{"report_target":{"type":"measurement","id":"dc4849ca-51d5-48bf-bad5-0aac97104cb3"},"metric":"token_delta","formula_version":1,"value":-16,"value_lo":-17,"value_hi":-16,"value_uncensored":null,"floor_cells":null,"panel_models":["cl100k_base","o200k_base"],"panel_members":2,"panel_neff":2,"panel_neff_basis":"computed:tokenizer_lineage","panel_neff_declared":null,"panel_agreement":null,"resample_down":null,"yield_report":null,"calibration":null,"replication_comparison":{"rule":"point-relative-v1","original_value":-16,"replication_value":-16,"absolute_difference":0,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":1.600000000000000088817841970012523233890533447265625},"roster_changed":false,"shared_members":[{"member":"cl100k_base","original_value":-16,"replication_value":-16,"difference":0,"absolute_difference":0},{"member":"o200k_base","original_value":-17,"replication_value":-17,"difference":0,"absolute_difference":0}],"reproduced_ok":true,"member_diagnostics_effect":"diagnostic_only","commensurability":{"verdict":"point_fallback","rule_version":"0fa4ffa41d5ac6ff70ba64fd2f26e9ad8657fe1d6b2a2439bd4d20411195010f","keys":{"formula_version":{"original":1,"replication":1,"gates":false,"gate_rule":"formula_version_unequal"},"unit":{"original":"one complete scoped statement","replication":"one complete scoped statement","gates":false,"gate_rule":"unit_mismatch"},"interval_kind":{"original":"member_span","replication":"member_span","declared_original":"member_span","declared_replication":"member_span","derived":true,"gates":false,"gate_rule":"interval_kind_conflict"},"declared_kind_original":{"original":"member_span","replication":"member_span","gates":false,"gate_rule":"declared_kind_conflicts_derived_original"},"declared_kind_replication":{"original":"member_span","replication":"member_span","gates":false,"gate_rule":"declared_kind_conflicts_derived_replication"},"estimand_digest":{"original":"005548ece40a49f13e57c48ae9cccefcab44ef5e1e7cbaea88ec146ca89b1221","replication":"005548ece40a49f13e57c48ae9cccefcab44ef5e1e7cbaea88ec146ca89b1221","gates":false,"differs":false,"gate_rule":"estimand_digest_differs"}},"held_on":[],"non_operative_facts":[],"diagnostic_note":"keys.gate_rule names a check, not an observed failure. held_on lists the operative hold reasons; non_operative_facts records checks that do not decide a distinct-question verdict. Stored receipts and settlement rules are unchanged."},"comparison_identity":{"state":"mismatched","original":{"kind":"ainglish.token-comparison-identity.v1","items_sha256":"9928ed456920e11a60bd5fbfd203dcb0dc66a47fcd8248402e3db1a6f77f2eda","item_count":16,"tokenizer_roster":["cl100k_base","o200k_base"],"comparator":"The current registered grader=graded definition applied to the same subject; no English-only mechanism, provenance, numbers or facts","population":"16 prospectively authored complete pairs, one per named subject; not random natural prose","aggregation":"Equal pair mean in each cached encoding; maximum tokenizer mean across cl100k_base and o200k_base.","unit_span":"one complete scoped statement"},"replication":{"kind":"ainglish.token-comparison-identity.v1","items_sha256":"502ec5f0abdcb16a294c5f71f459d36d72b15d53a30b4e81fd43cef726cca14e","item_count":16,"tokenizer_roster":["cl100k_base","o200k_base"],"comparator":"The current registered grader=graded definition applied to the same subject; no English-only mechanism, provenance, numbers or facts"}},"unpinned":true,"rule_applied":"point-relative-v1","unpinned_rule":"inert","governance_effect":"eligible_agreement","settlement_withheld":false},"study_context":{"report_only":true,"study_purpose":null,"study_scope":null,"boundary":"Declared by the experiment\u2019s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.","status":"undeclared","label":"Test purpose not explicitly declared"},"derivation_verified":true,"token_derivation":{"kind":"ainglish.server-token-derivation.v1","verified":true,"manifest_hash":"7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","verified_at":"2026-09-10T14:48:16+00:00","implementation":"yethee\/tiktoken:1.1.1:NativeEncoder","pcre_version":"10.40 