{"as_of":"2026-08-18T09:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:18f4fdf1d530860e13b7383a29a005958f0078b4e7e9de84d0df718500f0a59a","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:48:09.232556Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:16:41.545919Z","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":"2026-07-03T16:48:39.897925Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-08-16T05:16:41.545919Z","title":"How to complete domain tuning while keeping general ability in llm: Adaptive layer-wise and element-wise regularization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.21239","last_updated":"2025-04-30T00:28:32Z","snapshot_observed_at":"2026-08-18T07:11:07.068969Z","submitted_at":"2025-04-30T00:28:32Z","title":"Memorization and Knowledge Injection in Gated LLMs","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-16T05:16:41.545919Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2504.21239"},"observation_digest":"sha256:b8cf4463b37c063a5bdf5f2754741c60f467a5b4a62f0278e3a904ba98de3448","observation_id":"c2a425a5-f885-41d3-9b9a-315bb942bb31","resolution":{"observed_at":"2026-08-16T05:16:41.545919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-08-06T18:49:25.873848Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07296","last_updated":"2025-07-09T21:43:06Z","snapshot_observed_at":"2026-08-18T00:06:49.684722Z","submitted_at":"2025-07-09T21:43:06Z","title":"Time Series Foundation Models for Multivariate Financial Time Series Forecasting","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:25.873848Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2507.07296"},"observation_digest":"sha256:8a6024ea67d2ea96de4fa80b46f8138a0639418db529c8a5e17f3f0eac937ea5","observation_id":"b9596d81-af4b-4be6-b67f-4a788950bc15","resolution":{"observed_at":"2026-08-06T18:49:25.873848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-08-04T23:23:41.525376Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.06650","last_updated":"2025-09-08T13:04:07Z","snapshot_observed_at":"2026-08-15T01:46:49.069429Z","submitted_at":"2025-09-08T13:04:07Z","title":"Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T23:23:41.525376Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2509.06650"},"observation_digest":"sha256:00223f616a36a29d4c67caaa97bc0ba0ff353160bfaea89d3b71b8eba63099ce","observation_id":"09cbdec8-e815-49f7-912e-cedb07a11b06","resolution":{"observed_at":"2026-08-04T23:23:41.525376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":"2501.13669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-07-03T16:48:39.897925Z","title":"How to alleviate catastrophic forgetting in llms finetuning? hierarchical layer-wise and element-wise regularization","venue":null,"work_id":"34c3a01d-9101-40cb-a0fe-8809f3a3b5e2","year":2025},"citing_paper":{"arxiv_id":"2602.12705","last_updated":"2026-04-07T11:35:36Z","snapshot_observed_at":"2026-07-06T22:45:44.135338Z","submitted_at":"2026-02-13T08:19:38Z","title":"MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-15T22:52:30.992054Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2602.12705"},"observation_digest":"sha256:c6e06eaaae4e6ff2a70c2755f6d51a6cd8afdb5571ee75bef15870028b7c3fed","observation_id":"319b1bc1-b991-40c3-bae2-da6c529c6a94","resolution":{"observed_at":"2026-05-15T22:56:50.460181Z","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":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":"2501.13669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-07-03T16:48:39.897925Z","title":"How to alleviate catastrophic forgetting in llms finetuning? hierarchical layer-wise and element-wise regularization","venue":null,"work_id":"34c3a01d-9101-40cb-a0fe-8809f3a3b5e2","year":2025},"citing_paper":{"arxiv_id":"2605.06166","last_updated":"2026-05-07T12:52:02Z","snapshot_observed_at":"2026-08-16T06:49:16.391802Z","submitted_at":"2026-05-07T12:52:02Z","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-08T13:40:50.908566Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2605.06166"},"observation_digest":"sha256:2097c7119b9093531ce80ffb2e0436eced12a4ba25ebad61145851c182dca6ff","observation_id":"77785bd3-0de9-4bd4-a6c8-5aac75750fa7","resolution":{"observed_at":"2026-05-11T18:51:07.467799Z","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":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":"2501.13669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-07-03T16:48:39.897925Z","title":"How to alleviate catastrophic forgetting in llms finetuning? hierarchical layer-wise and element-wise