Edition of Friday 13 November 2026

93% on RepoMod-Bench: porting 200K-line codebases with a proof in the loop

Comments on “93% on RepoMod-Bench: porting 200K-line codebases with a proof in the loop”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

Bosun reports that its Parity-based workflow passed 93% of hidden tests across 21 RepoMod-Bench repository ports (88% on the twelve 50K-plus-line cases), versus 48% for the paper's best published agent and 74% for the paper's Codex setup run on the newer Sol model.

Read the original at blog.bosun.ai. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 92 of 137 with a score of 0.60. The panel rated it highest on new information (0.91) and substantiated (0.83), lowest on audience breadth (0.61). The judges disagreed most on promotional (spread 0.46), so the story is marked contested. Placed No. 92, No. 71 by score alone: the eleventh Programming & dev tools story of the day (−0.080), and close to “Terminal-Bench 4.1: 23 of 66 tasks have scoring or data problems”, No. 5 on Wednesday 11 November 2026 (−0.013). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Benchmark results for AI agent code porting with a vendor-promotional framing; substantive numbers and public data, but self-reported, vendor-run, with heavy product pitch and some overclaiming.
AI judgeJudge 3gpt-5.6-luna
A detailed, reproducible evaluation of agent-assisted cross-language porting, with public transcripts, proofs, code, controls, costs, and limitations. Strongly actionable for software teams, though best-of-three reporting, regrading, and a demo CTA temper confidence.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.60total under rubric v2.3Contestedjudges differ by 0.46 on promotional

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.64
  • Reader interest0.76
  • Audience breadth0.61
  • Practical relevance0.72
  • Substantiated0.83
  • Technical depth0.80
  • New information0.91
  • Counts against: Promotional0.35
  • Counts against: Overclaim0.44

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.700.450.780.640.33+0.24+0.154
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.750.600.920.760.32+0.26+0.197
Audience breadthHow many people who build technology does it concern?0.630.500.700.610.20+0.13+0.079
Practical relevanceHow useful is it to someone who builds software or tech products?0.760.550.860.720.31+0.22+0.159
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.980.600.900.830.38+0.05+0.041
Technical depthHow technically substantive is it?0.910.600.880.800.30+0.05+0.040
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.860.900.980.910.12+0.05+0.046
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.140.600.300.350.46 , above the contested threshold−0.19−0.066
OverclaimDo the headline or conclusions claim more than the body supports?0.350.600.380.440.25−0.11−0.049
Sum of contributions+0.602
Claim-check penalty0.000
Total, as published0.602

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #92 on Rubric, 13 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-13/92/"><img src="https://rubric.hrih.si/badge/2026-11-13/92.svg" alt="Ranked #92 on Rubric, 13 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:42 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “93% on RepoMod-Bench: porting 200K-line codebases with a proof in the loop”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.75

    llama.cpp v1.0