TheBotique

Paper Polisher Pro — AI Detector & Academic Polishing

AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, translation-smell, paragraph attribution, journal precheck with discipline context, style-norm conventions check, quality re

as observed 2026-11-19T03:34:19.174Z
Identifier
paper-polisher-pro
Source
ClawHub
Version observed
7.9.0
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-09-16T18:18:14.270Z
Observations recorded
33
Installs (reported upstream)
19
Weekly downloads (upstream)
3,028
Declared license
MIT-0

Observation history

2026-11-19T03:34:19.174Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "output contract schemas (4 core outputs + zero-dep validator + selfcheck); manifest generator single-sourced (--check byte-compare, gated); pp_api parity completed (trend_data/sch "manifest single-sourcing: packaging writes data/PACKAGE_MANIFEST.json (all shipped files outside data/, sha256+bytes) instead of overwriting the data-file INTEGRITY_MANIFEST.json
latestVersion "7.7.0" "7.9.0"
summary "AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, tra "AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, tra
2026-11-12T21:45:54.906Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "install integrity self-check (INTEGRITY_MANIFEST.json sha256 manifest + pp_doctor --deep hash/parse verification + trunk/package manifest gates + gen tool)" "output contract schemas (4 core outputs + zero-dep validator + selfcheck); manifest generator single-sourced (--check byte-compare, gated); pp_api parity completed (trend_data/sch
latestVersion "7.6.0" "7.7.0"
2026-11-07T16:42:40.757Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "dual-form acceptance parity (verify_forms.py --form sh|ch|both, FORM-aware smoke); archive/README caliber discipline gated; skill.json 12-layer aligned; SKILL_ZH caliber pointer" "install integrity self-check (INTEGRITY_MANIFEST.json sha256 manifest + pp_doctor --deep hash/parse verification + trunk/package manifest gates + gen tool)"
latestVersion "7.5.0" "7.6.0"
2026-11-06T15:44:01.875Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "physical caliber separation (29 historical result files archived, top level gated to CURRENT.md table); version-era pointer; pp_api SDK gains fix_suggest/evidence_sections/term_pr "dual-form acceptance parity (verify_forms.py --form sh|ch|both, FORM-aware smoke); archive/README caliber discipline gated; skill.json 12-layer aligned; SKILL_ZH caliber pointer"
latestVersion "7.4.0" "7.5.0"
2026-11-05T14:44:09.628Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "batch auto-retry (--retries) with failed_files diagnostic list; guided tour (pp.py tour, five live stations); quick start references bundled real outputs; sample outputs regenerat "physical caliber separation (29 historical result files archived, top level gated to CURRENT.md table); version-era pointer; pp_api SDK gains fix_suggest/evidence_sections/term_pr
latestVersion "6.4.0" "7.4.0"
2026-10-23T01:44:40.541Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v6.1.0: report explainer & hardened feedback — new pp_explain.py (pp.py explain) turns any workflow/detect JSON into a plain-language three-part reading (verdict / evidence / acti "batch auto-retry (--retries) with failed_files diagnostic list; guided tour (pp.py tour, five live stations); quick start references bundled real outputs; sample outputs regenerat
latestVersion "6.1.0" "6.4.0"
2026-10-19T22:50:38.661Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v6.0.0: reporting & experience major — new pp_trend.py (pp.py trend) renders multi-round rewrite trajectories from workflow JSONs into one self-contained HTML (inline-SVG score li "v6.1.0: report explainer & hardened feedback — new pp_explain.py (pp.py explain) turns any workflow/detect JSON into a plain-language three-part reading (verdict / evidence / acti
latestVersion "6.0.0" "6.1.0"
2026-10-18T21:45:32.509Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.8.1: terminology bank extended with practice-derived standardization mappings (self-coined abbreviations and colloquial metaphors registered as aliases of standard names, so te "v6.0.0: reporting & experience major — new pp_trend.py (pp.py trend) renders multi-round rewrite trajectories from workflow JSONs into one self-contained HTML (inline-SVG score li
latestVersion "5.8.1" "6.0.0"
2026-10-16T19:37:29.109Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.6.0: llm-jargon release — three-tier AI-flavor self-check (L1 metaphor-abuse blacklist / L2 tone words / L3 sentence patterns) with case-library contrasts and whitelist phrasin "v5.8.1: terminology bank extended with practice-derived standardization mappings (self-coined abbreviations and colloquial metaphors registered as aliases of standard names, so te
latestVersion "5.6.0" "5.8.1"
2026-10-15T18:48:12.129Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.5.0: style-norm & ledger release — term-consistency check (23-group variant bank, mixing-not-correctness); findings ledger in workflow reports; sub-tool matrix completed; super "v5.6.0: llm-jargon release — three-tier AI-flavor self-check (L1 metaphor-abuse blacklist / L2 tone words / L3 sentence patterns) with case-library contrasts and whitelist phrasin
latestVersion "5.5.0" "5.6.0"
2026-10-14T17:39:07.962Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "v5.4.0: journal-context release — journal precheck 2.0 (discipline detection with --discipline override plus per-discipline reading guide; the 20-25% reference line stays the cros "v5.5.0: style-norm & ledger release — term-consistency check (23-group variant bank, mixing-not-correctness); findings ledger in workflow reports; sub-tool matrix completed; super