regularization","venue":null,"work_id":"34c3a01d-9101-40cb-a0fe-8809f3a3b5e2","year":2025},"citing_paper":{"arxiv_id":"2605.20005","last_updated":"2026-05-19T15:36:52Z","snapshot_observed_at":"2026-08-15T13:30:43.174440Z","submitted_at":"2026-05-19T15:36:52Z","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-20T07:14:59.396900Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2605.20005"},"observation_digest":"sha256:7ec8c71dbb8bab7dc50eb9c131a3db0b37816962d3ccca87a0b1d043b30e4798","observation_id":"8024744e-d69d-4b3f-8437-27cc47238bdd","resolution":{"observed_at":"2026-05-20T07:18:07.037798Z","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":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"cited_work":{"arxiv_id":"2501.13669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13669","snapshot_observed_at":"2026-07-03T16:48:39.897925Z","title":"How to alleviate catastrophic forgetting in llms finetuning? hierarchical layer-wise and element-wise regularization","venue":null,"work_id":"34c3a01d-9101-40cb-a0fe-8809f3a3b5e2","year":2025},"citing_paper":{"arxiv_id":"2606.24901","last_updated":"2026-06-12T13:44:48Z","snapshot_observed_at":"2026-08-03T03:21:51.293576Z","submitted_at":"2026-06-12T13:44:48Z","title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-06-27T05:02:18.347642Z"},"links":{"cited_paper":"/paper/2501.13669","citing_paper":"/paper/2606.24901"},"observation_digest":"sha256:5c7605f17b0bb1b2cd025c2338694e28f3f890d4e6d6a003c57faa61643c423c","observation_id":"c68c8346-c38b-4a80-bf4d-2840eaff01f1","resolution":{"observed_at":"2026-07-03T16:48:39.899620Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2501.13669/citation-record","integrity":"/paper/2501.13669/integrity","json":"/paper/2501.13669/citation-record.json","paper":"/paper/2501.13669"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-17T18:04:53.578114Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-10T15:48:09.198507Z","title":"J., Shen, Y ., Wallis, P., Allen-Zhu, Z., Li, Y ., Wang, S., Wang, L., and Chen, W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.198507Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:37518cebd78bc6ff2b9d7078940a11d240275a98734cdb9c6e19f98c69d26268","observation_id":"b1fdb145-edf6-4151-9ec7-104192ad5a75","resolution":{"observed_at":"2026-08-10T15:48:09.198507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03732","last_updated":"2023-11-28T03:23:20Z","snapshot_observed_at":"2026-08-14T13:45:26.254758Z","submitted_at":"2023-11-28T03:23:20Z","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03732","snapshot_observed_at":"2026-08-10T15:48:09.202117Z","title":"A rank stabilization scaling factor for fine-tuning with lora","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.202117Z"},"links":{"cited_paper":"/paper/2312.03732","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:caceaaae676bc96cfc47aca8e53227b2032305ea9a89f2abd49fed6f88a79b98","observation_id":"e70865d5-88c7-42d0-89b8-f1855a627193","resolution":{"observed_at":"2026-08-10T15:48:09.202117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:48:09.363661Z","title":"and Joty, S","venue":null,"work_id":"63e5b11d-d26f-495f-899a-c0dc3135863e","year":2022},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.212647Z"},"links":{"citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:df2f552c6ead6c8371aa0049b50831153d7b6cb2973ec648edaa065129ddb317","observation_id":"4394c8d1-fdcc-4b2b-ba5c-f84eda8a976f","resolution":{"observed_at":"2026-08-10T15:48:09.367007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2402.18865","last_updated":"2024-02-29T05:27:45Z","snapshot_observed_at":"2026-08-17T22:17:50.259942Z","submitted_at":"2024-02-29T05:27:45Z","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18865","snapshot_observed_at":"2026-08-10T15:48:09.216082Z","title":"Analyzing and reducing catastrophic forgetting in parameter efficient tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.216082Z"},"links":{"cited_paper":"/paper/2402.18865","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:bc09fd0b3bd54be8a956b7866426ded948498c691f483f1ca852629b0c19fa8e","observation_id":"99ed3f3a-10e2-4439-a35a-8b6e26d07237","resolution":{"observed_at":"2026-08-10T15:48:09.216082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:48:09.353406Z","title":"and Feng, Y","venue":null,"work_id":"23caa54a-dfb7-46f4-9e8d-2468c8c11f7b","year":2023},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.219517Z"},"links":{"citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:4810fafacebaf2ccdd4e734f2f94cc13eb0069e1802d8fce9bfc4b3bcb9c84af","observation_id":"b15f408f-1404-40a2-b615-3684ce2875b3","resolution":{"observed_at":"2026-08-10T15:48:09.356655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-10T15:48:09.222872Z","title":"Llama: Open and efficient foundation lan- guage models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.222872Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:0f8e025fcf1f320c745683d7518bdca3ba3fd16183f834a04b34601cebc433a5","observation_id":"6e74f434-3076-4636-bd6c-895693d6f52c","resolution":{"observed_at":"2026-08-10T15:48:09.222872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:48:09.340971Z","title":"Learning to prompt for continual