@qe-libs/rena-wasm 0.1.1 → 0.1.4

package/README.md

@@ -32,12 +32,14 @@ const model = ena.fit(rows, {
   dims:          2,
 });
 
-model.centroids        // Float64Array  nUnits × dims
-model.networks         // Float64Array  nUnits × nConnections (normed)
-model.positions        // Float64Array  nCodes × dims
+model.model.centroids  // Float64Array  nUnits × dims
+model.lineWeights      // Float64Array  nUnits × nConnections (normed)
+model.connectionCounts // Float64Array  nUnits × nConnections (raw unit counts)
+model.rowConnectionCounts // Float64Array nRows × nConnections (raw row counts)
+model.rotation.nodes   // Float64Array  nCodes × dims
 model.connectionNames  // ['Data & Technical.Constraints', ...]
-model.unitLabels       // ['UserName1_ConditionA', ...]
-model.columnNames      // ['SVD1', 'SVD2']
+model.model.unitLabels // ['UserName1_ConditionA', ...]
+model.rotation.columnNames // ['SVD1', 'SVD2']
 
 // Per-unit helpers
 model.centroid('Alice_A')  // number[]  length = dims
@@ -70,7 +72,7 @@ const model = ena.fit(rows, {
 Returns raw (un-normalised) network vectors without running the full pipeline.
 
 ```js
-const { networks, unitLabels, connectionNames, nUnits, nConnections } =
+const { connectionCounts, rowConnectionCounts, unitLabels, connectionNames, nUnits, nConnections } =
   ena.accumulate(rows, { codes, units, conversations, window: 4 });
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qe-libs/rena-wasm",
-  "version": "0.1.1",
+  "version": "0.1.4",
   "description": "JavaScript/WebAssembly ENA pipeline — thin orchestration layer over @qe-libs/libqe-wasm",
   "main": "src/index.js",
   "type": "module",
@@ -31,7 +31,7 @@
     "resolver": "<rootDir>/jest-resolver.cjs"
   },
   "dependencies": {
-    "@qe-libs/libqe-wasm": "^0.1.0"
+    "@qe-libs/libqe-wasm": "^0.1.4"
   },
   "devDependencies": {
     "jest": "^29.0.0"

package/src/index.js

@@ -12,6 +12,7 @@
  *
  * Top-level fields (= R's set$...):
  *   connectionCounts  Float64Array  (nUnits × nConnections) — raw accumulation
+ *   rowConnectionCounts Float64Array (nRows × nConnections) — per-row raw accumulation
  *   lineWeights       Float64Array  (nUnits × nConnections) — sphere-normed
  *   points            Float64Array  (nUnits × dims)         — projected positions
  *   rotationMatrix    Float64Array  (nConnections × dims)   — rotation vectors
@@ -23,6 +24,7 @@
  *   dims              number
  *
  * model sub-object (= R's set$model$...):
+ *   model.rowConnectionCounts Float64Array (nRows × nConnections) — per-row raw accumulation
  *   model.centroids           Float64Array  (nUnits × dims) — LWS centroids
  *   model.variance            number[]      variance explained per dim
  *   model.unitLabels          string[]
@@ -41,7 +43,7 @@
 import loadLibQE from '@qe-libs/libqe-wasm';
 import { parseData } from './data.js';
 import {
-    accumulate, sphereNorm, center,
+    sphereNorm, center,
     rotateSVD, rotateMeans, rotateGeneralized,
     project, nodePositions, spaceDistCorr,
 } from './pipeline.js';
@@ -107,6 +109,7 @@ class ENAModel {
     constructor(opts) {
         // ── top-level fields (= R's set$...) ────────────────────────────────
         this.connectionCounts = opts.connectionCounts;  // raw networks
+        this.rowConnectionCounts = opts.rowConnectionCounts;
         this.lineWeights      = opts.lineWeights;       // sphere-normed networks
         this.points           = opts.points;            // projected unit positions
         this.rotationMatrix   = opts.rotationMatrix;    // n_connections × dims
@@ -118,6 +121,7 @@ class ENAModel {
 
         // ── model sub-object (= R's set$model$...) ───────────────────────────
         this.model = {
+            rowConnectionCounts: opts.rowConnectionCounts,
             centroids:           opts.centroids,           // LWS positions
             variance:            opts.variance,            // variance explained
             unitLabels:          opts.unitLabels,
@@ -183,10 +187,33 @@ class ENAModel {
     }
 }
 
+// ── weight models (= R's `weight.by`) ────────────────────────────────────────
+
+/**
+ * Map a weight-model name to its element-wise transform, matching the webtool's
+ * server.js mapping to R weight.by functions:
+ *   'sqrt'    → Math.sqrt          (R "sqrt")
+ *   'log'     → Math.log1p         (R "log1p", i.e. log(x+1); guards log(0))
+ *   'product' → identity           (raw non-binary counts; R's "product" string
+ *                                    is not a function, so no transform)
+ * A falsy value or 'binary' returns null (binary accumulation, no transform).
