openpr_J_v3_1.txt

====================================================================================================
CASE J  PR #36698  (open-pr, v3.1 prompt)
file: Mathlib/Combinatorics/Enumerative/LatinSquare.lean  line: 257.0
reviewer: @vlad902  on 2026-03-17T07:34:52Z
advice_kind: refactor (suggestion block)
prompt_tokens: 5980  completion_tokens: 1783
HUMAN reviewer (ground truth):
  > ```suggestion
  >   once_per_row i' :=
  >     h.bijective.comp (A.once_per_row (f.symm i') |>.comp g.symm.bijective)
  > ```
====================================================================================================

[SYSTEM]
----------------------------------------------------------------------------------------------------
You are an expert reviewer for the Lean 4 / mathlib4 mathematical library. Given a NEW code hunk from an open pull request and a set of historically retrieved (past_hunk, past_comment) pairs, your job is to identify which past reviewer feedback would also apply to the new hunk.

Two failure modes are equally bad and you must avoid BOTH:
  (X) "axis-miss" false positive: a past comment and the new code look similar on the surface, but the past reviewer's concern is not present in the new hunk. (Example: past comment is about `ppSpace` formatting, new hunk's actual problem is "this whole function shouldn't return a string".)
  (Y) "over-refusal" false negative: a candidate IS genuinely applicable, but you refuse because its concern axis didn't appear in your initial inventory. (Example: you forgot to list `refactor-simplify` for a proof hunk, then declined a candidate that correctly suggests using a higher-level lemma.)

A correct silent output is more valuable than a confident wrong-axis answer, but losing a clearly-applicable candidate is also a real cost.

Read carefully before producing JSON. Follow the four steps below in order.

STEP 1 — STRUCTURAL + SEMANTIC READING OF THE NEW HUNK.
  1a. Parse the code shape: tactic-mode vs term-mode, declaration kind (`def` / `theorem` / `lemma` / `instance` / `class` / `structure` / `abbrev` / `syntax` / `notation`), attributes (`@[simp]`, `@[to_additive]`, `@[deprecated]`, `@[ext]`, `@[fun_prop]`, `@[reassoc]`, …), universe parameters, implicit/explicit binders, docstring style, proof tactics used.
  1b. Inventory what *could* be criticized about THIS specific hunk. Pick as many as apply from this list of "concern axes":
     - correctness-bug        (code doesn't typecheck / is logically wrong)
     - naming                  (lemma/def name doesn't follow conventions)
     - docstring               (missing, unclear, typo, wrong phrasing)
     - attribute               (missing/wrong `@[simp]` / `@[to_additive]` …)
     - style-syntax            (`fun x ↦` vs `fun x =>`, `by use _; exact _` vs `⟨_, _⟩`, whitespace/`ppSpace`, notation preference)
     - proof-golf              (the proof tactics could be shorter/nicer)
     - refactor-simplify       (same statement provable with less machinery, e.g. use a dedicated higher-level lemma instead of manual rewriting)
     - generalize-signature    (hypotheses too strong; remove/weaken a typeclass)
     - design-smell-architectural (this API shape is wrong; returning a string, unnecessary instance, redundant definition, etc.)
     - imports-module          (superfluous imports, module structure)
     - namespace-organization  (`_root_`, namespace boundary, file placement)
     - automation-tactic       (should use / should teach `aesop_cat`, `gcongr`, `positivity`, etc.)
     - instance-diamond        (this instance creates an ambiguity / defeq diamond with another)
     - unify-with-existing     (a similar definition/lemma already exists)
     - junk-value              (docstring should note behavior at the "undefined" input; handled via `0`/`⊥`/`⊤`)
  1c. DEFAULT-INCLUDE RULE. For ANY non-trivial proof or definition hunk (i.e. not a pure-imports/notation/file-header hunk), you MUST include the following axes in your plausible list unless the hunk is so trivial that they cannot apply: `refactor-simplify`, `proof-golf`, `docstring`, `naming`. These are the most common reviewer concerns; gating them out by omission caused real misses in past evaluation. Adding them is cheap; they only trigger a promotion if a candidate also matches.
  1d. List the concerns that PLAUSIBLY apply to the new hunk (including the defaults from 1c). If none from outside 1c are obviously present, that is fine — the defaults still cover proof/definition hunks.