learning","venue":null,"work_id":"50d274e6-663b-4ffe-a3bd-f833974dc959","year":2022},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.226378Z"},"links":{"citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:c0d9f93df9bd979164349e6daf04376f2a5b0ca4e1aa18ba2871ef8b3c9821d8","observation_id":"c85b423b-3223-46a9-8f85-c00ffa391539","resolution":{"observed_at":"2026-08-10T15:48:09.346478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2407.18242","last_updated":"2025-03-22T09:29:15Z","snapshot_observed_at":"2026-08-17T22:14:24.262905Z","submitted_at":"2024-07-25T17:57:12Z","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18242","snapshot_observed_at":"2026-08-10T15:48:09.229492Z","title":"Lora- pro: Are low-rank adapters properly optimized? arXiv preprint arXiv:2407.18242,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.229492Z"},"links":{"cited_paper":"/paper/2407.18242","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:586846c69c415ca5bf8d16f527fc1125c72fcb79e445b4b7a8ab731b3076a604","observation_id":"35aae84b-805b-4103-8dd8-8057454f0445","resolution":{"observed_at":"2026-08-10T15:48:09.229492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06209","last_updated":"2017-07-19T17:28:46Z","snapshot_observed_at":"2026-08-17T19:08:01.495561Z","submitted_at":"2017-07-19T17:28:46Z","title":"Crowdsourcing Multiple Choice Science Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06209","snapshot_observed_at":"2026-08-10T15:48:09.232556Z","title":"F., and Gardner, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.232556Z"},"links":{"cited_paper":"/paper/1707.06209","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:c158ede695717c0dfc25b3212bc75487ae593438c3d85501b37ff0f391dd751d","observation_id":"25fb14e9-3569-468e-bc09-9c9c4cdf5d2b","resolution":{"observed_at":"2026-08-10T15:48:09.232556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:48:09.373834Z","title":"Continual learning of neural machine translation within low forgetting risk regions","venue":null,"work_id":"ab050685-7b1c-4695-8517-482f5b4196c6","year":2022},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.194858Z"},"links":{"citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:1984ec542d111f4be22e98fff767a54f8c95c784621039d1dc90720ed754e999","observation_id":"26528d6c-6f83-4808-a67a-43be8481a683","resolution":{"observed_at":"2026-08-10T15:48:09.377244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2306.09782","last_updated":"2024-06-06T13:22:26Z","snapshot_observed_at":"2026-08-17T12:59:32.603234Z","submitted_at":"2023-06-16T11:37:15Z","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09782","snapshot_observed_at":"2026-08-10T15:48:09.205619Z","title":"Full parameter fine-tuning for large language models with lim- ited resources","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.205619Z"},"links":{"cited_paper":"/paper/2306.09782","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:6bec05004d831e7456110d009eab43ca845d929360b439d88f70a68b3d8f7444","observation_id":"ad5a4959-e3c8-4ce2-9288-e9c6209d88a7","resolution":{"observed_at":"2026-08-10T15:48:09.205619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-10T15:48:09.187110Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.187110Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:36cdb7421076386a263309b1ab81cb3d1cb7e95cbe53cfce06f170caf78a85c2","observation_id":"ba665177-3c62-4cbb-99c0-f5e461067757","resolution":{"observed_at":"2026-08-10T15:48:09.187110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T15:48:09.209187Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.209187Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:5c353cb59dad8dd24f3d2aeaee59efe5f4cda743d2a5e6776906bc906fa49ef9","observation_id":"1fa7aade-254d-465b-b2d4-0c1759052836","resolution":{"observed_at":"2026-08-10T15:48:09.209187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00027","last_updated":"2020-12-31T19:00:10Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-12-31T19:00:10Z","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00027","snapshot_observed_at":"2026-08-10T15:48:09.191348Z","title":"The pile: An 800gb dataset of diverse text for language modeling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T15:48:09.191348Z"},"links":{"cited_paper":"/paper/2101.00027","citing_paper":"/paper/2501.13669"},"observation_digest":"sha256:8a46213852f989388fed6b705a2320e09fb9878f1cba54e4be2a8e8528ae5cba","observation_id":"10362ff7-80da-4dff-abf8-c47cf79f888c","resolution":{"observed_at":"2026-08-10T15:48:09.191348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.13669","last_updated":"2025-02-17T13:10:33Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T22:14:56.222387Z","submitted_at":"2025-01-23T13:54:53Z","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":14},"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 14 of 14 outbound references and 7 inbound Pith citation observations for arXiv:2501.13669."}