bex/tag_preprocessor/code.py

@@ -53,6 +53,76 @@ BEHAVIORAL_PREFIXES = (
 
 CALL_PREFIXES = ("function.call", "function.method.call", "reference.call", "reference.class", "constructor", "function")
 
+
+def coarsen_token(capname):
+    """Map a tree-sitter capture name to a language-agnostic category.
+
+    Uses capture names from highlights.scm — same across all languages.
+    Function calls are kept as raw text (they ARE the behavioral content).
+    Only structural tokens (keywords, types) are coarsened.
+    """
+    if capname.startswith("function.call") or capname.startswith("reference.call"):
+        return None  # keep raw
+    if capname.startswith("function.method.call"):
+        return None  # keep raw
+    if capname.startswith("constructor"):
+        return None  # keep raw
+    if capname.startswith("function"):
+        return None  # keep raw (bare @function in Kotlin etc.)
+    if capname.startswith("keyword.return"):
+        return "RETURN"
+    if capname.startswith("keyword.raise") or capname.startswith("keyword.throw"):
+        return "RAISE"
+    if capname.startswith("keyword.yield"):
+        return "YIELD"
+    if capname.startswith("keyword.exception"):
+        return "EXCEPTION"
+    if capname.startswith("keyword.conditional"):
+        return "IF"
+    if capname.startswith("keyword.repeat"):
+        return "LOOP"
+    if capname.startswith("keyword.function"):
+        return "FUN"
+    if capname.startswith("keyword"):
+        return "KW"
+    if capname.startswith("type.definition"):
+        return "TYPE"
+    if capname.startswith("type"):
+        return "TYPE"
+    if capname.startswith("variable.builtin"):
+        return "BUILTIN"
+    if capname.startswith("variable"):
+        return "VAR"
+    if capname.startswith("constant"):
+        return "CONST"
+    if capname.startswith("string"):
+        return "STR"
+    if capname.startswith("number"):
+        return "NUM"
+    if capname.startswith("boolean"):
+        return "BOOL"
+    if capname.startswith("attribute"):
+        return "ATTR"
+    return "OTHER"
+
+
+def _extract_coarsened_tokens(seq):
+    """Extract coarsened tokens from a method sequence.
+
+    Function calls are kept as raw text (they are the behavioral content).
+    Structural tokens (keywords, types) are mapped to language-agnostic
+    categories via coarsen_token().
+    Returns list of strings: either raw text or category label.
+    """
+    result = []
+    for capname, text, _ in seq:
+        for prefix in BEHAVIORAL_PREFIXES:
+            if capname.startswith(prefix):
+                cat = coarsen_token(capname)
+                result.append(text if cat is None else cat)
+                break
+    return result
+
 def _extract_call_tokens(seq):
     """Extract ordered call-like tokens from a method sequence.
 

experiments/EXPERIMENT_LOG.md

@@ -115,6 +115,43 @@ appears with different method names in different packages.
 
 ---
 
+## Round 6: Structural Coarsening (Experiment `coarsen_eval.py`)
+
+**Hypothesis:** Coarsening structural tokens (keywords, types) while keeping
+function names raw reveals cross-package patterns that pure-text misses.
+
+**Method:** `coarsen_token()` maps tree-sitter capture names to categories.
+Function calls kept as raw text (they ARE the content). Only structural tokens
+coarsened: RETURN, RAISE, IF, LOOP, EXCEPTION, KW, TYPE, FUN, ATTR.
+
+**Result:**
+
+| Codebase | Structural % | Raw coverage | Coarsened coverage | Δ |
+|----------|-------------|--------------|-------------------|---|
+| RAGSAK | 4.7% | 18.6% | 18.3% | -0.3% |
+| Flask | 36.1% | 17.5% | **28.8%** | **+11.3%** |
+
+Key findings:
+- RAGSAK: 95.3% function calls → coarsening has nothing to work with
+- Flask: 36.1% structural → coarsening significantly improves grouping
+- Flask k=3: cross-package contexts increase 40 → 47
+- Coarsened cross-package shapes: `('IF', 'KW', 'RETURN')` in 4 packages,
+  `('RETURN', 'render_template', 'render_template')` in 6 packages
+
+**Verdict:** Coarsening helps codebases with rich structural tokens (Python:
+IF, LOOP, EXCEPTION, KW). Doesn't help codebases dominated by function calls
+(Kotlin: 95% calls). The approach is sound but language-dependent in practice —
+depends on how rich the highlights.scm is.
+
+**What we learned:**
+- The 5% structural tokens DO carry signal when they exist
+- Python highlights.scm is much richer than Kotlin's
+- Coarsening is not dead — it's a tool for languages with rich captures
+- The real question is whether the coarsened patterns are USEFUL, not just
+  whether they exist
+
+---
+
 ## What We Learned (Summary)
 
 1. **Per-package grouping is too sparse.** 1-3 sequences per package isn't

experiments/coarsen_eval.py

@@ -0,0 +1,223 @@
+"""Coarsening Experiment — Compare raw vs coarsened token extraction.
+
+Tests whether collapsing method names → tree-sitter capture categories
+reveals cross-package patterns that raw text misses.
+"""
+
+import json
+import time
+from collections import defaultdict
+from pathlib import Path
+
+from bex.tag_preprocessor.analyze import (
+    _preprocess_files, _file_to_package, scan_directory
+)
+from bex.tag_preprocessor.code import (
+    _extract_call_tokens, _extract_coarsened_tokens
+)
+from bex.twotinf import build_soa
+from bex.rwr0 import rwr0
+
+
+RESULTS_DIR = Path(__file__).parent / "results"
+
+
+CODEBASES = {
+    "ragsak": {"name": "RAGSAK", "path": "/home/tobi/Desktop/kesai/RAGSAK", "ext": ".kt"},
+    "flask": {"name": "Flask", "path": "/home/tobi/Desktop/dervish/external_refs/flask", "ext": ".py"},
+}
+
+
+def load_data(base, ext):
+    """Load sequences, extract both raw and coarsened."""
+    groups = scan_directory(base)
+    files = groups.get(ext, [])
+    sequences, seq_files = _preprocess_files(files)
+
+    raw_seqs = [_extract_call_tokens(seq) for seq in sequences]
+    coarse_seqs = [_extract_coarsened_tokens(seq) for seq in sequences]
+    packages = [_file_to_package(fp, base) for fp in seq_files]
+
+    return raw_seqs, coarse_seqs, packages, seq_files
+
+
+def group_by_context(seqs, packages, k):
+    """Group sequences by first k symbols of their sequence."""
+    contexts = defaultdict(list)
+    for i, seq in enumerate(seqs):
+        if not seq:
+            contexts[("_eps",)].append((i, seq))
+        else:
+            ctx = tuple(seq[:k])
+            contexts[ctx].append((i, seq))
+    return contexts
+
+
+def group_by_package(seqs, packages):
+    """Group sequences by package."""