+ * @param {string|false|undefined} name
+ * @returns {((x:number)=>number)|null}
+ */
+function weightModelTransform(name) {
+    switch (name) {
+        case 'sqrt':    return Math.sqrt;
+        case 'log':     return Math.log1p;
+        case 'product': return (x) => x;
+        default:        return null;   // binary / off / unknown
+    }
+}
+
 // ── shared pipeline (post-accumulation) ──────────────────────────────────────
 
 function runPipeline(qe, rawNetworks, nUnits, nConnections, codes, unitLabels,
-                     metaData, rotMethod, groupA, groupB, dims, gParams) {
+                     metaData, rotMethod, groupA, groupB, dims, gParams,
+                     rowConnectionCounts = null) {
     const connectionNames = qe.connection_names(codes);
 
     // Sphere norm → lineWeights (= R's set$line.weights)
@@ -228,10 +255,11 @@ function runPipeline(qe, rawNetworks, nUnits, nConnections, codes, unitLabels,
     );
 
     // Node positions (LWS) → rotation.nodes + model.centroids
-    // libqe.node_positions expects centered-normed networks (pointsForProjection),
-    // not sphere-normed (lineWeights). Using lineWeights places code nodes in wrong locations.
+    // Matches rENA's lws.positions.sq, which regresses the projected points onto
+    // the SPHERE-normed line weights (enaset$line.weights) — not the centered
+    // networks.  Verified node-for-node against R rENA on rs.data.new.csv.
     const { nodes, centroids } = nodePositions(
-        qe, pointsForProjection, nUnits, nConnections, points, dims
+        qe, lineWeights, nUnits, nConnections, points, dims
     );
 
     // Variance explained (= R's model$variance)
@@ -243,6 +271,7 @@ function runPipeline(qe, rawNetworks, nUnits, nConnections, codes, unitLabels,
     return new ENAModel({
         // top-level
         connectionCounts:     rawNetworks,
+        rowConnectionCounts,
         lineWeights,
         points,
         rotationMatrix,
@@ -285,10 +314,11 @@ export default async function loadENA() {
          * @param {string[]} opts.codes            - Code column names
          * @param {string[]} opts.units            - Unit identifier column(s)
          * @param {string[]} opts.conversations    - Conversation identifier column(s)
-         * @param {number}   [opts.window=4]       - Backward window (simple path; ignored when tensor provided)
-         * @param {boolean}  [opts.binary=true]    - Binarise co-occurrences (simple path only)
-         * @param {boolean}  [opts.ordered=false]  - Directed networks (tensor path only)
-         * @param {object}   [opts.tensor]         - Context tensor definition
+         * @param {number}   [opts.window=4]       - Backward window; builds defaultTensor(window) when no tensor is given
+         * @param {boolean}  [opts.binary=true]    - Binarise each line's co-occurrences (unordered; ignored when weightModel is set)
+         * @param {boolean}  [opts.ordered=false]  - Directed networks
+         * @param {object}   [opts.tensor]         - Context tensor definition (overrides window)
+         * @param {string}   [opts.weightModel]    - 'product' | 'sqrt' | 'log' (per-line, before the unit sum)
          * @param {string}   [opts.rotation='svd'] - 'svd', 'mean', or 'generalized'
          * @param {number[]} [opts.groupA]         - Unit indices for means rotation group A
          * @param {number[]} [opts.groupB]         - Unit indices for means rotation group B
@@ -312,31 +342,36 @@ export default async function loadENA() {
                 gParams,
                 dims                 = 2,
                 codeMask,
+                weightModel,
             } = opts;
 
             if (!codes?.length)         throw new Error('opts.codes is required');
             if (!units?.length)         throw new Error('opts.units is required');
             if (!conversations?.length) throw new Error('opts.conversations is required');
 
+            // Weight model = R's `weight.by`. R applies it per LINE (each row's
+            // "product" co-occurrence counts) BEFORE summing per unit, mirroring
+            // accumulate.data.R (lapply(.SD, weight.by) over the per-line
+            // co-occurrence table, then per-unit aggregation). Because
+            // sqrt(Σ) ≠ Σsqrt, the transform is applied to each row's counts
+            // inside accumulateTensor, not to the unit-summed network.
