6458c1e772565f6","observation_id":"d48b7fb9-beb4-418c-958c-eb825063796e","resolution":{"observed_at":"2026-08-16T12:01:30.257089Z","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":"2026-08-16T12:01:30.261570Z","title":"Class-Incremental Learn- ing by Knowledge Distillation with Adaptive Feature Consolidation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.261570Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:cedd3d00a2282f74e0c701f066fe1cba63607a6be22245b8ad321b6242e97e63","observation_id":"450ddc38-e9dd-4b64-b106-f4e81915c6a3","resolution":{"observed_at":"2026-08-16T12:01:30.261570Z","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":"2026-08-16T12:01:30.266011Z","title":"Brown, Ben- jamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.266011Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:9a066690034173524a61e49de5036fe84b061599a3c09c16c8835131ae007a9f","observation_id":"218ae6f9-228e-4aef-be5e-b57de3538a3a","resolution":{"observed_at":"2026-08-16T12:01:30.266011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.02706","last_updated":"2021-12-05T23:13:13Z","snapshot_observed_at":"2026-08-16T17:36:54.468026Z","submitted_at":"2021-12-05T23:13:13Z","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","version":1},"cited_work":{"arxiv_id":"2112.02706","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.02706","snapshot_observed_at":"2026-08-16T12:01:31.062491Z","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","venue":"cs.CL","work_id":"f35ca02d-1229-41b7-bfeb-542cd09c8f17","year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.270383Z"},"links":{"cited_paper":"/paper/2112.02706","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:f3945a197acbeb39a78cc69a8dbabb279d2c52da6b1bb53fbad5f855811e1c6c","observation_id":"1e84ceb6-bbcd-4614-937f-3236e452be91","resolution":{"observed_at":"2026-08-16T12:01:31.069307Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T12:01:30.275025Z","title":"Introducing language guidance in prompt-based continual learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.275025Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:994fc34d2591177fa1f4060863ff4bff1292c025018e98806bfce0ba4d43c221","observation_id":"fdcfc724-229f-4149-a010-677adaae3cbd","resolution":{"observed_at":"2026-08-16T12:01:30.275025Z","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":"2026-08-16T12:01:30.279382Z","title":"On the stability-plasticity dilemma of class-incremental learning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.279382Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:8aa0660947d8fe238a3cc0bde5571b1cd482125da2f8cd70a1289ee717213164","observation_id":"322b0d2f-f675-4b00-b960-0dd79a6f67c4","resolution":{"observed_at":"2026-08-16T12:01:30.279382Z","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":"2026-08-16T12:01:30.283648Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.283648Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:ed9e196d548689fd69e8be814415538cb04773a680db3d59115ec634c11d2d32","observation_id":"b720968f-da36-46b2-ac67-70749a781c5a","resolution":{"observed_at":"2026-08-16T12:01:30.283648Z","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":"2026-08-16T12:01:30.288213Z","title":"Rusu, Kieran Milan, John Quan, Tiago Ra- malho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.288213Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:acdaf8a3edaa93c17cb10e7ae0f2c8f80aa8f872f78d9448e09d6a4817ec66a6","observation_id":"b6ff5e79-9d9a-4d65-a502-6e089b3e480e","resolution":{"observed_at":"2026-08-16T12:01:30.288213Z","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":"2026-08-16T12:01:30.292578Z","title":"Kopiczko, Tijmen Blankevoort, and Yuki M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.292578Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:4e7262cfeb6997368b31023848afa6aded216c75ef3aaa5feaac034549eaa391","observation_id":"5bfc9d82-7da7-46d0-b6a7-ae33f2272e31","resolution":{"observed_at":"2026-08-16T12:01:30.292578Z","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":"2026-08-16T12:01:30.296883Z","title":"Hierarchical mo- tion understanding via motion programs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.296883Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:7e4f797b239e99bdda0c0b93604a1f2ef5707b1f65f6eb335d8968b8cef1d963","observation_id":"be867aeb-9b4e-4009-93a4-98345837cc34","resolution":{"observed_at":"2026-08-16T12:01:30.296883Z","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":"2026-08-16T12:01:30.301496Z","title":"Overcoming catas- trophic forgetting