+    contexts = defaultdict(list)
+    for i, seq in enumerate(seqs):
+        contexts[packages[i]].append((i, seq))
+    return contexts
+
+
+def infer_sore(seqs):
+    """Try to infer a SORE from a list of sequences. Returns SORE string or None."""
+    if len(seqs) < 2:
+        return None
+    clean = [s for s in seqs if s]
+    if len(clean) < 2:
+        return None
+    unique = len(set(tuple(s) for s in clean))
+    if unique / len(clean) > 0.9:
+        return None
+    alphabet = set()
+    for s in clean:
+        alphabet.update(s)
+    if len(alphabet) > 20:
+        return None
+    try:
+        soa = build_soa(clean)
+        sore = rwr0(soa)
+        return sore if sore != "∅" else None
+    except Exception:
+        return None
+
+
+def measure_group(ctx, items, label):
+    """Measure properties of a group."""
+    seqs = [seq for _, seq in items]
+    n = len(seqs)
+    unique = len(set(tuple(s) for s in seqs))
+    unique_ratio = unique / n if n else 1.0
+    alphabet = set()
+    for s in seqs:
+        alphabet.update(s)
+    sore = infer_sore(seqs)
+    return {
+        "context": str(ctx),
+        "label": label,
+        "methods": n,
+        "unique": unique,
+        "unique_ratio": round(unique_ratio, 3),
+        "alphabet_size": len(alphabet),
+        "sore": sore[:200] if sore else None,
+        "sore_success": sore is not None,
+    }
+
+
+def find_cross_package(groups_by_ctx, packages):
+    """Find contexts that span multiple packages."""
+    ctx_to_pkgs = defaultdict(set)
+    for ctx, items in groups_by_ctx.items():
+        for idx, _ in items:
+            ctx_to_pkgs[ctx].add(packages[idx])
+    return {ctx: pkgs for ctx, pkgs in ctx_to_pkgs.items() if len(pkgs) > 1}
+
+
+def run_comparison(name, raw_seqs, coarse_seqs, packages, k_values=(1, 2, 3)):
+    """Run raw vs coarsened comparison for one codebase."""
+    results = {"name": name, "raw": {}, "coarsened": {}}
+
+    for label, seqs in [("raw", raw_seqs), ("coarsened", coarse_seqs)]:
+        results[label]["seq_count"] = len(seqs)
+        alphabet = set()
+        for s in seqs:
+            alphabet.update(s)
+        results[label]["alphabet_size"] = len(alphabet)
+        results[label]["alphabet_sample"] = sorted(alphabet)[:30]
+
+        for k in k_values:
+            t0 = time.time()
+            groups = group_by_context(seqs, packages, k)
+            elapsed = time.time() - t0
+
+            # Measure all groups
+            group_results = []
+            sore_successes = 0
+            methods_in_good = 0
+            total_methods = 0
+
+            for ctx, items in sorted(groups.items(), key=lambda x: -len(x[1])):
+                m = measure_group(ctx, items, f"{label}_k{k}")
+                group_results.append(m)
+                total_methods += m["methods"]
+                if m["sore_success"]:
+                    sore_successes += 1
+                    methods_in_good += m["methods"]
+
+            # Cross-package analysis
+            cross_pkg = find_cross_package(groups, packages)
+
+            results[label][f"k{k}"] = {
+                "contexts": len(groups),
+                "sore_successes": sore_successes,
+                "total_methods": total_methods,
+                "methods_in_good": methods_in_good,
+                "coverage": round(methods_in_good / total_methods * 100, 1) if total_methods else 0,
+                "cross_package_contexts": len(cross_pkg),
+                "elapsed": round(elapsed, 3),
+                "top_groups": group_results[:10],
+                "cross_pkg_examples": [
+                    {"context": str(ctx), "packages": len(pkgs)}
+                    for ctx, pkgs in sorted(cross_pkg.items(), key=lambda x: -len(x[1]))[:10]
+                ],
+            }
+
+    return results
+
+
+def print_results(results):
+    """Pretty-print comparison results."""
+    name = results["name"]
+    print(f"\n{'=' * 70}")
+    print(f"  {name}")
+    print(f"{'=' * 70}")
+
+    raw = results["raw"]
+    coarse = results["coarsened"]
+
+    print(f"\n  Alphabet size:  raw={raw['alphabet_size']}  coarsened={coarse['alphabet_size']}  "
+          f"reduction={raw['alphabet_size'] - coarse['alphabet_size']} ({(1 - coarse['alphabet_size']/raw['alphabet_size'])*100:.0f}%)")
+    print(f"  Coarsened categories: {coarse['alphabet_sample']}")
+
+    for k in [1, 2, 3]:
+        rk = raw.get(f"k{k}", {})
+        ck = coarse.get(f"k{k}", {})
+        print(f"\n  --- k={k} ---")
+        print(f"  {'':20s} {'Raw':>10s} {'Coarsened':>10s}")
+        print(f"  {'Contexts':20s} {rk.get('contexts',0):10d} {ck.get('contexts',0):10d}")
+        print(f"  {'SORE successes':20s} {rk.get('sore_successes',0):10d} {ck.get('sore_successes',0):10d}")
+        print(f"  {'Coverage':20s} {rk.get('coverage',0):9.1f}% {ck.get('coverage',0):9.1f}%")
+        print(f"  {'Cross-pkg contexts':20s} {rk.get('cross_package_contexts',0):10d} {ck.get('cross_package_contexts',0):10d}")
+
+        # Show cross-package examples from coarsened
+        cross_examples = ck.get("cross_pkg_examples", [])
+        if cross_examples:
+            print(f"  Cross-package shapes:")
+            for ex in cross_examples[:5]:
+                print(f"    {ex['context']}  ({ex['packages']} packages)")
+
+
+def main():
+    all_results = {}
+    for key, cfg in CODEBASES.items():
+        print(f"\nLoading {cfg['name']}...")
