{"as_of":"2026-08-11T05:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f055b4f7fdefd76c35fa05d854e7bddab39c59ffb88a44643566cab07b72db4f","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T04:31:27.945380Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.10770/citation-record","integrity":"/paper/2605.10770/integrity","json":"/paper/2605.10770/citation-record.json","paper":"/paper/2605.10770"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"citeulike-article-id =","venue":null,"work_id":"93f7c922-af4d-4069-86dd-a6ec6342df7d","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:3d95adc1f78071fafb61f78b29b252226c37f1b383e9df23025045f37fb26f16","observation_id":"6b4cf2b3-7987-4350-9dd4-5e56a55af4a3","resolution":{"observed_at":"2026-05-12T14:46:38.349663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Continual Learning of Large Language Models: A Comprehensive Survey , url =","venue":null,"work_id":"d53a1a6d-a76f-420e-a61f-6a898188d5ef","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:48981d18a05196ad55f34211fff7f4f362b57df87af702f259fbdf0af261c208","observation_id":"2b460e7d-f5f4-4c96-9c3a-36c0c9b75c0d","resolution":{"observed_at":"2026-05-12T14:46:38.364376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1073/pnas.1611835114","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T00:26:39.056637Z","title":"doi: 10.1073/pnas.1611835114","venue":"Proceedings of the National Academy of Sciences","work_id":"6c82f0ba-a185-45cb-a5eb-efcbacd90a09","year":2017},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:5a2926148ed8db391051a68f3f0ca3f932b5d81d5c15ea13722c19f3553ef213","observation_id":"cd4ce520-7243-4ab5-9b18-d7c4f18265c7","resolution":{"observed_at":"2026-05-12T04:36:22.640203Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-08T04:38:18.329888+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T04:38:18.329888+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance , year =","venue":null,"work_id":"6305bdb1-fc03-4b49-a3a9-7d5ae8e5dc57","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:c6e86b64cc8fbe977aa23c19d5f42a6488c1478cc82786395d78766ec0bba824","observation_id":"90978649-bdf9-41a6-938d-d03f7760ccc9","resolution":{"observed_at":"2026-05-12T14:46:38.356636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods , year =","venue":null,"work_id":"35ee0362-ba59-4a4e-abed-4c3a041b3f87","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:1e607d39ad2447c8815c141163a3bad690477b9d527ec12c2a0cffc1976e924f","observation_id":"aefc0c24-c390-44ff-9f38-ac9f2fa14ab3","resolution":{"observed_at":"2026-05-12T14:46:38.368983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Chen and Suchin Gururangan and Mitchell Wortsman and Alon Albalak and Yonatan Bitton and Marianna Nezhurina and Amro Abbas and Cheng","venue":null,"work_id":"80243748-8f05-4dd7-bbf3-98b05aedc46e","year":2024},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:cd61d1bbf0007eaa144ce7859712c274e90a157de3cb553738b5e0edc3e7328d","observation_id":"859b3be0-b56c-485a-b54a-749652f3634c","resolution":{"observed_at":"2026-05-12T14:46:38.281872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference , url =","venue":null,"work_id":"fadcb5bc-46e6-47d6-b99d-3191634bebae","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:4cb2630c35d7ce127f63b65633789892484a6df566f530b9ea7e60b132cfaa3c","observation_id":"189bc2c6-3689-4543-a38c-ac71245dc48c","resolution":{"observed_at":"2026-05-12T14:46:38.182183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yang and Bin Wu and Laurence Aitchison and Emine Yilmaz and Aldo Lipani , booktitle =","venue":null,"work_id":"4d7e4c89-7bb6-4946-846b-5bdf47665277","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:40610ea824c3af437e682022930cce67bc27e3b50c8c3971c531a55c5664e644","observation_id":"2b8a0010-a7f9-4b30-8512-6d4ac2913f6b","resolution":{"observed_at":"2026-05-12T14:46:38.289960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cross-Stitch Networks for Multi-task Learning , url =","venue":null,"work_id":"4332ae08-f4ed-455e-85ab-a1b082d8c4c8","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:6da65fb2cee51fbfb50f99e9b5ba89407ecd44af0f0fb2666ffa6ef5ce7e8c5a","observation_id":"36cda691-dfc3-425b-b02b-3a19f2cacc65","resolution":{"observed_at":"2026-05-12T14:46:38.303912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Latent