+            // `product` is the non-binarized row counts themselves (identity);
+            // any weight model therefore forces non-binary accumulation.
+            const weightFn = weightModelTransform(weightModel);
+            const effBinary = weightFn ? false : binary;
+
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
                 parseData(rows, codes, units, conversations);
 
-            let rawNetworks, nConnections;
-
-            if (tensorDef) {
-                rawNetworks  = accumulateTensor(
-                    qe, rows, codeMatrix, nRows, nCodes, nUnits,
-                    unitOf, convoGroups, tensorDef, ordered
-                );
-                nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
-            } else {
-                rawNetworks  = accumulate(
-                    qe, codeMatrix, nRows, nCodes, nUnits,
-                    unitOf, convoGroups, windowSize, binary
-                );
-                nConnections = qe.choose_two(nCodes);
-            }
+            // Every model accumulates through the tensor path; a plain moving
+            // window is expressed as defaultTensor(window).
+            const { networks: rawNetworks, rowConnectionCounts } = accumulateTensor(
+                qe, rows, codeMatrix, nRows, nCodes, nUnits,
+                unitOf, convoGroups, tensorDef ?? defaultTensor(windowSize),
+                ordered, effBinary, weightFn
+            );
+            const nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
 
             // Apply code masking by zeroing out the masked connection columns across all units
             if (codeMask && codeMask.length === codes.length) {
@@ -368,7 +403,8 @@ export default async function loadENA() {
             }
 
             return runPipeline(qe, rawNetworks, nUnits, nConnections, codes,
-                               unitLabels, metaData, rotMethod, groupA, groupB, dims, gParams);
+                               unitLabels, metaData, rotMethod, groupA, groupB,
+                               dims, gParams, rowConnectionCounts);
         },
 
         /**
@@ -379,6 +415,7 @@ export default async function loadENA() {
          * @param {object}   opts  - codes, units, conversations, window, binary, ordered, tensor
          * @returns {{
          *   connectionCounts: Float64Array,
+         *   rowConnectionCounts: Float64Array | null,
          *   unitLabels:       string[],
          *   connectionNames:  string[],
          *   metaData:         Object[],
@@ -401,21 +438,12 @@ export default async function loadENA() {
                     unitOf, convoGroups, metaData } =
                 parseData(rows, codes, units, conversations);
 
-            let networks, nConnections;
-
-            if (tensorDef) {
-                networks     = accumulateTensor(
-                    qe, rows, codeMatrix, nRows, nCodes, nUnits,
-                    unitOf, convoGroups, tensorDef, ordered
-                );
-                nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
-            } else {
-                networks     = accumulate(
-                    qe, codeMatrix, nRows, nCodes, nUnits,
-                    unitOf, convoGroups, windowSize, binary
-                );
-                nConnections = qe.choose_two(nCodes);
-            }
+            const { networks, rowConnectionCounts } = accumulateTensor(
+                qe, rows, codeMatrix, nRows, nCodes, nUnits,
+                unitOf, convoGroups, tensorDef ?? defaultTensor(windowSize),
+                ordered, binary
+            );
+            const nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
 
             // Apply code masking by zeroing out the masked connection columns across all units
             if (codeMask && codeMask.length === codes.length) {
@@ -448,7 +476,7 @@ export default async function loadENA() {
 
             const connectionNames = qe.connection_names(codes);
             return {
-                connectionCounts: networks, unitLabels, connectionNames,
+                connectionCounts: networks, rowConnectionCounts, unitLabels, connectionNames,
                 metaData, nUnits, nConnections,
                 // Retained so tuneWindowSize() can rebuild at other window sizes
                 // (= R's ENAAccumulation$`_function.call`).
