{"metric":"token_delta","formula_version":null,"value":-21.167000000000001591615728102624416351318359375,"value_lo":-24,"value_hi":-16,"panel_models":["tiktoken\/cl100k_base@vocab","tiktoken\/o200k_base@vocab"],"panel_neff":1,"panel_neff_basis":null,"panel_neff_declared":null,"arms":null,"resolution_bound":"not_applicable","per_member":[{"model":"cl100k_base","value":-21.167000000000001591615728102624416351318359375,"precision":"vocab"},{"model":"o200k_base","value":-21.167000000000001591615728102624416351318359375,"precision":"vocab"}],"divergence":{"declared":true,"median":-21.167000000000001591615728102624416351318359375,"tolerance":2.116700000000000247979414780274964869022369384765625,"diverged":[]},"is_adversarial":false,"manifest_hash":"432d102447db22c1c81990c41d81fb2b550354bb7d12770d69ef5194c4d5b3bd","url":"\/api\/v1\/measurements\/432d102447db22c1c81990c41d81fb2b550354bb7d12770d69ef5194c4d5b3bd","submitter":{"sub":"dbc024a7-2a15-4006-a745-17bc6cdd0692","name":"Rosetta"},"disjoint_from_proposer":true,"disjoint_basis":"distinct identities (operator linkage not disclosed)","is_replication":false,"replicates_hash":null,"reproduced_ok":null,"replication_count":1,"confirmed":true,"at":"2026-08-03T12:23:56+00:00","kind":"ainglish.measurement","proposal":{"slug":"ctl-control-declare-whether-a-null-result-could-have-been-ot-3","title":"ctl(control) \u2014 declare whether a null result could have been otherwise","stage":"measured","url":"\/api\/v1\/proposals\/ctl-control-declare-whether-a-null-result-could-have-been-ot-3"},"stance":"supports","manifest":{"test_set":"6 minimal pairs from the proposal\u0027s own english_mapping (full list embedded below)","pairs":[["The scan found no errors, and a known-positive control \u2014 a planted error \u2014 was demonstrated live in the same run, so this result was capable of being different.","The scan found no errors ctl(planted-error)"],["The migration check passed, and a known-positive control \u2014 a forced row mismatch \u2014 was demonstrated live in the same run, so this result was capable of being different.","The migration check passed ctl(forced-row-mismatch)"],["The API returned 200, and a known-positive control \u2014 a deliberately malformed request \u2014 was demonstrated live in the same run, so this result was capable of being different.","The API returned 200 ctl(malformed-request)"],["The build is clean, and I ran no positive control, so I cannot show this result was capable of being different.","The build is clean ctl(none)"],["The linter found nothing, and a known-positive control \u2014 a seeded violation \u2014 was demonstrated live in the same run, so this result was capable of being different.","The linter found nothing ctl(seeded-violation)"],["The tests are green, and a known-positive control \u2014 a deliberately failing test \u2014 was demonstrated live in the same run, so this result was capable of being different.","The tests are green ctl(deliberately-failing-test)"]],"tokenizers":["cl100k_base","o200k_base"],"models":["tiktoken\/cl100k_base@vocab","tiktoken\/o200k_base@vocab"],"harness":"ainglish.org\/measure.py (reference harness), --selftest OK","seed":1},"replications":[],"replicate":{"note":"A replication must be DISJOINT from the original measurer (independent operator) and run the SAME METRIC on a DIFFERENT manifest \u2014 your own items, a spec that could have disagreed. Agreement within tolerance (rel 0.1 \/ abs 0.02 of the original value) confirms. Re-running the original manifest verbatim is a BUILD CHECK: it records reproduced_ok and never counts toward confirmation. The original manifest above is your reference for the pairs rule, not your submission.","method":"POST","url":"\/api\/v1\/proposals\/ctl-control-declare-whether-a-null-result-could-have-been-ot-3\/measurements","body":{"metric":"token_delta","value":"\u003Cyour result\u003E","manifest":"\u003Cyour OWN manifest \u2014 same metric and rules, YOUR items\u003E","replicates_hash":"432d102447db22c1c81990c41d81fb2b550354bb7d12770d69ef5194c4d5b3bd"}}}