+        raw_seqs, coarse_seqs, packages, seq_files = load_data(cfg["path"], cfg["ext"])
+        print(f"  {len(raw_seqs)} methods from {len(set(packages))} packages")
+
+        results = run_comparison(cfg["name"], raw_seqs, coarse_seqs, packages)
+        all_results[key] = results
+        print_results(results)
+
+        # Save
+        out_path = RESULTS_DIR / f"coarsen_{key}.json"
+        with open(out_path, "w") as f:
+            json.dump(results, f, indent=2)
+        print(f"\n  Saved to {out_path}")
+
+    return all_results
+
+
+if __name__ == "__main__":
+    main()

experiments/results/coarsen_flask.json

@@ -0,0 +1,993 @@
+{
+  "name": "Flask",
+  "raw": {
+    "seq_count": 1391,
+    "alphabet_size": 1055,
+    "alphabet_sample": [
+      "",
+      "!r",
+      "\" * 100)",
+      "\")",
+      "\", \"index\",",
+      "\", de",
+      "\", su",
+      "\"/\")",
+      "\"/t",
+      "\"X-Foo\"",
+      "\"about\"",
+      "\"ba",
+      "\"cus",
+      "\"fake a",
+      "\"fo",
+      "\"foo.vi",
+      "\"h",
+      "\"hello\"",
+      "\"lat",
+      "\"mer",
+      "\"nes",
+      "\"someth",
+      "\"spam\")",
+      "\"static",
+      "# ip addre",
+      "(\"\"), 40",
+      "(\"\", hea",
+      "()",
+      "(test",
+      "({\"msg\":"
+    ],
+    "k1": {
+      "contexts": 373,
+      "sore_successes": 22,
+      "total_methods": 1391,
+      "methods_in_good": 64,
+      "coverage": 4.6,
+      "cross_package_contexts": 58,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('_eps',)",
+          "label": "raw_k1",
+          "methods": 282,
+          "unique": 1,
+          "unique_ratio": 0.004,
+          "alphabet_size": 0,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('isinstance',)",
+          "label": "raw_k1",
+          "methods": 66,
+          "unique": 20,
+          "unique_ratio": 0.303,
+          "alphabet_size": 55,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('route',)",
+          "label": "raw_k1",
+          "methods": 59,
+          "unique": 54,
+          "unique_ratio": 0.915,
+          "alphabet_size": 148,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append',)",
+          "label": "raw_k1",
+          "methods": 53,
+          "unique": 3,
+          "unique_ratio": 0.057,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('get',)",
+          "label": "raw_k1",
+          "methods": 50,
+          "unique": 40,
+          "unique_ratio": 0.8,
+          "alphabet_size": 97,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Blueprint',)",
+          "label": "raw_k1",
+          "methods": 41,
+          "unique": 37,
+          "unique_ratio": 0.902,
+          "alphabet_size": 121,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('render_template',)",
+          "label": "raw_k1",
+          "methods": 33,
+          "unique": 2,
+          "unique_ratio": 0.061,
+          "alphabet_size": 2,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Flask',)",
+          "label": "raw_k1",
+          "methods": 28,
+          "unique": 26,
+          "unique_ratio": 0.929,
+          "alphabet_size": 63,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('abort',)",
+          "label": "raw_k1",
+          "methods": 17,
+          "unique": 2,
+          "unique_ratio": 0.118,
+          "alphabet_size": 3,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('super',)",
+          "label": "raw_k1",
+          "methods": 16,
+          "unique": 12,
+          "unique_ratio": 0.75,
+          "alphabet_size": 33,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('get',)",
+          "packages": 7
+        },
+        {
+          "context": "('render_template',)",
+          "packages": 6
+        },
+        {
+          "context": "('Flask',)",
+          "packages": 4
+        },
+        {
+          "context": "('pop',)",
+          "packages": 4
+        },
+        {
+          "context": "('isinstance',)",
+          "packages": 4
+        },
+        {
+          "context": "('setdefault',)",
+          "packages": 4
+        },
+        {
+          "context": "('post',)",
+          "packages": 3
+        },
+        {
+          "context": "('app_context',)",
+          "packages": 3
+        },
+        {
+          "context": "('test_client',)",
+          "packages": 3
+        }
+      ]
+    },
+    "k2": {
+      "contexts": 389,
+      "sore_successes": 22,
+      "total_methods": 1391,
+      "methods_in_good": 64,
+      "coverage": 4.6,
+      "cross_package_contexts": 54,
+      "elapsed": 0.001,
+      "top_groups": [
+        {
+          "context": "('_eps',)",
+          "label": "raw_k2",
+          "methods": 282,
+          "unique": 1,
+          "unique_ratio": 0.004,
+          "alphabet_size": 0,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('isinstance', 'isinstance')",
+          "label": "raw_k2",
+          "methods": 66,
+          "unique": 20,
+          "unique_ratio": 0.303,
+          "alphabet_size": 55,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('route', 'route')",
+          "label": "raw_k2",
+          "methods": 59,
+          "unique": 54,
+          "unique_ratio": 0.915,
+          "alphabet_size": 148,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append', 'append')",
+          "label": "raw_k2",
+          "methods": 53,
+          "unique": 3,
+          "unique_ratio": 0.057,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('get', 'get')",
+          "label": "raw_k2",
+          "methods": 50,
+          "unique": 40,
+          "unique_ratio": 0.8,
+          "alphabet_size": 97,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Blueprint', 'Blueprint')",
+          "label": "raw_k2",
+          "methods": 41,
+          "unique": 37,
+          "unique_ratio": 0.902,
+          "alphabet_size": 121,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('render_template', 'render_template')",
+          "label": "raw_k2",
+          "methods": 33,
+          "unique": 2,
+          "unique_ratio": 0.061,
+          "alphabet_size": 2,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Flask', 'Flask')",
+          "label": "raw_k2",
+          "methods": 28,
+          "unique": 26,
+          "unique_ratio": 0.929,
+          "alphabet_size": 63,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('abort', 'abort')",
+          "label": "raw_k2",
+          "methods": 17,
+          "unique": 2,
+          "unique_ratio": 0.118,
+          "alphabet_size": 3,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('super', 'super')",
+          "label": "raw_k2",
+          "methods": 16,
+          "unique": 12,
+          "unique_ratio": 0.75,
+          "alphabet_size": 33,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('get', 'get')",
+          "packages": 7
+        },
+        {
+          "context": "('render_template', 'render_template')",
+          "packages": 6
+        },
+        {
+          "context": "('Flask', 'Flask')",
+          "packages": 4
+        },
+        {
+          "context": "('pop', 'pop')",
+          "packages": 4
+        },
+        {
+          "context": "('isinstance', 'isinstance')",
+          "packages": 4
+        },
+        {
+          "context": "('setdefault', 'setdefault')",
+          "packages": 4
+        },
+        {
+          "context": "('post', 'post')",
+          "packages": 3
+        },
+        {
+          "context": "('app_context', 'app_context')",