@@ -491,21 +519,21 @@ export default async function loadENA() {
                 'maxSize must be greater than minSize to compare windows.'
             );
 
-            const { rows, codes, units, conversations, binary } = call;
+            const { rows, codes, units, conversations, binary, ordered } = call;
 
             // Parse once; only the window size changes between iterations.
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
                 parseData(rows, codes, units, conversations);
-            const nConnections = qe.choose_two(nCodes);
+            const nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
 
             // 1. Rebuild + fit at each window, collecting unit points.
             const dims = 2;
             const allPoints = [];
             for (const w of windowRange) {
-                const raw = accumulate(
-                    qe, codeMatrix, nRows, nCodes, nUnits,
-                    unitOf, convoGroups, w, binary
+                const { networks: raw } = accumulateTensor(
+                    qe, rows, codeMatrix, nRows, nCodes, nUnits,
+                    unitOf, convoGroups, defaultTensor(w), ordered, binary
                 );
                 const model = runPipeline(
                     qe, raw, nUnits, nConnections, codes,
@@ -531,10 +559,70 @@ export default async function loadENA() {
 
             // 4. Rebuild the accumulation at the selected window size.
             return api.accumulate(rows, {
-                codes, units, conversations, window: bestWindow, binary,
+                codes, units, conversations, window: bestWindow, binary, ordered,
             });
         },
 
+        /**
+         * Estimate the moving-window size via Cross-Covariance Decay (CCD)
+         * (= R's ena.ccd). Computes the noise-corrected cross-covariance decay
+         * curves over lags and returns the half-life lag as the window size.
+         *
+         * Unlike tuneWindowSize (which rebuilds+fits a full SVD model at each
+         * window), CCD runs directly on the raw code matrix per conversation —
+         * no accumulation/rotation — via the shared libqe kernel.
+         *
+         * @param {Object[]} rows
+         * @param {object}   opts
+         * @param {string[]} opts.codes            - Code column names
+         * @param {string[]} opts.conversations    - Conversation identifier column(s)
+         * @param {number}   [opts.maxWindow=20]   - Maximum lag to evaluate
+         * @param {number}   [opts.minOverlap=10]  - Minimum overlapping rows per conversation at a lag
+         * @returns {{
+         *   window_size:          number,
+         *   peak_lag:             number,
+         *   lag:                  number[],
+         *   frob:                 number[],
+         *   frob_sq_unbiased:     number[],
+         *   frob_unbiased_signed: number[],
+         *   total_weight:         number[],
+         * }}
+         */
+        ccd(rows, opts = {}) {
+            const { codes, conversations, maxWindow = 20, minOverlap = 10 } = opts;
+            if (!codes?.length)         throw new Error('opts.codes is required');
+            if (!conversations?.length) throw new Error('opts.conversations is required');
+
+            // Units are irrelevant to CCD; reuse conversations as a placeholder
+            // so parseData can build codeMatrix + convoGroups.
+            const { codeMatrix, nRows, nCodes, convoGroups } =
+                parseData(rows, codes, conversations, conversations);
+
+            // Flatten conversation row groups into (sizes, indices) for the kernel.
+            const groupSizes = [];
+            const rowIndices = [];
+            for (const rowIdxs of convoGroups.values()) {
+                groupSizes.push(rowIdxs.length);
+                for (const ri of rowIdxs) rowIndices.push(ri);
+            }
+
+            return qe.ccd_window(
+                codeMatrix, nRows, nCodes, groupSizes, rowIndices, maxWindow, minOverlap
+            );
+        },
+
+        /**
+         * Convenience wrapper returning only the estimated window size
+         * (= R's ena.ccd.window).
