Transparency

Measured costs

What this has cost, measured from each model call's own usage block rather than estimated. The line that matters most is the one nobody enjoys publishing: work that produced nothing and was paid for anyway.

Evidence chain verified. 1424 records, head 85702a792688998a…. Every action is hash-chained to the one before it; a reader can recompute the chain from the raw log below.

$2.5448

total measured spend

525

priced model calls

64

ledger entries

0

entries with incomplete cost

By what the money was for

scopespendwhat it covers
paper_read$1.9188reading a paper (five stages: reader A, reader B, critic, checker, prior-art gate)
unattributed$0.2837recorded before costs carried a scope label
reanalysis$0.1293bounded re-analysis of a paper’s reported values
checker_probe$0.0820adversarial probes against the independent claim checker
reanalysis_void$0.0521re-analysis whose output was discarded by an instrument bug, and paid for anyway
gate_variance$0.0520measuring how much the prior-art verdict moves on identical evidence
scout$0.0269locating gaps and generating hypotheses

A lower bound is still a measurement, and an unmeasured call is not. Where a call's cost could not be priced, the entry is counted and flagged rather than dropped or averaged in — the flag count is published above.

Every ledger entry (64)

seqscopecallsspendnote
1418reanalysis2$0.0192H51 analyst + verifier
1414scout2$0.0044scout proposal + prior-art gate calls
1407scout2$0.0085scout proposal + prior-art gate calls
1393paper_read5$0.0481all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1368paper_read5$0.0378all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1343paper_read5$0.0439all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1318paper_read5$0.0512all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1293paper_read5$0.0365all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1263paper_read5$0.0299all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1238paper_read5$0.0365all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1213paper_read5$0.0464all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1188paper_read5$0.0406all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1163paper_read5$0.0499all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1138paper_read5$0.0570all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1113paper_read5$0.0359all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1088paper_read5$0.0352all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1063paper_read5$0.0622all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1038paper_read5$0.0291all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1013paper_read5$0.0493all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
988paper_read5$0.0448all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
963paper_read5$0.0339all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
938paper_read5$0.0467all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
913paper_read5$0.0363all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
888paper_read5$0.0365all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
863paper_read5$0.0630all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
838paper_read5$0.0449all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
813paper_read5$0.0378all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
788paper_read5$0.0316all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
763paper_read5$0.0421all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
738paper_read5$0.0320all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
713paper_read5$0.0424all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
688paper_read5$0.0401all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
663paper_read5$0.0478all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
638paper_read5$0.0520all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
613paper_read5$0.0622all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
588paper_read5$0.0285all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
563paper_read5$0.0372all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
538paper_read5$0.0307all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
513paper_read5$0.0740all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
488paper_read5$0.0297all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
463paper_read5$0.0363all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
408paper_read5$0.0468all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
376paper_read5$0.0490all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
351paper_read5$0.0690all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
326paper_read5$0.0517all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
301paper_read5$0.0443all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
276paper_read5$0.0383all calls measured; 3 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
245cost_correction → corrects reanalysis0$-0.0013recorded $0.111391; measured $0.110121 (main run $0.100981 + H24/H30 rerun $0.009140)
244cost_correction → corrects reanalysis_void0$-0.0759recorded $0.128007 by summing overlapping per-record usages; the run measured $0.052062
243cost_correction → corrects cost_correction0$0.0772reverse the combined correction; the same money is re-applied below against the scopes that were wrong
242cost_correction0$-0.0772negative correction: the re-analysis per-record usage figures double-counted because usage was attributed with sumUsage(usages.slice(-2)) over a run-wide accumu
241reanalysis_void15$0.1280backfilled by cost reconciliation: summed from the 7 void re-analysis records themselves; the output was discarded by a property-name bug but the calls were pai
240reanalysis4$0.0104backfilled by cost reconciliation: run-reanalysis.mjs --only H24,H30 re-run to correct the recorded reason
239reanalysis14$0.1010backfilled by cost reconciliation: run-reanalysis.mjs first successful run: 7 hypotheses x 2 passes, $0.100981
238gate_variance13$0.0520backfilled by cost reconciliation: scripts/gate-variance.mjs run, 2026-09-14: 13 adjudicator calls, $0.052 (commit ba8e352)
237checker_probe215$0.0820backfilled by cost reconciliation: scripts/checker-probe.mjs run, 2026-09-14: 215 probes, $0.082 (commit e9e6337)
236scout3$0.0140backfilled by cost reconciliation: run-scout.mjs final cost lines, both scout runs plus the gate: $0.0067 + $0.0073 measured by the runs themselves
2085$0.0398all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1835$0.0407all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1345$0.0470all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
1095$0.0438all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
705$0.0353all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
465$0.0360all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound
225$0.0411all calls measured; 5 call(s) read from cache with cached tokens priced at zero in the rate card, so the total is a lower bound

Machine-readable: /society/costs.json.