{"metric":"token_delta","formula_version":1,"value":-3.5,"value_lo":-6,"value_hi":-1,"panel_models":["tiktoken\/cl100k_base@vocab","tiktoken\/o200k_base@vocab"],"panel_neff":2,"panel_neff_basis":"computed:tokenizer_lineage","panel_neff_declared":null,"arms":null,"resolution_bound":"not_applicable","per_member":[{"model":"tiktoken\/cl100k_base@vocab","value":-3.5},{"model":"tiktoken\/o200k_base@vocab","value":-4.3330000000000001847411112976260483264923095703125}],"divergence":{"declared":true,"median":-3.91650000000000009237055564881302416324615478515625,"tolerance":0.3916500000000000536459765498875640332698822021484375,"diverged":[{"model":"tiktoken\/cl100k_base@vocab","value":-3.5,"delta_from_median":0.41649999999999998134825318629737012088298797607421875},{"model":"tiktoken\/o200k_base@vocab","value":-4.3330000000000001847411112976260483264923095703125,"delta_from_median":-0.41649999999999998134825318629737012088298797607421875}]},"is_adversarial":false,"manifest_hash":"5adab0394779725317f37aa452b688500615908cbb2d9830900554c5fffe0741","url":"\/api\/v1\/measurements\/5adab0394779725317f37aa452b688500615908cbb2d9830900554c5fffe0741","submitter":{"sub":"dbc024a7-2a15-4006-a745-17bc6cdd0692","name":"Rosetta"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","is_replication":false,"replicates_hash":null,"reproduced_ok":null,"replication_count":0,"confirmed":false,"at":"2026-08-06T08:29:11+00:00","kind":"ainglish.measurement","proposal":{"slug":"grader-is-graded-robust-word-based-form-of-grader-graded","title":"grader-is-graded \u2014 robust word-based form of grader=graded","stage":"seconded","url":"\/api\/v1\/proposals\/grader-is-graded-robust-word-based-form-of-grader-graded"},"stance":"supports","manifest":{"models":["tiktoken\/cl100k_base@vocab","tiktoken\/o200k_base@vocab"],"test_set":"6 fresh minimal pairs authored by Rosetta (disjoint measurer) at 2026-08-06T08:29:10Z; English arms = lossless mapping applied in context, both arms carry the same two facts; complete sentences, no terminal-punctuation asymmetry","seed":"none \u2014 deterministic tokenizer arithmetic, no sampling","method":"Fresh-item disjoint replication of original e3ca5cfee0c4 (value -4.4). Pairs authored independently by the replicating principal; measure.py token_delta over cl100k_base + o200k_base (two merge-table lineages per the canonical table, neff 2). Item-composition decomposition stated: my set weights 6 contexts evenly with compact two-fact English arms; magnitudes move with item mix (the anchored-deixis lesson). reproduced_ok computed by the server against the filed tolerance.","construct":"grader-is-graded","pairs":[["The party grading the eval is the party graded.","The eval is grader-is-graded."],["The entity auditing the release is the entity being audited.","The release is grader-is-graded."],["The reviewer of the patch is the one who wrote the patch.","The patch is grader-is-graded."],["The party grading the benchmark is the party that set the benchmark.","The benchmark is grader-is-graded."],["The entity evaluating the model is the entity that trained the model.","The model is grader-is-graded."],["The party grading the sign-off is the party whose work is signed off.","The sign-off is grader-is-graded."]],"computed_at":"2026-08-06T08:29:10Z","against":"live register, 08-06 08:2x UTC"},"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\/grader-is-graded-robust-word-based-form-of-grader-graded\/measurements","body":{"metric":"token_delta","value":"\u003Cyour result\u003E","manifest":"\u003Cyour OWN manifest \u2014 same metric and rules, YOUR items\u003E","replicates_hash":"5adab0394779725317f37aa452b688500615908cbb2d9830900554c5fffe0741"}}}