Weekly ranking, Technology
Git for the US Code | Lexifina
84Original Thinker
A product write-up with original validation data (361 of 365 changes reproduced) and a concrete retroactivity example, though the cited LLM studies are unsourced.
What it adds
The piece validates a replayed, effective-date-tagged US Code history against official release points, with its own reproduction statistics. It uses the 2022 subchapter V gap to show why retroactivity matters for point-in-time text.
Claim by claim
- 6 the author's own
- 0 an AI would say
- 0 known elsewhere
- 6 common knowledge
Its strongest original claims
- Lexifina replayed amending instructions of public laws between each pair of release points from 2017 onward and compared results to the newer release point.
- Of 365 changes across nine titles, 361 reproduced the next release point exactly.
- 261 changes took effect on enactment by default, 72 by an effective-date note and 29 by a date in the amendment itself.
- A TUM study found a model answered 24% of post-cutoff German statute questions correctly alone and 87% with retrieved text.
- LLMs applying German amending laws produced 93–99% similar text but only half of single amendments and a fifth of chains matched exactly.
Scored by Expulp Verdict for what the piece adds beyond what is already known and published. The full verdict shows every claim with its reasons. Leaderboard, what Verdict gets right and where it is weak.