+          "packages": 3
+        },
+        {
+          "context": "('test_client', 'test_client')",
+          "packages": 3
+        }
+      ]
+    },
+    "k3": {
+      "contexts": 599,
+      "sore_successes": 43,
+      "total_methods": 1391,
+      "methods_in_good": 243,
+      "coverage": 17.5,
+      "cross_package_contexts": 40,
+      "elapsed": 0.001,
+      "top_groups": [
+        {
+          "context": "('_eps',)",
+          "label": "raw_k3",
+          "methods": 282,
+          "unique": 1,
+          "unique_ratio": 0.004,
+          "alphabet_size": 0,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('isinstance', 'isinstance', 'isinstance')",
+          "label": "raw_k3",
+          "methods": 66,
+          "unique": 20,
+          "unique_ratio": 0.303,
+          "alphabet_size": 55,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append', 'append')",
+          "label": "raw_k3",
+          "methods": 51,
+          "unique": 1,
+          "unique_ratio": 0.02,
+          "alphabet_size": 1,
+          "sore": "(append)+",
+          "sore_success": true
+        },
+        {
+          "context": "('route', 'route', 'index')",
+          "label": "raw_k3",
+          "methods": 42,
+          "unique": 37,
+          "unique_ratio": 0.881,
+          "alphabet_size": 73,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('render_template', 'render_template')",
+          "label": "raw_k3",
+          "methods": 31,
+          "unique": 1,
+          "unique_ratio": 0.032,
+          "alphabet_size": 1,
+          "sore": "(render_template)+",
+          "sore_success": true
+        },
+        {
+          "context": "('super', 'super', 'super')",
+          "label": "raw_k3",
+          "methods": 16,
+          "unique": 12,
+          "unique_ratio": 0.75,
+          "alphabet_size": 33,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('abort', 'abort')",
+          "label": "raw_k3",
+          "methods": 16,
+          "unique": 1,
+          "unique_ratio": 0.062,
+          "alphabet_size": 1,
+          "sore": "(abort)+",
+          "sore_success": true
+        },
+        {
+          "context": "('get', 'get')",
+          "label": "raw_k3",
+          "methods": 10,
+          "unique": 1,
+          "unique_ratio": 0.1,
+          "alphabet_size": 1,
+          "sore": "(get)+",
+          "sore_success": true
+        },
+        {
+          "context": "('pop', 'pop')",
+          "label": "raw_k3",
+          "methods": 10,
+          "unique": 1,
+          "unique_ratio": 0.1,
+          "alphabet_size": 1,
+          "sore": "(pop)+",
+          "sore_success": true
+        },
+        {
+          "context": "('setdefault', 'setdefault', 'append')",
+          "label": "raw_k3",
+          "methods": 9,
+          "unique": 1,
+          "unique_ratio": 0.111,
+          "alphabet_size": 2,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('render_template', 'render_template')",
+          "packages": 6
+        },
+        {
+          "context": "('get', 'get', 'get')",
+          "packages": 4
+        },
+        {
+          "context": "('isinstance', 'isinstance', 'isinstance')",
+          "packages": 4
+        },
+        {
+          "context": "('Flask', 'Flask', 'from_mapping')",
+          "packages": 3
+        },
+        {
+          "context": "('test_client', 'test_client')",
+          "packages": 3
+        },
+        {
+          "context": "('get', 'get')",
+          "packages": 3
+        },
+        {
+          "context": "('super', 'super', 'super')",
+          "packages": 3
+        },
+        {
+          "context": "('type', 'type', 'type')",
+          "packages": 3
+        },
+        {
+          "context": "('getattr', 'getattr', 'getattr')",
+          "packages": 3
+        }
+      ]
+    }
+  },
+  "coarsened": {
+    "seq_count": 1391,
+    "alphabet_size": 1063,
+    "alphabet_sample": [
+      "",
+      "!r",
+      "\" * 100)",
+      "\")",
+      "\", \"index\",",
+      "\", de",
+      "\", su",
+      "\"/\")",
+      "\"/t",
+      "\"X-Foo\"",
+      "\"about\"",
+      "\"ba",
+      "\"cus",
+      "\"fake a",
+      "\"fo",
+      "\"foo.vi",
+      "\"h",
+      "\"hello\"",
+      "\"lat",
+      "\"mer",
+      "\"nes",
+      "\"someth",
+      "\"spam\")",
+      "\"static",
+      "# ip addre",
+      "(\"\"), 40",
+      "(\"\", hea",
+      "()",
+      "(test",
+      "({\"msg\":"
+    ],
+    "k1": {
+      "contexts": 166,
+      "sore_successes": 3,
+      "total_methods": 1391,
+      "methods_in_good": 20,
+      "coverage": 1.4,
+      "cross_package_contexts": 22,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k1",
+          "methods": 448,
+          "unique": 101,
+          "unique_ratio": 0.225,
+          "alphabet_size": 97,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ATTR',)",
+          "label": "coarsened_k1",
+          "methods": 120,
+          "unique": 112,
+          "unique_ratio": 0.933,
+          "alphabet_size": 296,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('IF',)",
+          "label": "coarsened_k1",
+          "methods": 117,
+          "unique": 109,
+          "unique_ratio": 0.932,
+          "alphabet_size": 209,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('KW',)",
+          "label": "coarsened_k1",
+          "methods": 91,
+          "unique": 80,
+          "unique_ratio": 0.879,
+          "alphabet_size": 246,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('EXCEPTION',)",
+          "label": "coarsened_k1",
+          "methods": 78,
+          "unique": 43,
+          "unique_ratio": 0.551,
+          "alphabet_size": 83,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append',)",
+          "label": "coarsened_k1",
+          "methods": 51,
+          "unique": 3,
+          "unique_ratio": 0.059,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('FUN',)",
+          "label": "coarsened_k1",
+          "methods": 48,
+          "unique": 46,
+          "unique_ratio": 0.958,
+          "alphabet_size": 127,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Blueprint',)",
+          "label": "coarsened_k1",
+          "methods": 40,
+          "unique": 36,
+          "unique_ratio": 0.9,
+          "alphabet_size": 119,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('get',)",
+          "label": "coarsened_k1",
+          "methods": 25,
+          "unique": 24,
+          "unique_ratio": 0.96,
+          "alphabet_size": 61,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Flask',)",
+          "label": "coarsened_k1",
+          "methods": 23,
+          "unique": 23,
+          "unique_ratio": 1.0,
+          "alphabet_size": 69,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('RETURN',)",
+          "packages": 14
+        },
+        {
+          "context": "('get',)",
+          "packages": 7
+        },
+        {
+          "context": "('LOOP',)",
+          "packages": 6
+        },
+        {
+          "context": "('IF',)",
+          "packages": 6
+        },
+        {
+          "context": "('FUN',)",
+          "packages": 5
+        },
+        {
+          "context": "('KW',)",
+          "packages": 5
+        },
+        {
+          "context": "('pop',)",
+          "packages": 4
+        },
+        {
+          "context": "('EXCEPTION',)",
+          "packages": 4
+        },
+        {
+          "context": "('setdefault',)",