+         *
+         * @param {Object[]} rows
+         * @param {object}   opts  - see ccd()
+         * @returns {number}  estimated window size
+         */
+        ccdWindow(rows, opts = {}) {
+            return api.ccd(rows, opts).window_size;
+        },
+
         /**
          * Per-dimension t-based confidence intervals around the column means.
          * Matches R's conf.ints / libqe::mean_ci.
@@ -581,10 +669,135 @@ export default async function loadENA() {
             return qe.group_stats(g1Points, nG1, dims, g2Points, nG2, dims);
         },
 
+        /**
+         * PRIA — find the largest set of codes (up to removeNum) that can be
+         * removed while keeping the model's goodness-of-fit within `threshold`
+         * of the full model.  Brute-force subset search matching R
+         * PRIA::pria(): for k = 1..removeNum, over every k-subset of codes,
+         * build the reduced model (fit with a codeMask that drops every
+         * connection touching a removed code), gate on
+         * min_d(gof_reduced[d] / gof_full[d]) >= threshold where gof is the
+         * per-dimension ena_correlation(points, centroids), and keep the subset
+         * with the MOST codes removed, then the highest reduced dim-1 variance.
+         *
+         * @returns {{ removed: string[], removedIndices: number[], k: number,
+         *             variance: (number|null) }}
+         */
+        pria(rows, opts = {}) {
+            const {
+                codes, units, conversations,
+                window: windowSize = 4, binary = true, ordered = false,
+                rotation = 'svd', dims = 2, gParams, groupA, groupB,
+                removeNum = 3, threshold = 0.95,
+            } = opts;
+            if (!codes?.length)         throw new Error('opts.codes is required');
+            if (!units?.length)         throw new Error('opts.units is required');
+            if (!conversations?.length) throw new Error('opts.conversations is required');
+
+            const m  = codes.length;
+            const rn = Math.min(removeNum, m - 3);   // never reduce below 3 codes
+            const empty = { removed: [], removedIndices: [], k: 0, variance: null };
+            if (rn < 1) return empty;
+
+            const gofDims  = Math.min(dims, 2);       // R scores on dims 1:2
+            const baseOpts = { codes, units, conversations, window: windowSize,
+                               binary, ordered, rotation, dims, gParams, groupA, groupB };
+
+            const D = gofDims;  // score on the first 2 dims (R's get_pria_scores_2Ds)
+            // Extract a D-column submatrix (given row indices) from a flat
+            // row-major (nRows × dims) array.
+            const sub = (flat, rowIdxs) => {
+                const out = new Float64Array(rowIdxs.length * D);
+                rowIdxs.forEach((r, t) => { for (let d = 0; d < D; d++) out[t * D + d] = flat[r * dims + d]; });
+                return out;
+            };
+            // ena_correlation(A, B) → [r_dim0, r_dim1] (col 0 of the dims×3 result).
+            const corr2 = (Aflat, Bflat, nRows) => {
+                const r = qe.ena_correlation(Array.from(Aflat), nRows, D,
+                                             Array.from(Bflat), nRows, D, 0.95);
+                const out = [];
+                for (let d = 0; d < D; d++) out.push(r.data[d * 3]);
+                return out;
+            };
+            const full   = api.fit(rows, baseOpts);
+            const nUnits = full.nUnits;
+            const unitRows = Array.from({ length: nUnits }, (_, i) => i);
+            const gofOf    = (mdl) => corr2(sub(mdl.points, unitRows), sub(mdl.model.centroids, unitRows), nUnits);
+            const gFull    = gofOf(full);
+            const fullPts2 = sub(full.points, unitRows);
+
+            // All k-subsets of [0..m) as index arrays.