with unlabeled data in the wild","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.301496Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0323d1db59827cf8f8ceca479770c519756f5f65667a2f050d6e8c6f69a297af","observation_id":"c650891a-5db9-4afa-872f-11a8f0f56ef2","resolution":{"observed_at":"2026-08-16T12:01:30.301496Z","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":"2026-08-16T12:01:30.306510Z","title":"Do pre-trained mod- els benefit equally in continual learning? In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 6485–6493, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.306510Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:feda81d6aaaf3a7280f9cc592120d24e4e3f6c48bdd195807fbde5e8914b2f24","observation_id":"4c46448c-97b4-4762-840f-b4f81b1e71f6","resolution":{"observed_at":"2026-08-16T12:01:30.306510Z","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":"2026-08-16T12:01:30.311016Z","title":"Overcoming catastrophic forgetting by incremental moment matching","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.311016Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:a7566c54b88a43bd366a89895e51a35e8a9ee3e2f59bb9ad4c84f5fdebbff024","observation_id":"6fb97376-de8a-40c2-9272-7b0900790464","resolution":{"observed_at":"2026-08-16T12:01:30.311016Z","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":"2026-08-16T12:01:30.315410Z","title":"Symbolic replay: Scene graph as prompt for continual learning on vqa task","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.315410Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:d111b90dd94c94f01a4bd6174b06ec86433cdd28b1d3e513d3b22697230e3bff","observation_id":"9bfc115d-4eb2-4ba4-80a6-0886fa68ad97","resolution":{"observed_at":"2026-08-16T12:01:30.315410Z","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":"2026-08-16T12:01:30.319903Z","title":"The power of scale for parameter-efficient prompt tuning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.319903Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:2b3ed26b7f15d0033b981239fcec51bd7b8bbe04c5f572650e322de8b7426bf0","observation_id":"de31fddd-2fb7-48e3-9786-51f1aaab4a3d","resolution":{"observed_at":"2026-08-16T12:01:30.319903Z","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":"2026-08-16T12:01:30.324524Z","title":"Atlas: Adapter- based multi-modal continual learning with a two-stage learning strategy, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.324524Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:588f049b162d5f854b9801d8731357f3b2aa35013f6e2a02d3bccee20cbbe585","observation_id":"d1131116-d8e0-4b0f-ac27-3b077ccbb17e","resolution":{"observed_at":"2026-08-16T12:01:30.324524Z","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":"2026-08-16T12:01:30.329031Z","title":"Prefix-tuning: Optimizing continuous prompts for generation, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.329031Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:75086ad6dd228b95053e1eaaedf77cf610a65c757a493c9b4fc8508f8734ee64","observation_id":"9e5c4cc1-5c01-4b3f-ac1e-57184ab99cff","resolution":{"observed_at":"2026-08-16T12:01:30.329031Z","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":"2026-08-16T12:01:30.333448Z","title":"Vb-lora: Extreme parameter efficient fine-tuning with vector banks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.333448Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:6bf706cdcbecd2e7cd6cdb5b26e1a41f15110cb958fd9659e4054d633d8a8b95","observation_id":"9deea414-3c8c-4e32-a067-a5677f3fb5cd","resolution":{"observed_at":"2026-08-16T12:01:30.333448Z","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":"2026-08-16T12:01:30.337985Z","title":"Learning without forgetting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.337985Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:aa9fa6a347fe85baaf34d552809b2f483498071a32a98ebfb4ec17f1c448c5ed","observation_id":"60ef683e-7a04-4173-bf12-f75f4c2dd604","resolution":{"observed_at":"2026-08-16T12:01:30.337985Z","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":"2026-08-16T12:01:30.342302Z","title":"Inflora: Interference-free low-rank adap- tation for continual learning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.342302Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:05f01ebc24cd5fb880345db2d2b86d066b10a79b8f0297720d5904e0322ea5af","observation_id":"2eb3fa92-affb-4eee-a136-b51d8943ca6b","resolution":{"observed_at":"2026-08-16T12:01:30.342302Z","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":"2026-08-16T12:01:30.346746Z","title":"Trgp: Trust region gradient