+          "packages": 4
+        },
+        {
+          "context": "('Flask',)",
+          "packages": 3
+        }
+      ]
+    },
+    "k2": {
+      "contexts": 353,
+      "sore_successes": 23,
+      "total_methods": 1391,
+      "methods_in_good": 346,
+      "coverage": 24.9,
+      "cross_package_contexts": 49,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k2",
+          "methods": 234,
+          "unique": 1,
+          "unique_ratio": 0.004,
+          "alphabet_size": 1,
+          "sore": "RETURN",
+          "sore_success": true
+        },
+        {
+          "context": "('ATTR', 'ATTR')",
+          "label": "coarsened_k2",
+          "methods": 80,
+          "unique": 74,
+          "unique_ratio": 0.925,
+          "alphabet_size": 171,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('IF', 'KW')",
+          "label": "coarsened_k2",
+          "methods": 67,
+          "unique": 60,
+          "unique_ratio": 0.896,
+          "alphabet_size": 134,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append', 'append')",
+          "label": "coarsened_k2",
+          "methods": 51,
+          "unique": 3,
+          "unique_ratio": 0.059,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('Blueprint', 'Blueprint')",
+          "label": "coarsened_k2",
+          "methods": 40,
+          "unique": 36,
+          "unique_ratio": 0.9,
+          "alphabet_size": 119,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN', 'render_template')",
+          "label": "coarsened_k2",
+          "methods": 33,
+          "unique": 2,
+          "unique_ratio": 0.061,
+          "alphabet_size": 3,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('KW', 'FUN')",
+          "label": "coarsened_k2",
+          "methods": 32,
+          "unique": 30,
+          "unique_ratio": 0.938,
+          "alphabet_size": 122,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN', 'isinstance')",
+          "label": "coarsened_k2",
+          "methods": 32,
+          "unique": 2,
+          "unique_ratio": 0.062,
+          "alphabet_size": 6,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('get', 'get')",
+          "label": "coarsened_k2",
+          "methods": 25,
+          "unique": 24,
+          "unique_ratio": 0.96,
+          "alphabet_size": 61,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ATTR', 'route')",
+          "label": "coarsened_k2",
+          "methods": 24,
+          "unique": 22,
+          "unique_ratio": 0.917,
+          "alphabet_size": 103,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('RETURN',)",
+          "packages": 9
+        },
+        {
+          "context": "('get', 'get')",
+          "packages": 7
+        },
+        {
+          "context": "('RETURN', 'render_template')",
+          "packages": 6
+        },
+        {
+          "context": "('LOOP', 'KW')",
+          "packages": 6
+        },
+        {
+          "context": "('IF', 'KW')",
+          "packages": 5
+        },
+        {
+          "context": "('KW', 'FUN')",
+          "packages": 4
+        },
+        {
+          "context": "('pop', 'pop')",
+          "packages": 4
+        },
+        {
+          "context": "('setdefault', 'setdefault')",
+          "packages": 4
+        },
+        {
+          "context": "('IF', 'isinstance')",
+          "packages": 4
+        },
+        {
+          "context": "('Flask', 'Flask')",
+          "packages": 3
+        }
+      ]
+    },
+    "k3": {
+      "contexts": 529,
+      "sore_successes": 30,
+      "total_methods": 1391,
+      "methods_in_good": 400,
+      "coverage": 28.8,
+      "cross_package_contexts": 47,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k3",
+          "methods": 234,
+          "unique": 1,
+          "unique_ratio": 0.004,
+          "alphabet_size": 1,
+          "sore": "RETURN",
+          "sore_success": true
+        },
+        {
+          "context": "('IF', 'KW', 'KW')",
+          "label": "coarsened_k3",
+          "methods": 34,
+          "unique": 29,
+          "unique_ratio": 0.853,
+          "alphabet_size": 73,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ATTR', 'ATTR', 'route')",
+          "label": "coarsened_k3",
+          "methods": 34,
+          "unique": 31,
+          "unique_ratio": 0.912,
+          "alphabet_size": 74,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN', 'render_template', 'render_template')",
+          "label": "coarsened_k3",
+          "methods": 33,
+          "unique": 2,
+          "unique_ratio": 0.061,
+          "alphabet_size": 3,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('append', 'append')",
+          "label": "coarsened_k3",
+          "methods": 33,
+          "unique": 1,
+          "unique_ratio": 0.03,
+          "alphabet_size": 1,
+          "sore": "(append)+",
+          "sore_success": true
+        },
+        {
+          "context": "('RETURN', 'isinstance', 'isinstance')",
+          "label": "coarsened_k3",
+          "methods": 32,
+          "unique": 2,
+          "unique_ratio": 0.062,
+          "alphabet_size": 6,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ATTR', 'ATTR', 'FUN')",
+          "label": "coarsened_k3",
+          "methods": 31,
+          "unique": 28,
+          "unique_ratio": 0.903,
+          "alphabet_size": 92,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ATTR', 'route', 'route')",
+          "label": "coarsened_k3",
+          "methods": 24,
+          "unique": 22,
+          "unique_ratio": 0.917,
+          "alphabet_size": 103,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('EXCEPTION',)",
+          "label": "coarsened_k3",
+          "methods": 21,
+          "unique": 1,
+          "unique_ratio": 0.048,
+          "alphabet_size": 1,
+          "sore": "EXCEPTION",
+          "sore_success": true
+        },
+        {
+          "context": "('Blueprint', 'Blueprint', 'ATTR')",
+          "label": "coarsened_k3",
+          "methods": 21,
+          "unique": 20,
+          "unique_ratio": 0.952,
+          "alphabet_size": 76,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('RETURN',)",
+          "packages": 9
+        },
+        {
+          "context": "('RETURN', 'render_template', 'render_template')",
+          "packages": 6
+        },
+        {
+          "context": "('get', 'get', 'get')",
+          "packages": 4
+        },
+        {
+          "context": "('IF', 'KW', 'RETURN')",
+          "packages": 4
+        },
+        {
+          "context": "('get', 'get', 'IF')",
+          "packages": 4
+        },
+        {
+          "context": "('IF', 'KW', 'KW')",
+          "packages": 4
+        },
+        {
+          "context": "('IF', 'isinstance', 'isinstance')",
+          "packages": 4
+        },
+        {
+          "context": "('Flask', 'Flask', 'from_mapping')",
+          "packages": 3
+        },
+        {
+          "context": "('RETURN', 'test_client', 'test_client')",
+          "packages": 3
+        },
+        {
+          "context": "('RETURN', 'get', 'get')",
+          "packages": 3
+        }
+      ]
+    }
+  }
+}

experiments/results/coarsen_ragsak.json

@@ -0,0 +1,993 @@
+{
+  "name": "RAGSAK",
+  "raw": {
+    "seq_count": 1594,
+    "alphabet_size": 1724,
+    "alphabet_sample": [
+      "",
+      "\"Cann",
+      "\"Fail",
+      "\"k",
+      "(",
+      "(\"",
+      "()",
+      "(documen",
+      "(val scores: List<Double> = emptyList())",
+      ") && s3",