+            const combos = (n, k) => {
+                const res = [], cur = [];
+                const rec = (start) => {
+                    if (cur.length === k) { res.push(cur.slice()); return; }
+                    for (let i = start; i < n; i++) { cur.push(i); rec(i + 1); cur.pop(); }
+                };
+                rec(0);
+                return res;
+            };
+
+            let bestK = 0, bestVar = -Infinity, bestRemoved = [];
+            for (let k = 1; k <= rn; k++) {
+                for (const idxs of combos(m, k)) {
+                    const removedSet = new Set(idxs);
+                    const mask = [];
+                    for (let i = 0; i < m; i++) {
+                        const row = [];
+                        for (let j = 0; j < m; j++) {
+                            row.push((removedSet.has(i) || removedSet.has(j)) ? 0 : 1);
+                        }
+                        mask.push(row);
+                    }
+                    const red = api.fit(rows, { ...baseOpts, codeMask: mask });
+
+                    // Gate 1 — goodness-of-fit ratio vs full, per dim.
+                    const gRed = gofOf(red);
+                    let pass = true;
+                    for (let d = 0; d < D; d++) {
+                        if (gFull[d] === 0 || gRed[d] / gFull[d] < threshold) { pass = false; break; }
+                    }
+                    if (!pass) continue;
+
+                    // Gate 2 — reduced points AND retained-code nodes must each
+                    // correlate >= threshold with the full model (per dim, with a
+                    // per-dim sign flip that negates the node corr alongside it).
+                    const retained = [];
+                    for (let i = 0; i < m; i++) if (!removedSet.has(i)) retained.push(i);
+                    let [pc1, pc2] = corr2(fullPts2, sub(red.points, unitRows), nUnits);
+                    let [nc1, nc2] = corr2(sub(full.rotation.nodes, retained),
+                                           sub(red.rotation.nodes, retained), retained.length);
+                    if (pc1 < 0) { pc1 = -pc1; nc1 = -nc1; }
+                    if (pc2 < 0) { pc2 = -pc2; nc2 = -nc2; }
+                    if (Math.min(pc1, pc2, nc1, nc2) < threshold) continue;
+
+                    // Dim-1 variance proportion over the FULL rotation spectrum
+                    // (= R's set$model$variance[1] = diag(var(points.rotated))/sum);
+                    // NOT model.variance, which is the 2-dim projected ratio.
+                    const ev = red.rotation.eigenvalues;
+                    let evSum = 0; for (let i = 0; i < ev.length; i++) evSum += ev[i];
+                    const vr1 = evSum > 0 ? ev[0] / evSum : 0;
+                    // Prefer more codes removed; tie-break on higher dim-1 variance.
+                    if (k > bestK || (k === bestK && vr1 > bestVar)) {
+                        bestK = k; bestVar = vr1; bestRemoved = idxs.slice();
+                    }
+                }
+            }
+            return {
+                removed:        bestRemoved.map(i => codes[i]),
+                removedIndices: bestRemoved,
+                k:              bestK,
+                variance:       bestVar === -Infinity ? null : bestVar,
+            };
+        },
+
         /**
          * Helpers re-exported for consumers who want to build their own pipeline.
          */
         defaultTensor,
+
+        /** The underlying libqe WASM module, for custom low-level pipelines. */
+        qe,
     };
 
     return api;

package/src/pipeline.js

@@ -116,64 +116,6 @@ export function spaceDistCorr(A, B, m, d, maxSampleSize = 100000, rand = Math.ra
     return pearson(distA, distB);
 }
 
-// ── accumulation ─────────────────────────────────────────────────────────────
-
-/**
- * Accumulate windowed co-occurrences for all units across all conversations.
- *
- * For each conversation group, runs qe.accumulate_stanza() on the conversation's
- * rows to get per-row connection vectors, then folds each row's vector into its
- * owning unit's running sum.
- *
- * @param {object}      qe            libqe WASM module
- * @param {Float64Array} codeMatrix   n_rows × n_codes, row-major
- * @param {number}      nRows
- * @param {number}      nCodes
- * @param {number}      nUnits
- * @param {Int32Array}  unitOf        unit index per row
- * @param {Map}         convoGroups   convoIdx → [rowIdx, ...]