projection for continual learning, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.346746Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:a219bcf692029e7877bd87649e9a96b4233b5da4c2089f69340111e44ebdca82","observation_id":"4deb9981-bf78-491b-af1d-b11271bff628","resolution":{"observed_at":"2026-08-16T12:01:30.346746Z","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":"2026-08-16T12:01:30.350874Z","title":"The clear bench- mark: Continual learning on real-world imagery","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.350874Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:2027ef24e8c20ddd39bbda5e9b8a9cf0476fc6c92027f677ad66ee99ca34b67c","observation_id":"39cd3362-2df1-4f12-b746-f9bc52990984","resolution":{"observed_at":"2026-08-16T12:01:30.350874Z","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":"2026-08-16T12:01:30.355094Z","title":"Lora-based continual learning with constraints on critical parameter changes, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.355094Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:86049551ffe0d3c6456e52d9fb5f5f24caeb09c66db04eebd6fe14342953d48f","observation_id":"c60ac435-1361-40b9-b2d4-6ffe8ca550f9","resolution":{"observed_at":"2026-08-16T12:01:30.355094Z","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":"2026-08-16T12:01:30.359452Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.359452Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:c8aea301b7f1a2706c4dd6c61dece3a774e4d5a8f00b0949d652abeb0f35634e","observation_id":"25e67d42-2578-467a-be8b-c10358446c97","resolution":{"observed_at":"2026-08-16T12:01:30.359452Z","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":"2026-08-16T12:01:30.363925Z","title":"Parameter-efficient fine-tuning for continual learn- ing: A neural tangent kernel perspective, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.363925Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:fd06bc2229ea4105167da000737e13ded3d6416e2cf07e2b8ebdf52c9f765a39","observation_id":"63414cf8-3618-400b-bd86-966a892d08a1","resolution":{"observed_at":"2026-08-16T12:01:30.363925Z","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":"2026-08-16T12:01:30.368240Z","title":"Dora: Weight-decomposed low-rank adaptation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.368240Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0553df563dc39e58023530ec1223d48c759101a089a69d6215cf534fb868ee78","observation_id":"0aedd2b1-b15c-461e-a31c-29aad9508ac9","resolution":{"observed_at":"2026-08-16T12:01:30.368240Z","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":"2026-08-16T12:01:30.372942Z","title":"Rotate your networks: Better weight consolidation and less catastrophic forgetting","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.372942Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:a869c69bad68d9ad7e14b74fd63621491fb3cce52be55230da925e4eb9316e61","observation_id":"43bd82d6-a3c8-4f38-ba3b-20a05ec0c618","resolution":{"observed_at":"2026-08-16T12:01:30.372942Z","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":"2026-08-16T12:01:30.377182Z","title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.377182Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:e4860f55ae13869681838c629f621204e95d0c850479d74976cad0178e1eb160","observation_id":"1488816f-5a21-40b2-80ce-ce5f08ee6a6f","resolution":{"observed_at":"2026-08-16T12:01:30.377182Z","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":"2026-08-16T12:01:30.381506Z","title":"Gpt understands, too","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.381506Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:09efaf02fb93904dfc75d78d35865f4271c8f13b80530c349ede53a9534e4189","observation_id":"bb139cb7-267f-491b-bafa-3553f514a64f","resolution":{"observed_at":"2026-08-16T12:01:30.381506Z","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":"2026-08-16T12:01:30.385517Z","title":"Adaptive aggregation net- works for class-incremental learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.385517Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:8936553365878f1a4ea380d5e534cb13e54576e2714b5393d1b5f293cd79e956","observation_id":"1406dff0-d1ce-4d5c-a043-79a085038c75","resolution":{"observed_at":"2026-08-16T12:01:30.385517Z","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":"2026-08-16T12:01:30.389817Z","title":"Rmm: Reinforced memory management for class-incremental