+      ")) {",
+      ",",
+      ".jo",
+      ".va",
+      "Acti",
+      "AgentCapabilityDescriptor",
+      "AgentDecision",
+      "AgentExecutionContext",
+      "AndServerWebExchangeMatcher",
+      "Any",
+      "AssertionError",
+      "AssistantMessage",
+      "AtomicLong",
+      "AtomicReference",
+      "AuthController",
+      "BCryptPasswordEncoder",
+      "BatchId",
+      "BatchJobController",
+      "BatchJobListener",
+      "BatchNotFoundException"
+    ],
+    "k1": {
+      "contexts": 510,
+      "sore_successes": 39,
+      "total_methods": 1594,
+      "methods_in_good": 125,
+      "coverage": 7.8,
+      "cross_package_contexts": 145,
+      "elapsed": 0.001,
+      "top_groups": [
+        {
+          "context": "('every',)",
+          "label": "raw_k1",
+          "methods": 102,
+          "unique": 93,
+          "unique_ratio": 0.912,
+          "alphabet_size": 232,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest',)",
+          "label": "raw_k1",
+          "methods": 59,
+          "unique": 54,
+          "unique_ratio": 0.915,
+          "alphabet_size": 131,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('listOf',)",
+          "label": "raw_k1",
+          "methods": 37,
+          "unique": 28,
+          "unique_ratio": 0.757,
+          "alphabet_size": 99,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "raw_k1",
+          "methods": 31,
+          "unique": 21,
+          "unique_ratio": 0.677,
+          "alphabet_size": 99,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runBlocking',)",
+          "label": "raw_k1",
+          "methods": 29,
+          "unique": 28,
+          "unique_ratio": 0.966,
+          "alphabet_size": 115,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('trim',)",
+          "label": "raw_k1",
+          "methods": 27,
+          "unique": 24,
+          "unique_ratio": 0.889,
+          "alphabet_size": 59,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('warn',)",
+          "label": "raw_k1",
+          "methods": 26,
+          "unique": 4,
+          "unique_ratio": 0.154,
+          "alphabet_size": 10,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('builder',)",
+          "label": "raw_k1",
+          "methods": 25,
+          "unique": 24,
+          "unique_ratio": 0.96,
+          "alphabet_size": 128,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('info',)",
+          "label": "raw_k1",
+          "methods": 23,
+          "unique": 19,
+          "unique_ratio": 0.826,
+          "alphabet_size": 73,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('parse',)",
+          "label": "raw_k1",
+          "methods": 18,
+          "unique": 18,
+          "unique_ratio": 1.0,
+          "alphabet_size": 49,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('every',)",
+          "packages": 18
+        },
+        {
+          "context": "('builder',)",
+          "packages": 16
+        },
+        {
+          "context": "('listOf',)",
+          "packages": 13
+        },
+        {
+          "context": "('runTest',)",
+          "packages": 12
+        },
+        {
+          "context": "('info',)",
+          "packages": 11
+        },
+        {
+          "context": "('mockk',)",
+          "packages": 11
+        },
+        {
+          "context": "('trim',)",
+          "packages": 10
+        },
+        {
+          "context": "('isEmpty',)",
+          "packages": 9
+        },
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('debug',)",
+          "packages": 9
+        }
+      ]
+    },
+    "k2": {
+      "contexts": 918,
+      "sore_successes": 76,
+      "total_methods": 1594,
+      "methods_in_good": 249,
+      "coverage": 15.6,
+      "cross_package_contexts": 100,
+      "elapsed": 0.001,
+      "top_groups": [
+        {
+          "context": "('listOf', 'listOf')",
+          "label": "raw_k2",
+          "methods": 37,
+          "unique": 28,
+          "unique_ratio": 0.757,
+          "alphabet_size": 99,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('warn', 'status')",
+          "label": "raw_k2",
+          "methods": 22,
+          "unique": 1,
+          "unique_ratio": 0.045,
+          "alphabet_size": 4,
+          "sore": "warn.status.body.ErrorResponse",
+          "sore_success": true
+        },
+        {
+          "context": "('_eps',)",
+          "label": "raw_k2",
+          "methods": 16,
+          "unique": 1,
+          "unique_ratio": 0.062,
+          "alphabet_size": 0,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('VectorChunk', 'mapOf')",
+          "label": "raw_k2",
+          "methods": 13,
+          "unique": 11,
+          "unique_ratio": 0.846,
+          "alphabet_size": 42,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ery {', 'stKnowledgeBases()')",
+          "label": "raw_k2",
+          "methods": 13,
+          "unique": 5,
+          "unique_ratio": 0.385,
+          "alphabet_size": 13,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('productionClasses', 'filter')",
+          "label": "raw_k2",
+          "methods": 13,
+          "unique": 13,
+          "unique_ratio": 1.0,
+          "alphabet_size": 16,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "raw_k2",
+          "methods": 11,
+          "unique": 1,
+          "unique_ratio": 0.091,
+          "alphabet_size": 1,
+          "sore": "mockk",
+          "sore_success": true
+        },
+        {
+          "context": "('filesIn', 'assertTrue')",
+          "label": "raw_k2",
+          "methods": 11,
+          "unique": 5,
+          "unique_ratio": 0.455,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest', 'ChatResponse')",
+          "label": "raw_k2",
+          "methods": 10,
+          "unique": 10,
+          "unique_ratio": 1.0,
+          "alphabet_size": 36,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest', 'mockk')",
+          "label": "raw_k2",
+          "methods": 9,
+          "unique": 7,
+          "unique_ratio": 0.778,
+          "alphabet_size": 27,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('listOf', 'listOf')",
+          "packages": 13
+        },
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('trim', 'lowercase')",
+          "packages": 5
+        },
+        {
+          "context": "('mutableListOf', 'mutableListOf')",
+          "packages": 5
+        },
+        {
+          "context": "('defaultCapabilityId',)",
+          "packages": 4
+        },
+        {
+          "context": "('every', 'defaultCapabilityId')",
+          "packages": 4
+        },
+        {
+          "context": "('clearAllMocks',)",
+          "packages": 4
+        },
+        {
+          "context": "('VectorChunk', 'mapOf')",
+          "packages": 4
+        },
+        {
+          "context": "('Builder',)",
+          "packages": 4
+        },
+        {
+          "context": "('Any',)",
+          "packages": 4
+        }
+      ]
+    },
+    "k3": {
+      "contexts": 1066,
+      "sore_successes": 89,
+      "total_methods": 1594,
+      "methods_in_good": 297,
+      "coverage": 18.6,
+      "cross_package_contexts": 69,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('warn', 'status', 'body')",
+          "label": "raw_k3",
+          "methods": 22,
+          "unique": 1,
+          "unique_ratio": 0.045,
+          "alphabet_size": 4,
+          "sore": "warn.status.body.ErrorResponse",
+          "sore_success": true
+        },
+        {