STEP 2 — PER-CANDIDATE CONCERN CLASSIFICATION.
  For EACH candidate, identify which concern axis (from the same list) the past reviewer's comment was about. Read the past comment carefully: the reviewer's *words* (not the past code) tell you the concern axis. If a past comment ships a `suggestion` code block, that block is evidence for what the reviewer wanted changed — but the axis of concern comes from the prose around it. Ignore candidates whose past comment is pure bikeshed or where you cannot identify a clear concern.

STEP 3 — AXIS MATCH + APPLICABILITY CHECK.
  A candidate is eligible for `strong_matches` ONLY if BOTH:
    (a) Its axis (from step 2) is among the new hunk's plausible concerns (from step 1d), OR you can clearly justify (in `applies_because`) why this axis IS present in the new hunk after all — in which case ADD that axis to `new_hunk_plausible_concerns` in your output. Late additions are allowed but should be the exception, not the rule.
    (b) You can write a concrete adaptation that a Lean/mathlib reviewer would plausibly post on the new hunk *today*, given what is visible in the hunk.
  Before promoting, write — in the JSON output, per match — a `why_might_not_apply` field giving the strongest counter-argument against promotion (one short sentence).

  DEMOTION RULE (this is the #1 axis-miss-prevention lever):
    If your counter-argument names a SPECIFIC PROPERTY of the new hunk that would make the past advice not apply or already-followed — e.g. "the new code already uses term-mode", "the lemma is already named correctly", "the import is actually used at line X", "the new code does not declare an instance, so the diamond risk does not apply" — then DEMOTE to `weak_observations` instead of promoting.
    Only PROMOTE if the counter-argument is generic doubt that does NOT identify a specific reason the new hunk evades the past advice — e.g. "this is partly stylistic preference", "the user may have intended this", "I cannot verify without seeing more context". Generic doubt does not block promotion; specific evasion does.

  Cross-candidate synthesis is allowed: if candidate X establishes that an identifier in the new hunk is a `class`, and candidate Y shows the preferred term-mode `instance := ⟨...⟩` template, they jointly support a promotion. List both in `supporting_past_prs` and still produce one `why_might_not_apply`.

STEP 4 — CONFIDENCE AND OUTPUT.
  Confidence scale:
    - "high"   — ≥1 strong match survives step 3 AND the adaptation is a near-verbatim application of a past comment; the counter-argument is generic.
    - "medium" — ≥1 strong match survives step 3 BUT needs adaptation or synthesis; counter-argument is generic doubt rather than specific evasion.
    - "low"    — no candidate survives step 3; only stylistic patterns worth mentioning as `weak_observations`.
    - "none"   — retrieved pool's concerns don't match anything plausible about the new hunk; state this and stop.

Output JSON ONLY, matching this exact schema:

{
  "new_hunk_plausible_concerns": [<axis labels from Step 1d, plus any added in Step 3a>],
  "summary": "<one sentence describing what we found>",
  "confidence": "high"|"medium"|"low"|"none",
  "strong_matches": [
    {
      "past_pr": <int>,
      "past_file": "<string>",
      "past_concern_axis": "<axis label from the list>",
      "past_comment_excerpt": "<verbatim short quote from the past comment OR the relevant snippet from its suggestion block>",
      "applies_because": "<one or two sentences linking past code/comment to the new hunk's structure AND explaining why the concern axis matches>",
      "suggested_adaptation": "<one sentence on what the reviewer might say on the new hunk>",
      "why_might_not_apply": "<one short sentence — strongest counter-argument against this promotion>",
      "supporting_past_prs": [<int>, ...]
    }
  ],
  "weak_observations": [
    {
      "observation": "<short string>",
      "axis": "<axis label>",
      "supporting_past_prs": [<int>, ...]
    }
  ]
}

Quote short — under 40 words per excerpt. Do not invent axis labels outside the list.