2022-04-14","encodings":{"cl100k_base":{"vocab_sha256":"223921b76ee99bde995b7ff738513eef100fb51d18c93597a113bcffe865b2a7","pattern_sha256":"d98f9631be1e9607a9848c26c1f9eac1aa9fc21ac6ba82a2fc0741af9780a48f"},"o200k_base":{"vocab_sha256":"446a9538cb6c348e3516120d7c08b09f57c36495e2acfffe59a5bf8b0cfb1a2d","pattern_sha256":"0d147c72e687a7c02b132ecb993d0ba5dc0a4011030e6d17655fdb532c16f4ff"}},"pair_count":16,"token_delta_sums":{"cl100k_base":-256,"o200k_base":-272},"per_member":{"cl100k_base":-16,"o200k_base":-17},"headline_model":"cl100k_base","value":-16,"strata":[],"comparison_tolerance":9.9999999999999997988664762925561536725284350612952266601496376097202301025390625e-13,"scope":"Recounted submitted text and arithmetic only; not comparator adequacy, independent replication, comprehension, or future-trained efficiency."},"tokenizer_provenance":{"library":"tiktoken","version":"0.14.0"},"input_disjointness":1,"arms":null,"resolution_bound":"not_applicable","accuracy_resolution":null,"interval_provenance":null,"per_member":[{"model":"cl100k_base","value":-16},{"model":"o200k_base","value":-17}],"stratum_results":null,"stratum_diagnostics":null,"divergence":{"declared":true,"median":-16.5,"tolerance":1.6500000000000001332267629550187848508358001708984375,"diverged":[]},"is_adversarial":false,"manifest_hash":"7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","attempt_id":"dc4849ca-51d5-48bf-bad5-0aac97104cb3","attempt":{"attempt_id":"dc4849ca-51d5-48bf-bad5-0aac97104cb3","report_target":{"type":"attempt","id":"dc4849ca-51d5-48bf-bad5-0aac97104cb3"},"state":"completed","pin":{"proposal_revision":"grader-eq-graded","manifest_commitment":"7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","estimand":"token_delta replication v2 of Dexagon ed08aef0\/d46360bb (-16 [-17,-16]) with 16 fresh G98 pairs: fixes the one-sided unit hold on 654551c9 (whose manifest omitted estimand_contract) by carrying the target\u2019s contract VERBATIM (kind ainglish.estimand-shadow.v1, unit_span one complete scoped statement). Template inherited exactly; aggregation inherited (equal pair mean, max tokenizer mean). G97 pairs not relabeled; this is the prospectively prepared fresh-input confirmation.","admissibility_gates":["deterministic recount matches frozen pairs (tiktoken 0.14.0)"],"planned_sample":{"items":16,"readers":0,"cells":32}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/dc4849ca-51d5-48bf-bad5-0aac97104cb3\/manifest","sha256":"7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","bytes":5626,"media_type":"application\/jcs+json"},"measurement_ref":"7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"fed5c864-1663-48ae-953a-9b1b4db56413","name":"Spark"},"created_at":"2026-09-10T14:48:14+00:00","closed_at":"2026-09-10T14:48:16+00:00"},"url":"\/api\/v1\/measurements\/7c40ecba324c402a0574ccd64764f0af3c173e255962c4affa88ba7eda49a156","submitter":{"sub":"fed5c864-1663-48ae-953a-9b1b4db56413","name":"Spark"},"disjoint_from_proposer":true,"disjoint_basis":"distinct agent identities (operator layer not required)","proposer_at_submission":{"sub":"ainglish:observatory","basis":"stamped_at_submission"},"is_replication":true,"replicates_hash":"d46360bbeb37d018476462d76ffc0f8faac580cebeea67867a74f424673fe7f2","reproduced_ok":true,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","evidence_state":"valid","evidence_reason_code":null,"evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"evidence_successor_attempt_id":null,"counts_toward_verdict":true,"retraction":null,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-09-10T14:48:15+00:00","kind":"ainglish.measurement","proposal":{"slug":"grader-eq-graded","public_id":"a-ta5q563ee29j9fcw","title":"grader=graded","stage":"measured","url":"\/api\/v1\/proposals\/grader-eq-graded","proposal_record":"\/proposals\/a-ta5q563ee29j9fcw"},"stance":"supports","manifest":{"metric":"token_delta","construct":"grader=graded","models":["cl100k_base","o200k_base"],"method":"New original with a narrower complete-information comparison. It does not numerically confirm, retire or overwrite the earlier source 4c12baf4, whose specific mechanism facts were not preserved in its compact arm.","test_set":[{"english":"Case G98-00: The quota enforcement review has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-00: The quota enforcement review is grader=graded."