{"name":"keplearn","repo":"owls-on-wires/keplearn","url":"https://midorreal.com/project/owls-on-wires-keplearn","repository":"https://github.com/owls-on-wires/keplearn","description":"Symbolic regression in seconds.","facts":{"license":{"value":"MIT","source":"https://github.com/owls-on-wires/keplearn","checked":"21 Nov 2026"},"language":{"value":"Rust","source":"https://github.com/owls-on-wires/keplearn","checked":"21 Nov 2026"},"last_release":{"value":"v2.1.2, 21 Nov 2026","source":"https://github.com/owls-on-wires/keplearn/releases","checked":"21 Nov 2026"},"releases":{"value":"19","source":"https://github.com/owls-on-wires/keplearn/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/owls-on-wires/keplearn/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/owls-on-wires/keplearn","checked":"21 Nov 2026"}},"stars":150.0,"writeup":{"what_it_is":"Keplearn is a symbolic regression engine written in Rust. It reads tabular data from stdin and prints candidate closed-form equations as JSON. It is distributed as a single binary with no dependencies.","audience":"Researchers and engineers finding closed-form equations in tabular measurement data","claims":[{"kind":"specific","claim":"Ships as a single binary with zero dependencies","excerpt":"Single binary, zero dependencies (fully static with the musl target)","status":"not_checked"},{"kind":"specific","claim":"Output is deterministic: the same input produces the same output","excerpt":"Deterministic; the same input produces the same output, byte for byte","status":"not_checked"},{"kind":"specific","claim":"Reported r2 is computed from the printed equation itself","excerpt":"The reported `r2` is computed from the printed equation itself, never","status":"not_checked"},{"kind":"specific","claim":"Achieves 64.7% symbolic solution rate on the Feynman suite at noise 0 in SRBench","excerpt":"Feynman (116) | 75 (64.7%) | 65 (56.0%)","status":"not_checked"},{"kind":"broad","claim":"Exact laws usually resolve in milliseconds","excerpt":"exact laws usually resolve in\n  milliseconds","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-30"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":98,"reality":58,"gap":40,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T09:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":23,"gap_high":62,"rule":"early-2.0"},"changes":[{"date":"2026-11-21T01:39:04+00:00","text":"Latest release v2.1.2","source":"https://github.com/owls-on-wires/keplearn/releases"},{"date":"2026-09-13T02:02:18+00:00","text":"First release","source":"https://github.com/owls-on-wires/keplearn/releases"},{"date":"2026-09-13T01:03:41+00:00","text":"Repository created","source":"https://github.com/owls-on-wires/keplearn"}],"cite":"keplearn is a GitHub project at https://github.com/owls-on-wires/keplearn written mainly in Rust, described there as \"Symbolic regression in seconds\".","attribution":"Data from Mid or Real, https://midorreal.com/project/owls-on-wires-keplearn, checked 22 November 2026. Attribution with a link is required.","still_real":null}