[USER]
----------------------------------------------------------------------------------------------------
NEW HUNK from open PR #36698 (file: Mathlib/Combinatorics/Enumerative/LatinSquare.lean):
```
@@ -0,0 +1,933 @@
... [217 lines above hidden]
+      exact Group.mulLeft_bijective (G := G),
+    once_per_column := by
+      simp only [OncePerColumn, Matrix.col]
+      exact Group.mulRight_bijective (G := G)
+   }
+
+
+@[expose] public section Equivalence
+
+/-- Given relabeling maps for the rows, columns, and symbols,
+    produce the relabeled Latin rectangle. -/
+@[reducible]
+def renameLatinRectangle
+    (f : m ≃ m')
+    (g : n ≃ n')
+    (h : α ≃ β)
+    (A : LatinRectangle m n α) :
+    LatinRectangle m' n' β := {
+  M := fun i' j' ↦ h (A.M (f.symm i') (g.symm j')),
+  exactly_n_symbols := by
+    have g' : Fintype.card n = Fintype.card n' := Fintype.card_congr g
+    have h' : Fintype.card α = Fintype.card β := Fintype.card_congr h
+    have k' := A.exactly_n_symbols
+    omega,
+  once_per_row := by
+    simp only [OncePerRow, Matrix.row]
+    have h' := A.once_per_row
+    simp only [OncePerRow, Matrix.row] at h'
+    intro i'
+    specialize h' (f.symm i') --(h.symm b')
+    have h_comp :
+      (fun j' ↦ h (LatinRectangle.M (f.symm i') (g.symm j'))) =
+      h ∘ (LatinRectangle.M (f.symm i')) ∘ g.symm := by
+      ext
+      simp
+    rw [h_comp]
+    apply Function.Bijective.comp
+    · exact Equiv.bijective h
+    · apply Function.Bijective.comp
+      · exact h'
+      · exact Equiv.bijective g.symm,
```

RETRIEVED CANDIDATES (top-20 by hunk-embedding similarity, sorted by sim desc):

--- candidate 1 (sim=0.662, past_pr=#10834, file=NatNumberCategories) ---
PAST HUNK:
```
@@ -0,0 +1,416 @@
+/-
+Copyright (c) 2024 Colin Jones. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Author: Colin Jones
+-/
+import Mathlib
```
PAST COMMENT (from reviewer):
This file is supposed to be part of Mathlib, it can't import mathlib without creating an infinite loop. Just import the files you need:
```suggestion
import Mathlib.Algebra.GeomSum
import Mathlib.NumberTheory.Divisors
import Mathlib.Tactic.NormNum.Prime
import Mathlib.Analysis.Normed.Field.Basic
```

--- candidate 2 (sim=0.648, past_pr=#2960, file=Mathlib/Data/Matrix/Basic.lean) ---
PAST HUNK:
```
@@ -0,0 +1,2829 @@
... [2476 lines above hidden]
+  invFun M := M.submatrix eₘ eₙ
+  left_inv M := by simp
+  right_inv M := by simp
+#align matrix.reindex Matrix.reindex
+
+@[simp]
+theorem reindex_apply (eₘ : m ≃ l) (eₙ : n ≃ o) (M : Matrix m n α) :
+    reindex eₘ eₙ M = M.submatrix eₘ.symm eₙ.symm :=
+  rfl
+#align matrix.reindex_apply Matrix.reindex_apply
+
+-- @[simp] -- Porting note: simp can prove this
+theorem reindex_refl_refl (A : Matrix m n α) : reindex (Equiv.refl _) (Equiv.refl _) A = A :=
```
PAST COMMENT (from reviewer):
Whoops, this one was probably meant to say something else. That's out of scope here though.

--- candidate 3 (sim=0.648, past_pr=#28708, file=Mathlib/Data/Matrix/Stochastic.lean) ---
PAST HUNK:
```
@@ -0,0 +1,250 @@
+/-
+Copyright (c) 2025 Steven Herbert. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Steven Herbert
+-/
+
+import Mathlib.Data.Matrix.Basic
```
PAST COMMENT (from reviewer):
```suggestion
import Mathlib.Data.Matrix.Basic
import Mathlib.Data.Matrix.Mul
```

