--- title: "court-report-statistics — Mova code model" description: "Mova code model of yom-hadin/src/report.rs: components with their labels, obernants and the model text." url: "https://groupants.elamur.ai/free/en/mova/yom-hadin/src/report.rs.groupant/statistics.groupant/" --- Elamur: [Mova](https://md.mova.elamur.ai/free/en/) · [Dictionary](https://md.dictionary.elamur.ai/free/en/) · [Research](https://md.research.elamur.ai/free/en/) · **Groupants** This page as HTML: # court-report-statistics The groupant beside yom-hadin/src/report.rs in the Mova repository: what the code computes, what it never does, how to go back from its outputs, its invariants, cost and checks. ## Facts - **kind:** groupant_fragment - **status:** partial source derived models - **source:** [`yom-hadin/src/report.rs`](https://github.com/ElamurAI/mova-free/blob/main/yom-hadin/src/report.rs) - **source SHA-256:** `eb60c61212e8f64a…` - **covers:** Weighted severity statistics and midpoint percentile. (bytes 6210–7468) - **part of:** [court-report](https://md.groupants.elamur.ai/free/en/mova/yom-hadin/src/report.rs.groupant/) - **repository folder:** [`yom-hadin/src/report.rs.groupant/statistics.groupant`](https://github.com/ElamurAI/mova-free/tree/main/yom-hadin/src/report.rs.groupant/statistics.groupant) - **repository commit:** `855da7bd4a7b` > **Implementation material.** A Mova code model describes this code at one source revision: partial models, finite checks and their stated scope. It is not a reviewed general exposition, and its labels are shown as written, never raised. ## Components | component | label | where | |---|---|---| | **approximant** | partial | [approximant](#approximant) | | **ast** | partial | `../syntax.json` | | **cost** | partial | `model.md` | | **descriptant** | present | [descriptant](#descriptant) | | **invariant** | partial | [Invariant](#invariant) | | **tests** | finite native checks | [tests](#tests) | ## Obernants The typed relations around the forward model: the behaviour complement (what the code never does), the reverse reconstruction (every input compatible with an output) and specialised views. | id | type | label | where | |---|---|---|---| | `behavior_complement` | behavior_complement | partial source derived model | [behavior_complement](#behavior-complement) | | `reverse_reconstruction` | reverse_reconstruction | partial source derived model | [reverse_reconstruction](#reverse-reconstruction) | | `milder_modal_tie` | milder_modal_tie | partial source derived model | [milder_modal_tie](#milder-modal-tie) | | `epsilon_quantile` | epsilon_quantile | partial source derived model | [epsilon_quantile](#epsilon-quantile) | | `percentile_midrank` | percentile_midrank | partial source derived model | [percentile_midrank](#percentile-midrank) | | `finite_domain` | finite_domain | partial source derived model | [finite_domain](#finite-domain) | ## Model text ### descriptant #### Weighted severity statistics and midpoint percentile. ##### Epoch 2026-10-31 Prospective review preceded test edits. Runtime logic unchanged; three sources gain tests. Synthetic witnesses do not validate legal conclusions. Composition: Aggregate by sorted severity, modal strict-greater first tie, quantiles first cumulative threshold, percentile below plus half equal. Retained limits: partial syntax, opaque macros; no live corpus, teacher, parser model, production filesystem or frozen gold. Complete semantics and executable approximants remain open. ### approximant #### Forward model Weighted severity statistics and midpoint percentile. Aggregate by sorted severity, modal strict-greater first tie, quantiles first cumulative threshold, percentile below plus half equal. Not an executable substitute. Percentage approximation is unsupported without a useful metric; future profiles limited to 1/2/5/10% require actual-reference comparison. ### models ## Typed models: Weighted severity statistics and midpoint percentile. Subject: yom-hadin/src/report.rs, SHA-256 eb60c61212e8f64ad0b3c67ed5dfbd9623e384479ec54567ed762cc8504b58ff. Domain: bounded finite synthetic rules/cases; valid indices and successful allocation unless a section narrows this. Each relation observes implementation, not legal authority. Status: partial source-derived model, finite evidence mapped in tests.md. ### behavior_complement Empty stats cannot return Some; finite positive weights cannot give percentile outside0..100. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### reverse_reconstruction Given summary, compatible weight histograms satisfy modal inequalities and cumulative quantile crossings; row permutations and subdivided equal-class weights are nonunique preimages modulo summation rounding. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### milder_modal_tie BTree order ascending severity plus strict > chooses lower class for equal aggregate weights. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### epsilon_quantile Threshold p*total-1e-9 deliberately admits earlier crossing; tiny totals may select even zero-mass lowest key. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### percentile_midrank Percentile=100*(weight below + weight equal/2)/total, so tied mass sits midpoint; no interpolation across absent classes. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### finite_domain Functions do not reject negative/NaN/infinite weights; these are outside admitted statistical interpretation, not promised errors. Operator: stated relation on this source projection. Assumptions: named domain and unchanged dependencies. Evidence: tests.md maps finite observations; other branches remain source review only. ### tests #### Checks and evidence External run label: octopus-wave31-court-2026-10-31; exact commands in native-commands.json, per-source observations in source-test-map.json, numeric exits and named outcomes in raw logs. 19 exact selected native tests twice debug and twice release execute actual linked code on bounded hand-built cases. CLI covers argument helpers only. Full extraction/model initialization, actual jurisdiction loading, protocol disk errors, resource exhaustion and malformed public lattices are unexecuted. Module declarations have compile evidence only. Three compiled source-behavior mutants: count weight, precedence tie, modal tie; each requires compile success, named assertion failure, exact byte/hash restoration and positive rerun. Legacy fixture interventions count separately. Final observations: external evidence-summary.md. This node observes: Weighted severity statistics and midpoint percentile.. Unmapped models remain source-derived/prospective, not verified by the whole test count. Parent source witness map: [source-evidence.md](https://md.groupants.elamur.ai/free/en/mova/yom-hadin/src/report.rs.groupant/#source-evidence). Only the described fragment observation is supported; parent test names do not imply every fragment branch executed. ### invariant-and-cost ## Invariant and cost ### Invariant For finite nonnegative weights and positive finite total, returned classes are observed; zero-total stats None and percentile0. ### Cost O(N log K) stats and O(N) percentile; K distinct severities. Symbolic bounds, not timings. Resource exhaustion is not tested.