learning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.389817Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:6d1514486441f5d793041956134052e30381b324d53b7f975de201a9a1459c14","observation_id":"218e1d65-d8e2-4aae-8df0-1a14886636a5","resolution":{"observed_at":"2026-08-16T12:01:30.389817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-08-16T14:33:50.657682Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-16T12:01:30.394102Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.394102Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:935dc68f46bce039cbd1c539042d960f394f2a4dbb07325370859ae33f3cc8b5","observation_id":"47583abd-7a0a-4040-a9b5-66441a51d0d8","resolution":{"observed_at":"2026-08-16T12:01:30.394102Z","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":"2026-08-16T12:01:30.398442Z","title":"Learning to describe scenes with programs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.398442Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:ea6bef592da82239b65afffe2d6dc94bf74c9b70553f686e635146e20ece79a5","observation_id":"dc9cd66c-ec37-4e35-9b74-45a7fb732097","resolution":{"observed_at":"2026-08-16T12:01:30.398442Z","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":"2026-08-16T12:01:30.402816Z","title":"Gradient episodic memory for continual learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.402816Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:369f6d7c589b40b618adc9690ba6dda562d4e071463bb62038e5d87e7ccaddac","observation_id":"67230e68-6cb6-4156-aa49-5af5f107ea33","resolution":{"observed_at":"2026-08-16T12:01:30.402816Z","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":"2026-08-16T12:01:30.407679Z","title":"Gradient episodic memory for continual learning, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.407679Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:d1a74dcb227abcc2ec64075a6227fd3e83ad96a86248a559ede60d245865b0d7","observation_id":"ebb59362-1a8b-4d2d-8c54-f1252cb66d6d","resolution":{"observed_at":"2026-08-16T12:01:30.407679Z","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":"2026-08-16T12:01:30.411836Z","title":"Visual prompt tuning in null space for contin- ual learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.411836Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:0ddadf485cdb59414403818241ea49400c123f01b0915e853bf0355fd0b48582","observation_id":"1d7d7702-d5b8-4736-91a4-7ec6766abe52","resolution":{"observed_at":"2026-08-16T12:01:30.411836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06353","last_updated":"2020-09-15T13:27:13Z","snapshot_observed_at":"2026-07-06T08:57:29.493849Z","submitted_at":"2020-02-15T10:03:25Z","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06353","snapshot_observed_at":"2026-08-16T12:01:30.416207Z","title":"Univl: A unified video and lan- guage pre-training model for multimodal understanding and generation","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.416207Z"},"links":{"cited_paper":"/paper/2002.06353","citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:d5404db1b2de4645b590e9e1bb81346ba9d98ed7447e27cefa9ebd329f74998a","observation_id":"10029647-c288-4013-8867-4cf15a2a5729","resolution":{"observed_at":"2026-08-16T12:01:30.416207Z","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":"2026-08-16T12:01:30.420884Z","title":"Language semantic graph guided data-efficient learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.420884Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:239178ec7744dc26ebdcf095f82ce14326af8b756295849a3ea0c07d94579bec","observation_id":"0dd0c912-2588-44e0-b9b2-88173d1237b6","resolution":{"observed_at":"2026-08-16T12:01:30.420884Z","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":"2026-08-16T12:01:30.424989Z","title":"Online continual learning in image classification: An em- pirical survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","version":3},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-16T12:01:30.424989Z"},"links":{"citing_paper":"/paper/2504.13822"},"observation_digest":"sha256:b21889c2d93269473e21b9b6ce17047a057b4c8fbf760bb4ea33dadd792064cb","observation_id":"95e72d4b-65e0-4bf4-84dd-0541f5279278","resolution":{"observed_at":"2026-08-16T12:01:30.424989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.13822","last_updated":"2026-07-21T14:25:29Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T11:57:16.617418Z","submitted_at":"2025-04-18T17:51:51Z","title":"Parameter-Efficient Continual Fine-Tuning: A Survey"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":99,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":175},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 100 of 175 outbound references and 2 inbound Pith citation observations for arXiv:2504.13822."}