- * @param {number}      windowSize    backward window (rows)
- * @param {boolean}     binary        binarise co-occurrences
- *
- * @returns {Float64Array}  nUnits × nConnections, row-major
- */
-export function accumulate(qe, codeMatrix, nRows, nCodes, nUnits,
-                            unitOf, convoGroups, windowSize = 4, binary = true) {
-    const nConnections = qe.choose_two(nCodes);
-    const networks     = new Float64Array(nUnits * nConnections);
-
-    for (const [, rowIndices] of convoGroups) {
-        const nConvo = rowIndices.length;
-
-        // Extract code rows for this conversation (contiguous sub-matrix)
-        const convoCodes = new Float64Array(nConvo * nCodes);
-        for (let r = 0; r < nConvo; r++) {
-            const src = rowIndices[r];
-            convoCodes.set(
-                codeMatrix.subarray(src * nCodes, src * nCodes + nCodes),
-                r * nCodes
-            );
-        }
-
-        // Windowed accumulation — returns per-row connection vectors
-        const stanza = qe.accumulate_stanza(
-            convoCodes, nConvo, nCodes, windowSize, 0, binary
-        );
-        // stanza.data: nConvo × nConnections, row-major
-
-        // Fold each row into its unit's accumulator
-        for (let r = 0; r < nConvo; r++) {
-            const unit   = unitOf[rowIndices[r]];
-            const offset = r * nConnections;
-            for (let c = 0; c < nConnections; c++) {
-                networks[unit * nConnections + c] += stanza.data[offset + c];
-            }
-        }
-    }
-
-    return networks;
-}
-
 // ── normalization (sphere norm) ───────────────────────────────────────────────
 
 /**

package/src/tensor.js

@@ -119,9 +119,61 @@ export function inferFactorLevels(rows, factors) {
     return levels;
 }
 
+/**
+ * Weighted aggregation of a unit's per-response-row directed connection counts.
+ *
+ * Mirrors the kernel's aggregate_row_connections but applies a weight-model
+ * transform (R's weight.by) per LINE before the per-unit sum, so weight models
+ * behave identically on the tensor path and the windowed path. Non-binary by
+ * construction (the weight replaces the binarize step).
+ *
+ *   unordered: fold each directed row (m + mᵀ, upper triangle, column-major —
+ *              the same order as choose_two/connection_names), weight each
+ *              folded cell, then sum across rows.
+ *   ordered:   weight each directed cell, then sum across rows.
+ *
+ * @param {Float64Array|number[]} data  Row-major (nRccRows × nCodes²) counts.
+ * @param {number}   nRccRows           Number of response rows for this unit.
+ * @param {number}   nCodes
+ * @param {boolean}  ordered
+ * @param {(x:number)=>number} weightFn
+ * @returns {Float64Array}  length nCodes² (ordered) or choose_two(nCodes).
+ */
+function aggregateRowConnectionsWeighted(data, nRccRows, nCodes, ordered, weightFn) {
+    const nSq = nCodes * nCodes;
+    if (ordered) {
+        const out = new Float64Array(nSq);
+        for (let r = 0; r < nRccRows; r++) {
+            const base = r * nSq;
+            for (let c = 0; c < nSq; c++) out[c] += weightFn(data[base + c]);
+        }
+        return out;
+    }
+    const nTri = (nCodes * (nCodes - 1)) / 2;
+    const out = new Float64Array(nTri);
+    for (let r = 0; r < nRccRows; r++) {
+        const base = r * nSq;
+        let k = 0;
+        for (let col = 1; col < nCodes; col++) {
+            for (let row = 0; row < col; row++) {
+                // fold: m(row,col) + m(col,row), column-major reshape of the row
+                const folded = data[base + col * nCodes + row] +
+                               data[base + row * nCodes + col];
+                out[k] += weightFn(folded);
+                k++;
+            }
+        }
+    }
+    return out;
+}
+
 /**
  * Accumulate tensor networks for all units across all conversations.
  *
+ * Every accumulation — including plain windowed ENA, via defaultTensor(window)
+ * — runs through here, so the per-line finalisation (fold / binarize / weight)
+ * lives in exactly one place.
+ *
  * @param {object}      qe             libqe WASM module
  * @param {Object[]}    rows           Full dataset
  * @param {Float64Array} codeMatrix   n_rows × n_codes, row-major
@@ -132,11 +184,18 @@ export function inferFactorLevels(rows, factors) {
  * @param {Map}         convoGroups    convoIdx → [rowIdx, ...]
