{"ID":5676020,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-04T22:27:51.222151465Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01517","arxiv_id":"2607.01517","title":"Parameter Golf: What Really Works?","abstract":"How far can a language model improve under a strict artifact budget? Parameter Golf posed this question as an open community challenge in which participants trained the best language model, with the complete artifact (training code + compressed weights) required to fit within 16 MB and be trained in under ten minutes on 8xH100 SXM GPUs. Quality was measured in bits-per-byte (BPB), the average number of bits required to encode each byte of unseen text. We analyze 2,037 pull requests and 1,430 clean scored submissions from the contest, build a taxonomy of 84 optimization techniques, and measure each technique's contribution to BPB. The verified leaderboard score dropped from 1.2244 to 1.058 BPB across three phases -- a 13.6% reduction, despite individual techniques rarely improving BPB by more than 1%. We show that most gains in techniques shrink across competitive submissions, isolating the few methods that improve performance across stacks.","short_abstract":"How far can a language model improve under a strict artifact budget? Parameter Golf posed this question as an open community challenge in which participants trained the best language model, with the complete artifact (training code + compressed weights) required to fit within 16 MB and be trained in under ten minutes o...","url_abs":"https://arxiv.org/abs/2607.01517","url_pdf":"https://arxiv.org/pdf/2607.01517v1","authors":"[\"Prashanna Mani Paudel\",\"Shivanand Venkanna Sheshappanavar\"]","published":"2026-07-01T22:29:40Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}