--- candidate 4 (sim=0.642, past_pr=#1874, file=Mathlib/GroupTheory/Coset.lean) ---
PAST HUNK:
```
@@ -0,0 +1,891 @@
... [859 lines above hidden]
+
+end Subgroup
+
+namespace QuotientGroup
+
+variable [Group α]
+
+/-- If `s` is a subgroup of the group `α`, and `t` is a subset of `α ⧸ s`, then there is a
+(typically non-canonical) bijection between the preimage of `t` in `α` and the product `s × t`. -/
+@[to_additive "If `s` is a subgroup of the additive group `α`, and `t` is a subset of `α ⧸ s`, then
+ there is a (typically non-canonical) bijection between the preimage of `t` in `α` and the product
+ `s × t`."]
+noncomputable def preimageMkEquivSubgroupTimesSet (s : Subgroup α) (t : Set (α ⧸ s)) :
```
PAST COMMENT (from reviewer):
```suggestion
noncomputable def preimageMkEquivSubgroupProdSet (s : Subgroup α) (t : Set (α ⧸ s)) :
```

--- candidate 5 (sim=0.641, past_pr=#1874, file=Mathlib/GroupTheory/Coset.lean) ---
PAST HUNK:
```
@@ -0,0 +1,891 @@
... [876 lines above hidden]
+        leftRel_apply.mp (@Quotient.exact' _ (leftRel s) _ _ <| Quotient.out_eq' _)⟩,
+      ⟨QuotientGroup.mk a, a.2⟩⟩
+  invFun a :=
+    ⟨Quotient.out' a.2.1 * a.1.1,
+      show QuotientGroup.mk _ ∈ t by
+        rw [mk_mul_of_mem _ a.1.2, out_eq']
+        exact a.2.2⟩
+  left_inv := fun ⟨a, ha⟩ => Subtype.eq <| show _ * _ = a by simp
+  right_inv := fun ⟨⟨a, ha⟩, ⟨x, hx⟩⟩ => by ext <;> simp [ha]
+#align quotient_group.preimage_mk_equiv_subgroup_times_set
+  QuotientGroup.preimageMkEquivSubgroupTimesSet
+#align quotient_add_group.preimage_mk_equiv_add_subgroup_times_set
+  QuotientAddGroup.preimageMkEquivAddSubgroupTimesSet
```
PAST COMMENT (from reviewer):
```suggestion
#align quotient_group.preimage_mk_equiv_subgroup_times_set QuotientGroup.preimageMkEquivSubgroupProdSet
#align quotient_add_group.preimage_mk_equiv_add_subgroup_times_set QuotientAddGroup.preimageMkEquivAddSubgroupProdSet
```

--- candidate 6 (sim=0.640, past_pr=#21148, file=Mathlib/RingTheory/MatrixAlgebra.lean) ---
PAST HUNK:
```
@@ -4,23 +4,90 @@ Released under Apache 2.0 license as described in the file LICENSE.
 Authors: Kim Morrison, Eric Wieser
 -/
 import Mathlib.Data.Matrix.Basis
+import Mathlib.Data.Matrix.Composition
```
PAST COMMENT (from reviewer):
maybe open a new file just to make the large import happy?

--- candidate 7 (sim=0.640, past_pr=#21148, file=Mathlib/RingTheory/MatrixAlgebra.lean) ---
PAST HUNK:
```
@@ -4,23 +4,90 @@ Released under Apache 2.0 license as described in the file LICENSE.
 Authors: Kim Morrison, Eric Wieser
 -/
 import Mathlib.Data.Matrix.Basis
+import Mathlib.Data.Matrix.Composition
```
PAST COMMENT (from reviewer):
I wouldn't mind it so much if it was just this file and `PolynomialAlgebra`, but it does bump the imports of `Localization.Algebra` and its downstream files by quite a bit too. I wouldn't expect those to even know about matrices.

Maybe we should be flipping the import direction `MatrixAlgebra -> PolynomialAlgebra`?

--- candidate 8 (sim=0.637, past_pr=#6526, file=Mathlib/Algebra/Ring/UnitEquivs.lean) ---
PAST HUNK:
```
@@ -0,0 +1,69 @@
+/-
+Copyright (c) 2021 Johan Commelin. All rights reserved.
```
PAST COMMENT (from reviewer):
Is this a copy-paste error?
```suggestion
Copyright (c) 2023 Eric Rodriguez. All rights reserved.
```
Same remark for `Authors` field on line 4, though maybe this is co-authored?

