Formalizing the US Tax Code
Comments on “Formalizing the US Tax Code”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
Lexifina, a legal-data startup, translated the 2025 individual income tax into Lean with AI and compared it against PolicyEngine-US, Tax-Calculator and UsTaxes on 5,000 synthetic households. It reports 138 drafting faults in Title 26, agreement with PolicyEngine on 4,993 households, and bugs in the other tools, plus three small unpublished loopholes. Most figures are the author's own and unverified; the AI-run triage has had no lawyer or CPA review, and agreement among calculators does not show correctness. The model covers one tax year.
Why it ranked
No. 21 of 106 with a score of 0.64. The panel rated it highest on new information (0.93) and substantiated (0.90), lowest on audience breadth (0.51). Placed No. 21, No. 33 by score alone: the placement terms moved other stories past it.
- AI judgeJudge 2claude-haiku-5-5
- Formal verification of the US tax code with 138 real drafting faults and a validated model; technically deep and substantiated, but narrow audience and mostly policy/tax-focused rather than core builder work.
- AI judgeJudge 3gpt-5.6-luna
- A detailed, reproducible engineering and research account applying Lean, AI translation, cross-tool testing, and exhaustive search to tax law, with quantified findings, code claims, limitations, and several potentially novel results.
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
0.64total under rubric v2.3
- Significance0.61
- Reader interest0.75
- Audience breadth0.51
- Practical relevance0.59
- Substantiated0.90
- Technical depth0.87
- New information0.93
- Counts against: Promotional0.06
- Counts against: Overclaim0.23
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.55 | 0.45 | 0.82 | 0.61 | 0.37 | +0.24 | +0.146 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.59 | 0.70 | 0.97 | 0.75 | 0.38 | +0.26 | +0.196 |
| Audience breadthHow many people who build technology does it concern? | 0.51 | 0.40 | 0.62 | 0.51 | 0.22 | +0.13 | +0.066 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.53 | 0.45 | 0.78 | 0.59 | 0.33 | +0.22 | +0.129 |
| 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. | 0.95 | 0.85 | 0.91 | 0.90 | 0.10 | +0.05 | +0.045 |
| Technical depthHow technically substantive is it? | 0.88 | 0.85 | 0.88 | 0.87 | 0.03 | +0.05 | +0.043 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.91 | 0.90 | 0.99 | 0.93 | 0.09 | +0.05 | +0.047 |
| 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. | 0.06 | 0.10 | 0.01 | 0.06 | 0.09 | −0.19 | −0.011 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.32 | 0.30 | 0.08 | 0.23 | 0.24 | −0.11 | −0.026 |
| Sum of contributions | +0.636 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.636 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-11-12/21/"><img src="https://rubric.hrih.si/badge/2026-11-12/21.svg" alt="Ranked #21 on Rubric, 12 Nov 2026" width="245" height="28"></a>Claim check
Claim check: 1 matches source · 6 no source given · 1 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Couldn’t checkNumber
The authors' test suite on Title 26 of the US Code reports 257 findings, of which 138 are real drafting faults, 98 intended and 21 false alarms in the editors' hyperlinks.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “The suite reports 257 findings, each checked by an AI agent against the official text and its editorial notes: 98 intended”
The source says No passage could be compared.
Source cited by the article: uscode.house.gov/download/download.shtml
No source givenNumber
Under the 2025 SALT cap rules, a couple earning $300,000 each can deduct up to $25,000 on two separate returns but only $10,000 on one joint return.
The article gives no link or citation for it.
The article says “A couple earning $300,000 each can deduct up to $25,000 on two separate returns, but only $10,000 on one joint return”
The source says No source to compare with.
Matches sourceNumber
A family with three children can lose its whole EITC, up to $8,046, because its investment income is one dollar over $11,950.
The cited source says the same thing.
The article says “A family with three children can lose its whole EITC, up to $8,046, because its investment income is one dollar over $11,950”
The source says “You can’t claim the EIC unless your investment income is $11,950 or less. If your investment income is more than $11,950, you can’t claim the credit”
Source cited by the article: irs.gov/publications/p596
No source givenBenchmark result
The authors' model and PolicyEngine-US agreed on every figure for 4,993 of 5,000 households, with the other seven differing by at most $11, all in the EITC.
The article gives no link or citation for it.
The article says “Our model and PolicyEngine-US agreed on every figure for 4,993 of the 5,000 households. The other seven differ by at most $11, all in the EITC”
The source says No source to compare with.
No source givenNumber
UsTaxes had 14 bugs, which together affect about one ordinary household in six.
The article gives no link or citation for it.
The article says “UsTaxes had 14 bugs, each confirmed by recalculating an affected household”
The source says No source to compare with.
No source givenCausal conclusion
Tax-Calculator gives the EITC to married people filing separately without checking that the spouses lived apart, which the law requires.
The article gives no link or citation for it.
The article says “Tax-Calculator gave the EITC and the child and dependent care credit to married people filing separately without checking that the spouses lived apart, which the law requires”
The source says No source to compare with.
No source givenNumber
Filing separately can cut tax on Social Security benefits for a couple living together: with $48,000 of benefits and a $60,000 wage, the couple owes $7,050 jointly and $5,568 separately.
The article gives no link or citation for it.
The article says “With $48,000 of benefits and a $60,000 wage, the couple owes $7,050 jointly and $5,568 separately, $1,482 less”
The source says No source to compare with.
No source givenGeneralization
Everything large that the two searches found is already described in the planning literature, so the search found no novel large multi-year loophole.
The article gives no link or citation for it.
The article says “Everything large that the two searches found is already in the planning literature”
The source says No source to compare with.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 7 pts, not on front page
Recorded for context only, checked 12 Nov 2026, 05:47 UTC. It played no part in the ranking.