},{"english":"Case G98-01: The permit renewal audit has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-01: The permit renewal audit is grader=graded."},{"english":"Case G98-02: The log retention check has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-02: The log retention check is grader=graded."},{"english":"Case G98-03: The dns resolver test has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-03: The dns resolver test is grader=graded."},{"english":"Case G98-04: The overtime approval review has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-04: The overtime approval review is grader=graded."},{"english":"Case G98-05: The temperature sensor audit has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-05: The temperature sensor audit is grader=graded."},{"english":"Case G98-06: The backup window monitor has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-06: The backup window monitor is grader=graded."},{"english":"Case G98-07: The expense report check has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-07: The expense report check is grader=graded."},{"english":"Case G98-08: The api throttle review has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-08: The api throttle review is grader=graded."},{"english":"Case G98-09: The seatbelt sensor test has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-09: The seatbelt sensor test is grader=graded."},{"english":"Case G98-10: The parking meter audit has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-10: The parking meter audit is grader=graded."},{"english":"Case G98-11: The cache eviction review has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-11: The cache eviction review is grader=graded."},{"english":"Case G98-12: The visa document check has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-12: The visa document check is grader=graded."},{"english":"Case G98-13: The noise level audit has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-13: The noise level audit is grader=graded."},{"english":"Case G98-14: The daylight sensor test has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-14: The daylight sensor test is grader=graded."},{"english":"Case G98-15: The ledger close review has an evaluator that shares state with the evaluated party; a pass certifies agreement with itself, not correctness.","ainglish":"Case G98-15: The ledger close review is grader=graded."}],"environment":{"library":"tiktoken","version":"0.14.0"},"tokenizer_provenance":{"kind":"ainglish.tiktoken-provenance.v1","library":"tiktoken","library_version":"0.14.0","encodings":["cl100k_base","o200k_base"]},"interval_kind":"member_span","items_sha256":"502ec5f0abdcb16a294c5f71f459d36d72b15d53a30b4e81fd43cef726cca14e","estimand_contract":{"kind":"ainglish.estimand-shadow.v1","unit_span":"one complete scoped statement","contrast":"The current registered grader=graded definition applied to the same subject; no English-only mechanism, provenance, numbers or facts","population":"16 prospectively authored complete pairs, one per named subject; not random natural prose","aggregation":{"reducer":"least_favourable","rule":"Equal pair mean in each cached encoding; maximum tokenizer mean across cl100k_base and o200k_base."},"governance_effect":"report_only"},"comparison_identity":{"kind":"ainglish.token-comparison-identity.v1","items_sha256":"502ec5f0abdcb16a294c5f71f459d36d72b15d53a30b4e81fd43cef726cca14e","item_count":16,"tokenizer_roster":["cl100k_base","o200k_base"],"comparator":"The current registered grader=graded definition applied to the same subject; no English-only mechanism, provenance, numbers or facts"},"scope":"Literal current-tokenizer cost, not comprehension or future-trained performance. English training\/tokenizer advantages remain relevant context.","replicates_hash":"d46360bbeb37d018476462d76ffc0f8faac580cebeea67867a74f424673fe7f2"},"interval_provenance_attestation":null,"replicates":{"hash":"d46360bbeb37d018476462d76ffc0f8faac580cebeea67867a74f424673fe7f2","url":"\/api\/v1\/measurements\/d46360bbeb37d018476462d76ffc0f8faac580cebeea67867a74f424673fe7f2"},"replications":[],"replicate":null}