--- candidate 9 (sim=0.636, past_pr=#28100, file=Mathlib/LinearAlgebra/Matrix/GeneralLinearGroup/Basic.lean) ---
PAST HUNK:
```
@@ -14,6 +15,79 @@ see `LinearAlgebra/Matrix/GeneralLinearGroup/Defs.lean`.
 
 namespace Matrix
 
+open Matrix LinearMap
+
+variable {R n : Type*} [Fintype n]
```
PAST COMMENT (from reviewer):
```suggestion
variable {R V : Type*} [AddCommGroup V]
```

--- candidate 10 (sim=0.635, past_pr=#9428, file=Mathlib/AlgebraicTopology/SingularSet.lean) ---
PAST HUNK:
```
@@ -0,0 +1,71 @@
+/-
+Copyright (c) 2024 Johan Commelin. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Johan Commelin, Scott Morrison, Adam Topaz
```
PAST COMMENT (from reviewer):
Ah, I guess [we've argued this before](https://leanprover.zulipchat.com/#narrow/stream/113488-general/topic/Copyright.20header/near/280420005). I always take it to be the year the oldest definition/lemma of the file was created.

--- candidate 11 (sim=0.635, past_pr=#9428, file=Mathlib/AlgebraicTopology/SingularSet.lean) ---
PAST HUNK:
```
@@ -0,0 +1,71 @@
+/-
+Copyright (c) 2024 Johan Commelin. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Johan Commelin, Scott Morrison, Adam Topaz
```
PAST COMMENT (from reviewer):
Can you make sure the year is correct?

--- candidate 12 (sim=0.635, past_pr=#35467, file=Mathlib/Combinatorics/Quiver/Schreier.lean) ---
PAST HUNK:
```
@@ -0,0 +1,771 @@
... [5 lines above hidden]
+-/
+module
+
+public import Mathlib.Combinatorics.Quiver.Basic
+public import Mathlib.Combinatorics.Quiver.SingleObj
+public import Mathlib.Combinatorics.Quiver.Covering
+public import Mathlib.Combinatorics.Quiver.Symmetric
+public import Mathlib.Combinatorics.Quiver.ConnectedComponent
+public import Mathlib.GroupTheory.GroupAction.Quotient
+public import Mathlib.GroupTheory.QuotientGroup.Basic
+public import Mathlib.Algebra.Group.Subgroup.Basic
+public import Mathlib.GroupTheory.FreeGroup.Basic
+public import Mathlib.Tactic.Group
```
PAST COMMENT (from reviewer):
Can you use `#min_imports` at the bottom of the file and replace these with what it suggests?
(these aren't minimized, e.g. `Quiver.SingleObj` imports `Quiver.Symmetric`)

--- candidate 13 (sim=0.630, past_pr=#6205, file=Mathlib/Algebra/Order/LatticeGroup.lean) ---
PAST HUNK:
```
@@ -59,12 +61,10 @@ lattices.
 lattice, ordered, group
 -/
 
-
--- Needed for squares
 -- Needed for squares
```
PAST COMMENT (from reviewer):
What does this comment mean?

--- candidate 14 (sim=0.629, past_pr=#7385, file=Mathlib/MeasureTheory/Measure/Trim.lean) ---
PAST HUNK:
```
@@ -0,0 +1,136 @@
+/-
+Copyright (c) 2023 Rémy Degenne. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Rémy Degenne
+-/
```
PAST COMMENT (from reviewer):
Is this correct? I thought we've had `trim` for much longer than 9 months

--- candidate 15 (sim=0.629, past_pr=#11667, file=Mathlib/Combinatorics/SimpleGraph/Matching.lean) ---
PAST HUNK:
```
@@ -36,45 +36,42 @@ one edge, and the edges of the subgraph represent the paired vertices.
 
 * Tutte's Theorem
 
-* Hall's Marriage Theorem (see combinatorics.hall)
+* Hall's Marriage Theorem (see `Combinatorics.Hall.Basic`)
```
PAST COMMENT (from reviewer):
```suggestion
* Hall's Marriage Theorem (see Combinatorics.Hall.Basic)
```
I *think* this is the correct syntax for the linkifier to work

