paperlint 2.0.0

package/skills/paper-pipeline/repro/2026-08-08-grade-paper-writing-ablation-A6-oracle.log

@@ -0,0 +1,53 @@
+
+37 skills installed → 36 competitors per run
+
+ARMS — description length, word-set delta vs A0, mean prompt overlap
+arm label                               chars  words     −   +   ovAH   ovSH
+A0  baseline (verbatim)                  1174     94     0   0   0.85   0.78
+A1  short (sentences 1-2 only)            528     46    48   0   0.71   0.78
+A2  no-subordination                      992     85     9   0   0.85   0.78
+A3  no-negation                           965     81    13   0   0.85   0.78
+A4  no-machinery                          598     44    50   0   0.44   0.35
+A5  renamed (description identical)      1174     94     0   0   0.85   0.78
+A6  persona-only (A1's mirror)            225     22    72   0   0.19   0.35
+
+⚠ ovAH/ovSH FALL AS TEXT IS DELETED — caveat 2 in the header, quantified. The deletion arms carry
+  a vocabulary handicap against the parent's dominant factor. A rising deletion arm rose DESPITE it;
+  a flat one may be a real gain cancelled by it, and this design cannot tell. A5 is the only arm
+  with zero handicap (identical word set).
+
+oracle: 1 arm(s) x 8 closed-book picks over 37 descriptions
+
+=== A6 persona-only (A1's mirror)
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  AH  HIT   grade-paper-writing         grade the writing craft in this draft and name the offendi
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  AH  HIT   grade-paper-writing         run the blind multi-grader panel over the prose clarity an
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  AH  HIT   grade-paper-writing         score the title, the abstract and the intro architecture o
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  AH  HIT   grade-paper-writing         grade how well this reads, hedge stacking included, and gi
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  SH  HIT   grade-paper-writing         the abstract reads like a wall of jargon
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  SH  HIT   grade-paper-writing         the intro architecture is fine but the prose clarity is no
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  SH  HIT   grade-paper-writing         there is hedge stacking everywhere and the point never lan
+Ignoring 24 permissions.allow entries from .claude/settings.json and .claude/settings.local.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects["/home/user/mine"].hasTrustDialogAccepted: true in /root/.claude.json.
+  SH  HIT   grade-paper-writing         the writing does not read well even though the draft is fi
+
+ORACLE ACCURACY BY ARM (closed book, 37 descriptions in context, 1 pick each)
+arm label                               hit    AH    SH   none  wrong
+A0  baseline (verbatim)                  7/8   4/4   3/4     0      1
+A1  short (sentences 1-2 only)           7/8   4/4   3/4     0      1
+A2  no-subordination                     8/8   4/4   4/4     0      0
+A3  no-negation                          7/8   4/4   3/4     0      1
+A4  no-machinery                         8/8   4/4   4/4     0      0
+A5  renamed (description identical)      0/8   0/4   0/4     0      8
+A6  persona-only (A1's mirror)           8/8   4/4   4/4     0      0
+
+rows → repro/2026-08-08-grade-paper-writing-ablation-oracle.json
+
+READ AS AN UPPER BOUND, NOT A HUMAN, and read it AGAINST the harness arms: an arm where the
+oracle moves WITH the harness changed what is recoverable from the text; an arm where the oracle
+is flat and the harness moves changed what the harness DOES with the same recoverable text.

package/skills/paper-pipeline/repro/2026-08-08-grade-paper-writing-ablation-A6-raw.log