Multi-Task Architecture Learning , url =","venue":null,"work_id":"3fe51764-2f5c-42d8-bb36-30bcd92c91cd","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:e9bfcad7a7a874e89f5e35d5ab9609400959ce24c064c579a435e453ba3d1b7d","observation_id":"0daa44af-66f5-403b-b029-7a48b33ea0c8","resolution":{"observed_at":"2026-05-12T14:46:38.287217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection , url =","venue":null,"work_id":"f1174425-95ed-4abd-bfef-d8f029e3b6ce","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:5452fd54e4db0a577d99a8cb9a27a8d086426a3025050e2da4560b9d61d1d957","observation_id":"5c0a4a39-2756-4d88-9fc0-70870f15d31a","resolution":{"observed_at":"2026-05-12T14:46:38.262539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gradient Surgery for Multi-Task Learning , url =","venue":null,"work_id":"56690380-f16f-40ed-bc3d-4b0fc8774e92","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:35a8b8f6775dde530a945368830846740df6494ec7aa10f69a6d609800de0a14","observation_id":"5957f9c2-27cc-4360-9f23-c9ef4243ea9b","resolution":{"observed_at":"2026-05-12T14:46:38.206147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics , url =","venue":null,"work_id":"63812f73-2f85-4385-a05c-93be32f5c5a4","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:d502eadd2d4119cdb7045df57dc7fb3a73209a82b5a1098f9d94903ac8ecdf74","observation_id":"e82d199d-d3d3-4d07-ac9e-aba2c8f18459","resolution":{"observed_at":"2026-05-12T14:46:38.199326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks , url =","venue":null,"work_id":"e4b4af8b-1233-4c75-a1b8-6a8901b037bb","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:e835d37901364a2f31315e17153dcd4c20f9695f20c154f22c6025f067c6b055","observation_id":"b91e739e-7aa4-4362-bbd5-0be7c62baef3","resolution":{"observed_at":"2026-05-12T14:46:38.335827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models , url =","venue":null,"work_id":"62a2489a-084c-4273-989d-adf9df70f390","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:93209072b43214c41d4c5bc884ed15ed4a11c26227418d67843ced83011ee46a","observation_id":"3bb6db7e-d18c-42aa-96a3-356dd1628b5c","resolution":{"observed_at":"2026-05-12T14:46:38.342407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Balancing Training for Multilingual Neural Machine Translation , url =","venue":null,"work_id":"e969db53-1b71-466e-83c9-cf0c227a54c2","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:dcfe45326e182e4dc682a3e90e7f842f816ea84d43a256527781a508fd477f97","observation_id":"137d925e-303b-402d-9726-85738b0a6bf7","resolution":{"observed_at":"2026-05-12T14:46:38.233266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-Task Transfer Matters During Instruction-Tuning , url =","venue":null,"work_id":"fa4bf358-e98b-4882-8ffa-14bab02054e9","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b3fb6f588d6d2714c2b8dafb8c0220a81abba821acef39450fb0a7977840cf7b","observation_id":"57f73ef0-4293-428f-8a90-edc796528eb6","resolution":{"observed_at":"2026-05-12T14:46:38.301407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples , url =","venue":null,"work_id":"b97a6fa4-ecd0-4c90-9374-3269a02fe433","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:ab0f3eb26d7a34f35d62e3b8b54b85ce81bdbcd5709410ff2cd0681de93491c6","observation_id":"d52ae500-e1fd-4db6-8979-cc22f995630d","resolution":{"observed_at":"2026-05-12T14:46:38.329619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition , url =","venue":null,"work_id":"999fb527-739c-427d-b76b-f1162211a536","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:976d279f2db2d7f3dbea193faed8dcbbbf295a975b8be363f7eeb5bbf9aa0a8e","observation_id":"57bb3a3c-079f-4929-8435-ec6456c19b38","resolution":{"observed_at":"2026-05-12T14:46:38.278461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models , url =","venue":null,"work_id":"52f1e9df-5f8c-416e-89f9-345a9a978155","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:02f00a86ba63d1f726aa36684527825718da4161743924448072b8257eda0f24","observation_id":"e83857db-1708-4b8c-80a7-b904e038f203","resolution":{"observed_at":"2026-05-12T14:46:38.313213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics , url =","venue":null,"work_id":"d2b9a32b-bcf7-483c-a86d-d14a2d802bdf","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:caa43635189417585c25421ed89b6bb1a2fcddb11ecb5d466b3a38a5572d745e","observation_id":"5a78f988-844f-4f3c-a9a7-6c2e6b7e6efe","resolution":{"observed_at":"2026-05-12T14:46:38.249728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bell and Neil D","venue":null,"work_id":"60b6cf0e-135d-4527-ac5f-dfa0b9f00f8a","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b5c3d7292cab1336ff921a5813037b8eb3e728ff01fb7b8f5e6ca294fd1986aa","observation_id":"568f5947-83e6-4ed3-b621-80cf5882e533","resolution":{"observed_at":"2026-05-12T14:46:38.360260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Le and Tengyu Ma and Adams Wei Yu , booktitle =","venue":null,"work_id":"31a3cf3c-f70e-4323-b8c0-f3ade63829d9","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:31b07ed412633a7cc39afc793187f4883e65b3b6e753579b1ea5d98300f8184b","observation_id":"c52ca1da-abde-4233-a6c3-fbe2aa9efd47","resolution":{"observed_at":"2026-05-12T14:46:38.345795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"76abe9fa-d10f-4e50-9597-d2ec72485e89","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:79ca07e4838b08ed2333680a5d122e4de266f3260f8190e2e19d54ddef036615","observation_id":"d9cd8d09-6636-422b-b18b-776cc13af676","resolution":{"observed_at":"2026-05-12T14:46:38.298430Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning , url =","venue":null,"work_id":"bd0e6226-53d6-40ab-8531-113eab3de860","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:3a276bdae4db68a671f11f68023033a210da9bfb4b9c3b164de007daa5189b10","observation_id":"411be1a6-9f5a-4b4f-b249-f48e69734016","resolution":{"observed_at":"2026-05-12T14:46:38.236971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Kwok and Zhenguo Li and Adrian Weller and Weiyang Liu , booktitle =","venue":null,"work_id":"7b4fd55f-2ea0-4469-b4b2-4392db7a94fb","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:153a99b0d69d527d351a971aacdc6bceafc2bf5c222cdaa94cbf6fcb226d2934","observation_id":"4c3e44a9-c5dd-4142-bfdd-b756c8a17b06","resolution":{"observed_at":"2026-05-12T14:46:38.306979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning , url =","venue":null,"work_id":"c25bef1b-bcf3-466c-b207-262ca199bad5","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:9ecac1a899de4d4cdfad82dee434bf65359a6bd1d439b8bffd5cb06e8842633e","observation_id":"4532adfe-2f54-49b1-a5a9-833f1485d8da","resolution":{"observed_at":"2026-05-12T14:46:38.256143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"HuggingFace repository , title =","venue":null,"work_id":"476eb0a5-2712-46c9-ab50-214787fe3152","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:500c2c70ba20d8de7d0003fd6a747d6c2c28158a313ce2819ffde98467df9780","observation_id":"78b1e253-752c-49fc-92db-c5bd9e2ee82a","resolution":{"observed_at":"2026-05-12T14:46:38.202803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale , url =","venue":null,"work_id":"6c62b989-770e-4a66-aa08-2c626042dd41","year":2024},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:addaae801f472fa884bce914724a0922dc4e9440214906fab384e8d6189041ce","observation_id":"b229559b-ac24-4532-b429-aa2733da97e4","resolution":{"observed_at":"2026-05-12T14:46:38.268983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"40183569-2281-4df2-8518-65035cf0412c","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:e502f4047d388c339092563b1b34b3b6bf2ac3a158642e1e602727055cde6280","observation_id":"4d7ebfa3-f0e7-49d9-ad31-498a73b603d6","resolution":{"observed_at":"2026-05-12T14:46:38.318892Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining , year =","venue":null,"work_id":"878337eb-a892-4928-9ecf-2fd5f25999e8","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:347a855394a548415768cdbdf8eda3f522aef899d228f961a82c95fabf424e98","observation_id":"1302918b-a1ab-4a72-8db5-19a30a6cd076","resolution":{"observed_at":"2026-05-12T14:46:38.310228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Versatune: An efficient data composition framework for training multi-capability llms , year =","venue":null,"work_id":"d27b46f2-64da-46a1-a855-c94aade86eb3","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:daba6d3a597c4674e81818c740ebcf531f10767559231e3ecf7a8cf64a8baedc","observation_id":"8db27d5d-5a9d-4c03-bc7d-0332d1fa8b80","resolution":{"observed_at":"2026-05-12T14:46:38.168850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7ace1b5c-2b68-40f8-9938-89178e637e70","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:7d5a237201104ee34c7352f1ae3db8a86fdcc2fef49654462ea491b893162e2b","observation_id":"6cd84087-b629-4afa-8c33-b9851d2c78ae","resolution":{"observed_at":"2026-05-12T14:46:38.209450Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"1fc08929-2b65-4cb0-a303-0540ddb00bee","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:5f13f0ae9dd2aea6ae27bb63c80b31d7ffcca63499bed7bbd5c8576393e707a7","observation_id":"cb2f933f-f42b-417d-b75d-deed7cd45f20","resolution":{"observed_at":"2026-05-12T14:46:38.188659Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections , url =","venue":null,"work_id":"17b189f9-4a6b-48f3-bb93-dde5e577d712","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:e4c983794efd4549b45b1fc21b7e0a367b5df0d2c85fa6cb1fdd43c01a412a05","observation_id":"f119bbea-6a29-4647-8692-48604cc10617","resolution":{"observed_at":"2026-05-12T14:46:38.246650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Xing , booktitle =","venue":null,"work_id":"9759e821-ec5c-4709-aee8-2ac49e819ea0","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:a6adad9ccfc2b8af27879fe91ba3c14ce5f53e66291ed45e1d7cfea17149b472","observation_id":"a03b3c92-9cb0-46d2-a700-7ac178c86c8e","resolution":{"observed_at":"2026-05-12T14:46:38.185301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ArXiv preprint , title =","venue":null,"work_id":"fa78309c-c806-4537-8327-e4239a8afcb6","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:ec6b2caea27790581d98c343c4a0a0e19e202caf6d8a206199ceb51aa60b2787","observation_id":"ea12b5cd-dba0-4ec1-9930-b657127dec90","resolution":{"observed_at":"2026-05-12T14:46:38.265511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models , url =","venue":null,"work_id":"294027fa-5ac6-4f52-9e00-63b56792b75d","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:dcd2bcd75fe6cc885f2e341a5d5368686cc0ffff79b3f933a616308dd89ce207","observation_id":"134463b0-7a9b-4d64-a41b-1b084fb05a77","resolution":{"observed_at":"2026-05-12T14:46:38.216448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods , url =","venue":null,"work_id":"a667961d-edfc-4a5a-b1df-896721a00573","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:a29a3f5167ba256192625cf5d0db6023a4996189b2a4e64a3a93a9029c846df2","observation_id":"9527403c-d48e-42fc-bac3-d848d2d2fb8d","resolution":{"observed_at":"2026-05-12T14:46:38.315918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Training Verifiers to Solve Math Word Problems , url =","venue":null,"work_id":"d389605e-0d95-4d92-b103-5437cfb47b49","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b3b83e4d1dbcde81e0501b3514af1e7ec7d449b9ab8d608b372b18a0e589e2fa","observation_id":"7d9c43f1-31b0-42e2-b425-aef0eefd27d5","resolution":{"observed_at":"2026-05-12T14:46:38.242889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hugging Face repository , title =","venue":null,"work_id":"e3571209-eb62-4bd2-ac13-a47ea9cb705d","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b1e58824f98b23e197c37c68337a69d604827f8b3ab609af0ad5833f928980ac","observation_id":"4af8d705-cc5a-40e5-b84c-22d852fb1ffe","resolution":{"observed_at":"2026-05-12T14:46:38.229843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement , url =","venue":null,"work_id":"73981144-dc72-4839-a663-0cff3f891e68","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:0a952550aab19ef78a51a6f4e08735e1b3886ff35c7dcab7c00a4a8fc3757c60","observation_id":"545ece4e-20e5-45bf-a5e2-0d03d292041f","resolution":{"observed_at":"2026-05-12T14:46:38.222761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Merrill and Tatsunori Hashimoto and Yejin Choi and Jenia Jitsev and Reinhard Heckel and Maheswaran Sathiamoorthy and Alexandros