  * @param {object}      tensorDef      Tensor definition (see module docstring)
  * @param {boolean}     ordered        true → directed (n²); false → undirected
+ * @param {boolean}     [binary=true]  binarize each folded row (unordered only)
+ * @param {((x:number)=>number)|null} [weightFn=null]  per-line weight transform
  *
- * @returns {Float64Array}  nUnits × nConnections, row-major
+ * @returns {{ networks: Float64Array, rowConnectionCounts: Float64Array }}
+ *   networks            nUnits × nConnections, row-major
+ *   rowConnectionCounts nRows × nConnections, row-major — each row's finalised
+ *                       (folded / binarized / weighted) connection vector;
+ *                       rows sum by unit to `networks`
  */
 export function accumulateTensor(qe, rows, codeMatrix, nRows, nCodes, nUnits,
-                                  unitOf, convoGroups, tensorDef, ordered = false) {
+                                  unitOf, convoGroups, tensorDef, ordered = false,
+                                  binary = true, weightFn = null) {
     const {
         dims,
         dimsSender   = [],
@@ -154,7 +213,8 @@ export function accumulateTensor(qe, rows, codeMatrix, nRows, nCodes, nUnits,
         ? nCodes * nCodes
         : qe.choose_two(nCodes);
 
-    const networks = new Float64Array(nUnits * nConnections);
+    const networks            = new Float64Array(nUnits * nConnections);
+    const rowConnectionCounts = new Float64Array(nRows * nConnections);
 
     const dimsArr    = new Int32Array(dims);
     const senderArr  = new Int32Array(dimsSender);
@@ -191,6 +251,12 @@ export function accumulateTensor(qe, rows, codeMatrix, nRows, nCodes, nUnits,
         for (const [unit, localRows] of unitConvoRows) {
             const unitRowsArr = new Int32Array(localRows);
 
+            // Always accumulate the DIRECTED per-response-row counts (ordered
+            // kernel), exactly as tma does — it calls apply_tensor with the
+            // default ordered=TRUE and defers the ordered-vs-unordered decision
+            // to aggregation.  Passing the unordered flag here would make the
+            // kernel emit an already-symmetric matrix that the fold below would
+            // then double-count.
             const result = qe.accumulate_tensor_unit(
                 tensorData, dimsArr,
                 senderArr, receiverArr, modeArr,
@@ -198,17 +264,33 @@ export function accumulateTensor(qe, rows, codeMatrix, nRows, nCodes, nUnits,
                 unitRowsArr,
                 convoCodes, nConvo, nCodes,
                 times,
-                ordered
+                true
             );
 
-            // Add connection counts to this unit's accumulator
-            for (let c = 0; c < nConnections; c++) {
-                networks[unit * nConnections + c] += result.connection_counts[c];
+            // Finalise each raw per-response-row connection vector exactly as
+            // tma does in R: fold to the upper triangle and binarize per row
+            // (unordered), or keep the directed row (ordered). A weight model
+            // (R's weight.by) replaces the binarize step with its transform,
+            // applied per line before the per-unit sum. Unweighted rows go
+            // through the libqe kernel so fold/binarize semantics are shared
+            // across every binding. Row i of rcc is local row localRows[i].
+            const rcc = result.row_connection_counts;
+            for (let i = 0; i < rcc.rows; i++) {
+                const one = rcc.data.slice(i * rcc.cols, (i + 1) * rcc.cols);
+                const rowVec = weightFn
+                    ? aggregateRowConnectionsWeighted(one, 1, nCodes, ordered, weightFn)
+                    : qe.aggregate_row_connections(one, 1, rcc.cols, nCodes, ordered, binary);
+                const rowOff  = rowIndices[localRows[i]] * nConnections;
+                const unitOff = unit * nConnections;
+                for (let c = 0; c < nConnections; c++) {
+                    rowConnectionCounts[rowOff + c] = rowVec[c];
+                    networks[unitOff + c] += rowVec[c];
+                }
             }
         }
     }
 
-    return networks;
+    return { networks, rowConnectionCounts };
 }
 
 /**