@@ -0,0 +1,89 @@
+
+37 skills installed → 36 competitors per run
+
+ARMS — description length, word-set delta vs A0, mean prompt overlap
+arm label                               chars  words     −   +   ovAH   ovSH
+A0  baseline (verbatim)                  1174     94     0   0   0.85   0.78
+A1  short (sentences 1-2 only)            528     46    48   0   0.71   0.78
+A2  no-subordination                      992     85     9   0   0.85   0.78
+A3  no-negation                           965     81    13   0   0.85   0.78
+A4  no-machinery                          598     44    50   0   0.44   0.35
+A5  renamed (description identical)      1174     94     0   0   0.85   0.78
+A6  persona-only (A1's mirror)            225     22    72   0   0.19   0.35
+
+⚠ ovAH/ovSH FALL AS TEXT IS DELETED — caveat 2 in the header, quantified. The deletion arms carry
+  a vocabulary handicap against the parent's dominant factor. A rising deletion arm rose DESPITE it;
+  a flat one may be a real gain cancelled by it, and this design cannot tell. A5 is the only arm
+  with zero handicap (identical word set).
+
+mode=main  1 arm(s) x 8 prompts x 3 trials = 24 runs
+
+==============================================================================
+=== A6 persona-only (A1's mirror)  (225 chars, id vigiles-loose-skills:grade-paper-writing)
+  Spent: 224,224 tokens (10 in · 891 out · 179.4k cache) · ~$0.33 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  AH  0.33  T1 O0 S2  ov=0.25  grade the writing craft in this draft and name the offen
+  Spent: 314,086 tokens (12 in · 1.2k out · 268.1k cache) · ~$0.37 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  Session so far: 538,310 tokens · ~$0.70 API-equivalent
+  AH  1.00  T3 O0 S0  ov=0.22  run the blind multi-grader panel over the prose clarity 
+  AH  0.00  T0 O0 S3  ov=0.00  score the title, the abstract and the intro architecture
+  AH  0.00  T0 O0 S3  ov=0.29  grade how well this reads, hedge stacking included, and 
+  Spent: 406,626 tokens (18 in · 1.8k out · 359.0k cache) · ~$0.41 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  Session so far: 944,936 tokens · ~$1.11 API-equivalent
+  SH  1.00  T3 O0 S0  ov=0.75  the abstract reads like a wall of jargon
+  Spent: 275,164 tokens (12 in · 3.5k out · 225.3k cache) · ~$0.40 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  Session so far: 1,220,100 tokens · ~$1.51 API-equivalent
+  SH  0.00  T0 O0 S3  ov=0.00  the intro architecture is fine but the prose clarity is 
+  Spent: 269,497 tokens (9 in · 1.6k out · 223.1k cache) · ~$0.36 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  Session so far: 1,489,597 tokens · ~$1.87 API-equivalent
+  SH  0.00  T0 O3 S0  ov=0.00  there is hedge stacking everywhere and the point never l
+         instead: tighten-paper
+  Spent: 450,483 tokens (19 in · 1.9k out · 403.3k cache) · ~$0.42 API-equivalent
+  Billed to: your Claude subscription — $0 metered ✅
+  Session so far: 1,940,080 tokens · ~$2.29 API-equivalent
+  SH  1.00  T3 O0 S0  ov=0.67  the writing does not read well even though the draft is 
+
+==============================================================================
+THE ABLATION — target trigger rate by arm
+
+arm label                               chars       fired      AH      SH   Δ vs A0
+A0  baseline (verbatim)                  1174 54% (13/24)     58%     50%         —
+A1  short (sentences 1-2 only)            528 50% (12/24)     50%     50%      -4pp
+A2  no-subordination                      992 50% (12/24)     58%     42%      -4pp
+A3  no-negation                           965 54% (13/24)     58%     50%       0pp
+A4  no-machinery                          598 46% (11/24)     50%     42%      -8pp
+A5  renamed (description identical)      1174  25% (6/24)     33%     17%     -29pp
+A6  persona-only (A1's mirror)            225 42% (10/24)     33%     50%     -12pp
+
+==============================================================================
+TARGET / OTHER / SILENT — the parent's discriminator
+
+arm label                               target   other  silent
+A0  baseline (verbatim)                     54%      0%     46%
+A1  short (sentences 1-2 only)              50%      4%     46%
+A2  no-subordination                        50%      8%     42%
+A3  no-negation                             54%      0%     46%
+A4  no-machinery                            46%     13%     42%
+A5  renamed (description identical)         25%      4%     71%
+A6  persona-only (A1's mirror)              42%     13%     46%
+
+  OTHER  = a competitor was selected and the target was not. The parent saw ONE in 144 runs.
+  SILENT = nothing resolved. 42 of this skill's 48 parent runs were SILENT; that is the number
+           an arm has to move. See caveat 4: a run that simply answered is also SILENT.
+
+WHICH competitors took the runs (all arms):
+    7  tighten-paper
+    3  cold-read-diff
+
+🔴 n = 24 PER ARM. At ~20% baseline the 95% interval is roughly ±16pp. A factor of two is
+   readable; fifteen points is not. If every arm lands within noise of A0, the finding is that the
+   cause is NOT IN THE DESCRIPTION TEXT — report that, do not pick the largest number.
+
+per-run rows → repro/2026-08-08-grade-paper-writing-ablation.json
+
+Run --mode oracle before reading any arm as a mechanism: a harness move with a matching oracle
+move is a change in what the TEXT supports, not in what the harness does with it.

package/skills/paper-pipeline/repro/2026-08-08-grade-paper-writing-ablation-oracle.json

@@ -0,0 +1,450 @@
+[
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "tighten-paper",
+    "ok": false
+  },
+  {
+    "arm": "A0",
+    "label": "baseline (verbatim)",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "tighten-paper",
+    "ok": false
+  },
+  {
+    "arm": "A1",
+    "label": "short (sentences 1-2 only)",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A2",
+    "label": "no-subordination",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "cold-read-diff",
+    "ok": false
+  },
+  {
+    "arm": "A3",
+    "label": "no-negation",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A4",
+    "label": "no-machinery",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "tighten-paper",
+    "ok": false
+  },
+  {
+    "arm": "A5",
+    "label": "renamed (description identical)",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "?grade-paper-writing",
+    "ok": false
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "AH",
+    "prompt": "grade the writing craft in this draft and name the offending sentence in each dimension",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "AH",
+    "prompt": "run the blind multi-grader panel over the prose clarity and jargon discipline",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "AH",
+    "prompt": "score the title, the abstract and the intro architecture one to five",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "AH",
+    "prompt": "grade how well this reads, hedge stacking included, and give me the fix for each",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "SH",
+    "prompt": "the abstract reads like a wall of jargon",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "SH",
+    "prompt": "the intro architecture is fine but the prose clarity is not",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "SH",
+    "prompt": "there is hedge stacking everywhere and the point never lands",
+    "pick": "grade-paper-writing",
+    "ok": true
+  },
+  {
+    "arm": "A6",
+    "label": "persona-only (A1's mirror)",
+    "cell": "SH",
+    "prompt": "the writing does not read well even though the draft is finished",
+    "pick": "grade-paper-writing",
+    "ok": true
+  }
+]