G","venue":null,"work_id":"d5e1f300-b1e6-451a-9759-5d5360836206","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:aa7ee5171d2d191564aa1ddbb7599018259996379ac3defe176474e4d8e94ba3","observation_id":"cfabcf33-96cc-4fef-902f-acccc0d4aeec","resolution":{"observed_at":"2026-05-12T14:46:38.275489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06619","last_updated":"2024-02-09T18:51:49Z","snapshot_observed_at":"2026-07-06T17:28:06.332906Z","submitted_at":"2024-02-09T18:51:49Z","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","version":1},"cited_work":{"arxiv_id":"2402.06619","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.06619","snapshot_observed_at":"2026-07-04T08:49:41.489739Z","title":"Aya dataset: An open-access collection for multilingual instruction tuning","venue":null,"work_id":"2079f91b-7b98-41b3-9ba2-2288a176981c","year":2024},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"cited_paper":"/paper/2402.06619","citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:2ebd68069b31eaaabec4522df20e72ca0e4aca26da23076e9f3bc0045984959d","observation_id":"bbba8e8c-2b13-430c-ac2a-90fdd8f79079","resolution":{"observed_at":"2026-05-12T06:11:24.258431Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"bcd90ee2-6c1e-4902-a47e-3bf093bea225","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:efcf7e8b6d16fa1fc3376147d5eca0f2c8d24083695b2e7f26d970293d3f19f7","observation_id":"b42cb9d5-8d45-47c2-8b2f-e10bb0fde688","resolution":{"observed_at":"2026-05-12T14:46:38.172139Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"RepLiQA","venue":null,"work_id":"70547816-64a0-472c-80eb-0f4fd119f0da","year":2024},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:86e8ea6066bc9defac9a1027fbeab924f080a6ec479d3ccf4e55fcf6093abe31","observation_id":"20bdb53c-b68f-4358-bd46-b11d66dfc405","resolution":{"observed_at":"2026-05-12T14:46:38.292698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"42c00673-7e58-4c7a-9b3d-40f20c3c0d01","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:5d38bf40384a948d71eeff3b3feff0f1891a0ca6210ade167c76bdc6f53e2553","observation_id":"418081e9-19fe-4f7e-8c6b-c366266c0075","resolution":{"observed_at":"2026-05-12T14:46:38.239748Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"tinyBenchmarks: evaluating LLMs with fewer examples , url =","venue":null,"work_id":"f21d8ad6-8b00-4f95-855d-6a808568b134","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:86048fb7321b8104da01a0edfa565e3531bae4f80682abc5f53b465f0ed18a7d","observation_id":"b1b6a590-0fb0-4202-a7ed-565d541fc5c0","resolution":{"observed_at":"2026-05-12T14:46:38.225975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"17eb055f-22c0-4ebe-a98e-943b3d203ec9","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:a0ad6624e42def12c538304a113abc35df99d43adb33a906bdca1c51a1c857d4","observation_id":"ba5fff0b-6608-4d74-9c26-fd41b725ef57","resolution":{"observed_at":"2026-05-12T14:46:38.219341Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3dd409a7-e714-4afd-ba99-0f622331a949","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:8ab0152b0cdb45737f2cbd53cd661a66328bcaa6258920bf3b97a25b3d32c877","observation_id":"1f97dc0b-87d7-42b7-8c74-0c91ba6e2125","resolution":{"observed_at":"2026-05-12T14:46:38.253034Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6bb27018-f9ee-44ba-9e76-e88caf09fd31","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:39300526c1bc2cf5f24ad388da0c5c24d4bd57634547fcaf8a59d2b9032f0827","observation_id":"e110e402-f374-40e5-909b-f84e2e1f6dbc","resolution":{"observed_at":"2026-05-12T14:46:38.195817Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"e8e7d48e-c600-4118-a140-1ac028d8e494","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:f202c0c6e77e157d09e17b62e1d3f393081e017c40fd054a6c4db90a64e3b81b","observation_id":"2f866cc2-dd4a-4ed3-9ce5-0d915f169351","resolution":{"observed_at":"2026-05-12T14:46:38.284516Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"bd5fa5d2-2e27-43b3-b02c-2f557d1c504f","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:9f86888d668004aa45fc0190c973a6ec738eae91209375255a29e5cc2ed1cbf3","observation_id":"df9337af-c55e-4d52-b5dd-a56d968c4b3c","resolution":{"observed_at":"2026-05-12T14:46:38.192041Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ef882abf-1cd5-4bbf-a000-340cf3f6d334","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:fc9023ab537541948a410b4d723e5dec31409d381784f789b066fa5520b4e1e5","observation_id":"673c74a4-538d-4805-a82a-a344cf504240","resolution":{"observed_