--- candidate 16 (sim=0.627, past_pr=#9511, file=Mathlib/Algebra/Ring/Ext.lean) ---
PAST HUNK:
```
@@ -0,0 +1,528 @@
+/-
+Copyright (c) 2024 Raghuram Sundararajan. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Raghuram Sundararajan
+-/
+import Mathlib.Algebra.Ring.Defs
+import Mathlib.Algebra.Group.Ext
+-- import Mathlib
```
PAST COMMENT (from reviewer):
A commented-out line that is no longer needed can be safely deleted (we can always check the commits to get it back).
```suggestion
```

--- candidate 17 (sim=0.627, past_pr=#13401, file=Mathlib/GroupTheory/Congruence/BigOperators.lean) ---
PAST HUNK:
```
@@ -6,24 +6,42 @@ Authors: Amelia Livingston
 
 import Mathlib.GroupTheory.Congruence.Basic
 import Mathlib.Algebra.BigOperators.Group.Finset
+import Mathlib.Algebra.BigOperators.Group.Multiset
+import Mathlib.Algebra.BigOperators.Group.List
```
PAST COMMENT (from reviewer):
The first imports the other two
```suggestion
import Mathlib.Algebra.BigOperators.Group.Finset
```

--- candidate 18 (sim=0.627, past_pr=#14623, file=Mathlib/Combinatorics/SimpleGraph/Connectivity.lean) ---
PAST HUNK:
```
@@ -3,7 +3,10 @@ Copyright (c) 2021 Kyle Miller. All rights reserved.
 Released under Apache 2.0 license as described in the file LICENSE.
 Authors: Kyle Miller
 -/
+import Mathlib.Algebra.Order.Ring.Nat
 import Mathlib.Combinatorics.SimpleGraph.Subgraph
+import Mathlib.Data.Fintype.Card
+import Mathlib.Order.ConditionallyCompleteLattice.Basic
```
PAST COMMENT (from reviewer):
That is quite some new imports in an already long file. Maybe put the new lemmas (and any already existing related lemmas) in a new file?

I also don't see how the new imports are actually used in the new lemmas?

--- candidate 19 (sim=0.626, past_pr=#30047, file=Mathlib/Combinatorics/SimpleGraph/EdgeLabelling.lean) ---
PAST HUNK:
```
@@ -0,0 +1,227 @@
+/-
+Copyright (c) 2023 Bhavik Mehta. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Bhavik Mehta, Olivia Röhrig
+-/
+import Mathlib.Combinatorics.SimpleGraph.Maps
+import Mathlib.Combinatorics.SimpleGraph.Finite
+import Mathlib.Data.Fintype.BigOperators
+import Mathlib.Data.ZMod.Defs
```
PAST COMMENT (from reviewer):
I think we shouldn't need this import

--- candidate 20 (sim=0.626, past_pr=#30047, file=Mathlib/Combinatorics/SimpleGraph/EdgeLabelling.lean) ---
PAST HUNK:
```
@@ -0,0 +1,227 @@
+/-
+Copyright (c) 2023 Bhavik Mehta. All rights reserved.
+Released under Apache 2.0 license as described in the file LICENSE.
+Authors: Bhavik Mehta, Olivia Röhrig
+-/
+import Mathlib.Combinatorics.SimpleGraph.Maps
+import Mathlib.Combinatorics.SimpleGraph.Finite
+import Mathlib.Data.Fintype.BigOperators
+import Mathlib.Data.ZMod.Defs
```
PAST COMMENT (from reviewer):
(to be clear, I mean just the very last line - github doesn't let me select just one line to comment on!)


Decide which candidates' comments genuinely apply to the NEW hunk. If none, say so. Output JSON only.

[ASSISTANT]
----------------------------------------------------------------------------------------------------
{
  "new_hunk_plausible_concerns": [
    "refactor-simplify",
    "proof-golf",
    "docstring",
    "naming",
    "style-syntax",
    "correctness-bug"
  ],
  "summary": "None of the retrieved past review comments (mostly about imports, naming with Prod/Times, headers) clearly apply to this new definition/proof snippet.",
  "confidence": "none",
  "strong_matches": [],
  "weak_observations": []
}