+          "context": "('_eps',)",
+          "label": "raw_k3",
+          "methods": 16,
+          "unique": 1,
+          "unique_ratio": 0.062,
+          "alphabet_size": 0,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('VectorChunk', 'mapOf', 'mapOf')",
+          "label": "raw_k3",
+          "methods": 13,
+          "unique": 11,
+          "unique_ratio": 0.846,
+          "alphabet_size": 42,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ery {', 'stKnowledgeBases()', 'gRequest(m')",
+          "label": "raw_k3",
+          "methods": 12,
+          "unique": 4,
+          "unique_ratio": 0.333,
+          "alphabet_size": 11,
+          "sore": "ery {.stKnowledgeBases().gRequest(m.(ckKnowledgeBase(re.ertEquals(Kn.\"k|eckKnowledgeBase(r.(sertEquals(K.(\"|(sertEquals(t|sertNull(o)))",
+          "sore_success": true
+        },
+        {
+          "context": "('listOf', 'listOf', 'productionFiles')",
+          "label": "raw_k3",
+          "methods": 12,
+          "unique": 6,
+          "unique_ratio": 0.5,
+          "alphabet_size": 9,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "raw_k3",
+          "methods": 11,
+          "unique": 1,
+          "unique_ratio": 0.091,
+          "alphabet_size": 1,
+          "sore": "mockk",
+          "sore_success": true
+        },
+        {
+          "context": "('File', 'writeBytes', 'byteArrayOf')",
+          "label": "raw_k3",
+          "methods": 8,
+          "unique": 7,
+          "unique_ratio": 0.875,
+          "alphabet_size": 25,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest', 'ChatResponse', 'emptyList')",
+          "label": "raw_k3",
+          "methods": 7,
+          "unique": 7,
+          "unique_ratio": 1.0,
+          "alphabet_size": 33,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('filesIn', 'assertTrue', 'hasImport')",
+          "label": "raw_k3",
+          "methods": 7,
+          "unique": 2,
+          "unique_ratio": 0.286,
+          "alphabet_size": 3,
+          "sore": "filesIn.assertTrue.(hasImport)+",
+          "sore_success": true
+        },
+        {
+          "context": "('assertEquals', 'of', 'assertFailsWith')",
+          "label": "raw_k3",
+          "methods": 7,
+          "unique": 3,
+          "unique_ratio": 0.429,
+          "alphabet_size": 3,
+          "sore": "assertEquals.(of.(assertFailsWith)?)+",
+          "sore_success": true
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('_eps',)",
+          "packages": 9
+        },
+        {
+          "context": "('defaultCapabilityId',)",
+          "packages": 4
+        },
+        {
+          "context": "('clearAllMocks',)",
+          "packages": 4
+        },
+        {
+          "context": "('VectorChunk', 'mapOf', 'mapOf')",
+          "packages": 4
+        },
+        {
+          "context": "('Builder',)",
+          "packages": 4
+        },
+        {
+          "context": "('Any',)",
+          "packages": 4
+        },
+        {
+          "context": "('get',)",
+          "packages": 4
+        },
+        {
+          "context": "('registerProperties',)",
+          "packages": 4
+        },
+        {
+          "context": "('assumeTrue', 'isDockerAvailable', 'start')",
+          "packages": 4
+        },
+        {
+          "context": "('listOf', 'listOf', 'forEach')",
+          "packages": 4
+        }
+      ]
+    }
+  },
+  "coarsened": {
+    "seq_count": 1594,
+    "alphabet_size": 1728,
+    "alphabet_sample": [
+      "",
+      "\"Cann",
+      "\"Fail",
+      "\"k",
+      "(",
+      "(\"",
+      "()",
+      "(documen",
+      "(val scores: List<Double> = emptyList())",
+      ") && s3",
+      ")) {",
+      ",",
+      ".jo",
+      ".va",
+      "ATTR",
+      "Acti",
+      "AgentCapabilityDescriptor",
+      "AgentDecision",
+      "AgentExecutionContext",
+      "AndServerWebExchangeMatcher",
+      "Any",
+      "AssertionError",
+      "AssistantMessage",
+      "AtomicLong",
+      "AtomicReference",
+      "AuthController",
+      "BCryptPasswordEncoder",
+      "BatchId",
+      "BatchJobController",
+      "BatchJobListener"
+    ],
+    "k1": {
+      "contexts": 474,
+      "sore_successes": 33,
+      "total_methods": 1594,
+      "methods_in_good": 107,
+      "coverage": 6.7,
+      "cross_package_contexts": 128,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('every',)",
+          "label": "coarsened_k1",
+          "methods": 102,
+          "unique": 93,
+          "unique_ratio": 0.912,
+          "alphabet_size": 232,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k1",
+          "methods": 91,
+          "unique": 75,
+          "unique_ratio": 0.824,
+          "alphabet_size": 186,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest',)",
+          "label": "coarsened_k1",
+          "methods": 59,
+          "unique": 54,
+          "unique_ratio": 0.915,
+          "alphabet_size": 131,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('listOf',)",
+          "label": "coarsened_k1",
+          "methods": 36,
+          "unique": 27,
+          "unique_ratio": 0.75,
+          "alphabet_size": 95,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "coarsened_k1",
+          "methods": 31,
+          "unique": 21,
+          "unique_ratio": 0.677,
+          "alphabet_size": 100,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runBlocking',)",
+          "label": "coarsened_k1",
+          "methods": 29,
+          "unique": 28,
+          "unique_ratio": 0.966,
+          "alphabet_size": 117,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('trim',)",
+          "label": "coarsened_k1",
+          "methods": 26,
+          "unique": 23,
+          "unique_ratio": 0.885,
+          "alphabet_size": 57,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('warn',)",
+          "label": "coarsened_k1",
+          "methods": 26,
+          "unique": 4,
+          "unique_ratio": 0.154,
+          "alphabet_size": 11,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('builder',)",
+          "label": "coarsened_k1",
+          "methods": 24,
+          "unique": 23,
+          "unique_ratio": 0.958,
+          "alphabet_size": 126,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('info',)",
+          "label": "coarsened_k1",
+          "methods": 23,
+          "unique": 19,
+          "unique_ratio": 0.826,
+          "alphabet_size": 74,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('RETURN',)",
+          "packages": 36
+        },
+        {
+          "context": "('every',)",
+          "packages": 18
+        },
+        {
+          "context": "('builder',)",
+          "packages": 15
+        },
+        {
+          "context": "('runTest',)",
+          "packages": 12
+        },
+        {
+          "context": "('listOf',)",
+          "packages": 12
+        },
+        {
+          "context": "('info',)",
+          "packages": 11
+        },
+        {
+          "context": "('mockk',)",
+          "packages": 11
+        },
+        {
+          "context": "('trim',)",
+          "packages": 10
+        },
+        {
+          "context": "('isEmpty',)",
+          "packages": 9
+        },
+        {
+          "context": "('debug',)",
+          "packages": 9
+        }
+      ]
+    },
+    "k2": {
+      "contexts": 883,
+      "sore_successes": 69,
+      "total_methods": 1594,
+      "methods_in_good": 225,
+      "coverage": 14.1,
+      "cross_package_contexts": 108,