at":"2026-05-12T14:46:38.272038Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"dd799f70-7362-402a-8ee4-ba88b701436a","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:f0edc28425e2905e6a1e91842da8b3080d8803802f6bf7fe50b52079a6343134","observation_id":"8a30905f-2235-4499-8b2b-0d7db9d4fca4","resolution":{"observed_at":"2026-05-12T14:46:38.178812Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"0e7038dc-2290-4cdd-98ca-7fec63b79494","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:83210d03e4a6df9e2f96b0964bb4d22f8fc0b92759b2e8d0e80c4d17782c8b9b","observation_id":"f4a7467a-d0f4-4c09-ae26-540717f03bcd","resolution":{"observed_at":"2026-05-12T14:46:38.332904Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c742ce08-a72e-4325-951a-b057d72a2eca","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:6191a158d33c9885828fc8c43f04fbd34de043f034dc7b3f01e15c466c23269e","observation_id":"2a40d41f-445b-422d-bc25-6becdd73ff76","resolution":{"observed_at":"2026-05-12T14:46:38.339001Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dynamic Gradient Alignment for Online Data Mixing , url =","venue":null,"work_id":"24f8cf91-5425-41f6-9d7e-29a3da5a1300","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b7dfce1638820b6085a1589000940a2b59accff56ae92fc2361eeae9b3991c04","observation_id":"3155c176-ef00-4351-b652-bd07fe4238ab","resolution":{"observed_at":"2026-05-12T14:46:38.259329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"09e4ff5d-0e23-4ceb-a953-0257e23b0b2a","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:b719f5952e4c1f75dc87c2023b36581d80a9ce756c97eeefdd991df986d6cf99","observation_id":"eb462469-cb11-4235-b535-9147fe7d694d","resolution":{"observed_at":"2026-05-12T14:46:38.325635Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T04:23:18.253167Z","title":"Hu and Yelong Shen and Phillip Wallis and Zeyuan Allen","venue":null,"work_id":"5f3b76ce-67a1-49da-ac99-25a0386159d3","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:f8efa1333de9501f72b9bdbc19a76f39962648b6c75e86672cb10075d5efcc82","observation_id":"bcd6cb83-5090-41a0-8cfb-62566e94d5cc","resolution":{"observed_at":"2026-05-12T14:46:38.295638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yu and Jianfeng Gao , journal =","venue":null,"work_id":"f0c18cc9-438d-4636-baea-ce8b11461bc3","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:acfd7d01f365de128e1a904a6d774b2fe0a6f699f869cde74f903bb56c395bbf","observation_id":"72cb2c68-c48e-4e6c-9bfd-9e3f1e029a0e","resolution":{"observed_at":"2026-05-12T14:46:38.213284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to Reweight Examples for Robust Deep Learning , url =","venue":null,"work_id":"2c2a8bdc-1c1f-4a38-a88c-1ec31aaa485d","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:13708c6955898a38a648fae4803bdedf6471b3f9568eb18566ee5c9ae6564791","observation_id":"a8707d44-054e-4aae-bf6b-ba78d9b3335a","resolution":{"observed_at":"2026-05-12T14:46:38.322121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T14:17:10.867087Z","title":"journal=","venue":null,"work_id":"ebf06be2-cfae-41b4-8eae-292a4739eb50","year":null},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:c764559fab636783e9cfd71250e9fbd59148091ef98c0229dd392b8d977df061","observation_id":"d8c4b7c5-5c1c-4fe2-949f-de5acfa35270","resolution":{"observed_at":"2026-05-12T14:46:38.175206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Biometrika , volume=","venue":null,"work_id":"57faddb5-3188-4b84-a124-e65008b91aac","year":1989},"citing_paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-05-12T04:31:27.945380Z"},"links":{"citing_paper":"/paper/2605.10770"},"observation_digest":"sha256:e8515fbfffa4bd7291f99fdadb39f4029270d9681d6c22669b52c931f67b8fe0","observation_id":"d15fcac9-de82-4d0b-a81a-5ba1cdf96832","resolution":{"observed_at":"2026-05-12T14:46:38.353172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.10770","last_updated":"2026-05-11T16:02:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T12:45:48.079503Z","submitted_at":"2026-05-11T16:02:05Z","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":2,"unresolved":14,"verified_exact":0,"verified_fuzzy":46},"total_outbound_references":64},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2605.10770."}