+      "elapsed": 0.001,
+      "top_groups": [
+        {
+          "context": "('listOf', 'listOf')",
+          "label": "coarsened_k2",
+          "methods": 36,
+          "unique": 27,
+          "unique_ratio": 0.75,
+          "alphabet_size": 95,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('warn', 'RETURN')",
+          "label": "coarsened_k2",
+          "methods": 23,
+          "unique": 2,
+          "unique_ratio": 0.087,
+          "alphabet_size": 7,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k2",
+          "methods": 13,
+          "unique": 1,
+          "unique_ratio": 0.077,
+          "alphabet_size": 1,
+          "sore": "RETURN",
+          "sore_success": true
+        },
+        {
+          "context": "('VectorChunk', 'mapOf')",
+          "label": "coarsened_k2",
+          "methods": 13,
+          "unique": 11,
+          "unique_ratio": 0.846,
+          "alphabet_size": 42,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ery {', 'stKnowledgeBases()')",
+          "label": "coarsened_k2",
+          "methods": 13,
+          "unique": 5,
+          "unique_ratio": 0.385,
+          "alphabet_size": 13,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('productionClasses', 'filter')",
+          "label": "coarsened_k2",
+          "methods": 13,
+          "unique": 13,
+          "unique_ratio": 1.0,
+          "alphabet_size": 16,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('isEmpty', 'RETURN')",
+          "label": "coarsened_k2",
+          "methods": 12,
+          "unique": 12,
+          "unique_ratio": 1.0,
+          "alphabet_size": 59,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "coarsened_k2",
+          "methods": 11,
+          "unique": 1,
+          "unique_ratio": 0.091,
+          "alphabet_size": 1,
+          "sore": "mockk",
+          "sore_success": true
+        },
+        {
+          "context": "('filesIn', 'assertTrue')",
+          "label": "coarsened_k2",
+          "methods": 11,
+          "unique": 5,
+          "unique_ratio": 0.455,
+          "alphabet_size": 4,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('RETURN', 'RETURN')",
+          "label": "coarsened_k2",
+          "methods": 10,
+          "unique": 10,
+          "unique_ratio": 1.0,
+          "alphabet_size": 15,
+          "sore": null,
+          "sore_success": false
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('listOf', 'listOf')",
+          "packages": 12
+        },
+        {
+          "context": "('isEmpty', 'RETURN')",
+          "packages": 9
+        },
+        {
+          "context": "('RETURN',)",
+          "packages": 9
+        },
+        {
+          "context": "('RETURN', 'RETURN')",
+          "packages": 7
+        },
+        {
+          "context": "('trim', 'lowercase')",
+          "packages": 5
+        },
+        {
+          "context": "('mutableListOf', 'mutableListOf')",
+          "packages": 5
+        },
+        {
+          "context": "('defaultCapabilityId',)",
+          "packages": 4
+        },
+        {
+          "context": "('every', 'defaultCapabilityId')",
+          "packages": 4
+        },
+        {
+          "context": "('clearAllMocks',)",
+          "packages": 4
+        },
+        {
+          "context": "('VectorChunk', 'mapOf')",
+          "packages": 4
+        }
+      ]
+    },
+    "k3": {
+      "contexts": 1062,
+      "sore_successes": 82,
+      "total_methods": 1594,
+      "methods_in_good": 292,
+      "coverage": 18.3,
+      "cross_package_contexts": 74,
+      "elapsed": 0.0,
+      "top_groups": [
+        {
+          "context": "('warn', 'RETURN', 'status')",
+          "label": "coarsened_k3",
+          "methods": 22,
+          "unique": 1,
+          "unique_ratio": 0.045,
+          "alphabet_size": 5,
+          "sore": "warn.RETURN.status.body.ErrorResponse",
+          "sore_success": true
+        },
+        {
+          "context": "('RETURN',)",
+          "label": "coarsened_k3",
+          "methods": 13,
+          "unique": 1,
+          "unique_ratio": 0.077,
+          "alphabet_size": 1,
+          "sore": "RETURN",
+          "sore_success": true
+        },
+        {
+          "context": "('VectorChunk', 'mapOf', 'mapOf')",
+          "label": "coarsened_k3",
+          "methods": 13,
+          "unique": 11,
+          "unique_ratio": 0.846,
+          "alphabet_size": 42,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('ery {', 'stKnowledgeBases()', 'gRequest(m')",
+          "label": "coarsened_k3",
+          "methods": 12,
+          "unique": 4,
+          "unique_ratio": 0.333,
+          "alphabet_size": 11,
+          "sore": "ery {.stKnowledgeBases().gRequest(m.(ckKnowledgeBase(re.ertEquals(Kn.\"k|eckKnowledgeBase(r.(sertEquals(K.(\"|(sertEquals(t|sertNull(o)))",
+          "sore_success": true
+        },
+        {
+          "context": "('listOf', 'listOf', 'productionFiles')",
+          "label": "coarsened_k3",
+          "methods": 12,
+          "unique": 6,
+          "unique_ratio": 0.5,
+          "alphabet_size": 9,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('mockk',)",
+          "label": "coarsened_k3",
+          "methods": 11,
+          "unique": 1,
+          "unique_ratio": 0.091,
+          "alphabet_size": 1,
+          "sore": "mockk",
+          "sore_success": true
+        },
+        {
+          "context": "('parseStorageUri', 'RETURN', 'RETURN')",
+          "label": "coarsened_k3",
+          "methods": 8,
+          "unique": 5,
+          "unique_ratio": 0.625,
+          "alphabet_size": 14,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('File', 'writeBytes', 'byteArrayOf')",
+          "label": "coarsened_k3",
+          "methods": 8,
+          "unique": 7,
+          "unique_ratio": 0.875,
+          "alphabet_size": 25,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('runTest', 'ChatResponse', 'emptyList')",
+          "label": "coarsened_k3",
+          "methods": 7,
+          "unique": 7,
+          "unique_ratio": 1.0,
+          "alphabet_size": 33,
+          "sore": null,
+          "sore_success": false
+        },
+        {
+          "context": "('filesIn', 'assertTrue', 'hasImport')",
+          "label": "coarsened_k3",
+          "methods": 7,
+          "unique": 2,
+          "unique_ratio": 0.286,
+          "alphabet_size": 3,
+          "sore": "filesIn.assertTrue.(hasImport)+",
+          "sore_success": true
+        }
+      ],
+      "cross_pkg_examples": [
+        {
+          "context": "('RETURN',)",
+          "packages": 9
+        },
+        {
+          "context": "('defaultCapabilityId',)",
+          "packages": 4
+        },
+        {
+          "context": "('clearAllMocks',)",
+          "packages": 4
+        },
+        {
+          "context": "('VectorChunk', 'mapOf', 'mapOf')",
+          "packages": 4
+        },
+        {
+          "context": "('Builder',)",
+          "packages": 4
+        },
+        {
+          "context": "('Any',)",
+          "packages": 4
+        },
+        {
+          "context": "('get',)",
+          "packages": 4
+        },
+        {
+          "context": "('registerProperties',)",
+          "packages": 4
+        },
+        {
+          "context": "('assumeTrue', 'isDockerAvailable', 'start')",
+          "packages": 4
+        },
+        {
+          "context": "('listOf', 'listOf', 'forEach')",
+          "packages": 4
+        }
+      ]
+    }
+  }
+}