latestVersion "5.4.0" "5.5.0"
summary "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli "AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, tra
2026-10-13T16:37:28.889Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.2.0: style-norm release — academic writing convention self-check (pp_style_norm.py: full/half-width mixing, number-usage consistency, abbreviation first-use definitions, unit f "v5.4.0: journal-context release — journal precheck 2.0 (discipline detection with --discipline override plus per-discipline reading guide; the 20-25% reference line stays the cros
latestVersion "5.2.0" "5.4.0"
2026-10-11T14:42:02.570Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.1.0: rewrite-closure & batch-report release — rewrite-effect regression check (pp_rewrite_check.py: original vs revised engine-source comparison — document score/risk-band migr "v5.2.0: style-norm release — academic writing convention self-check (pp_style_norm.py: full/half-width mixing, number-usage consistency, abbreviation first-use definitions, unit f
latestVersion "5.1.0" "5.2.0"
2026-10-10T14:15:52.413Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v5.0.0: verification & rewrite-suggestions release — sentence-level rewrite suggestions (pp_fix_suggest.py: which sentences, why, how to improve — locate & strategy, never auto-re "v5.1.0: rewrite-closure & batch-report release — rewrite-effect regression check (pp_rewrite_check.py: original vs revised engine-source comparison — document score/risk-band migr
latestVersion "5.0.0" "5.1.0"
2026-10-09T13:20:37.333Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "v4.9.0: mixed-document calibration release — paragraph-level hi/med/lo thresholds calibrated on the controlled mixed benchmark (333 paragraphs with ground truth; best operating po "v5.0.0: verification & rewrite-suggestions release — sentence-level rewrite suggestions (pp_fix_suggest.py: which sentences, why, how to improve — locate & strategy, never auto-re
latestVersion "4.9.0" "5.0.0"
summary "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli
2026-10-08T12:19:32.804Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.8.0: measurement & output-contract integrity (independent third-party test round, 13 findings verified and addressed) — run_eval cache keys now bind engine mode (rules-only eva "v4.9.0: mixed-document calibration release — paragraph-level hi/med/lo thresholds calibrated on the controlled mixed benchmark (333 paragraphs with ground truth; best operating po
latestVersion "4.8.0" "4.9.0"
2026-10-07T11:52:53.866Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.6.0: onboarding release — new scripts/pp_workflow.py end-to-end self-check command (AI-rate detection + paragraph attribution + 4-layer gate + terminology + translation-smell + "v4.8.0: measurement & output-contract integrity (independent third-party test round, 13 findings verified and addressed) — run_eval cache keys now bind engine mode (rules-only eva
latestVersion "4.7.0" "4.8.0"
2026-10-06T10:50:34.888Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.6.0: onboarding release — new scripts/pp_workflow.py end-to-end self-check command (AI-rate detection + paragraph attribution + 4-layer gate + terminology + translation-smell + "v4.6.0: onboarding release — new scripts/pp_workflow.py end-to-end self-check command (AI-rate detection + paragraph attribution + 4-layer gate + terminology + translation-smell +
latestVersion "4.6.0" "4.7.0"
2026-10-05T10:33:23.015Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.5.0: programmable-interface release — new scripts/pp_api.py Python SDK (in-process detect_text with CLI parity; gate_text/term_report/smell_report/style_report/quality_report_f "v4.6.0: onboarding release — new scripts/pp_workflow.py end-to-end self-check command (AI-rate detection + paragraph attribution + 4-layer gate + terminology + translation-smell +
latestVersion "4.5.0" "4.6.0"
2026-10-04T09:46:17.065Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.4.0: measurement-integrity release — headline numbers re-measured fingerprint-bound: pre-2026 held-out AUROC 0.9998, current-gen 0.9400, human FPR@med 2.3% (supersedes the 0.90 "v4.5.0: programmable-interface release — new scripts/pp_api.py Python SDK (in-process detect_text with CLI parity; gate_text/term_report/smell_report/style_report/quality_report_f
latestVersion "4.4.0" "4.5.0"
2026-10-03T08:46:10.142Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.3.0: generation-split evaluation infrastructure — new 443-doc current-gen eval set (312 fresh AI from 9 families + 131 held-out humans); first quantified generation-gap numbers "v4.4.0: measurement-integrity release — headline numbers re-measured fingerprint-bound: pre-2026 held-out AUROC 0.9998, current-gen 0.9400, human FPR@med 2.3% (supersedes the 0.90
latestVersion "4.3.0" "4.4.0"
2026-10-01T06:47:50.210Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.2.0: batch recursion (--recursive walks subdirectories, relative paths); GitHub README landing page (description, quick start, family table, compliance statement); gate layer-3 "v4.3.0: generation-split evaluation infrastructure — new 443-doc current-gen eval set (312 fresh AI from 9 families + 131 held-out humans); first quantified generation-gap numbers
latestVersion "4.2.0" "4.3.0"
2026-09-30T05:46:36.081Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v4.1.0: smoothness layer (L13 surprisal-variation) fused into the score at 0.06 weight across all length bands — held-out A/B shows AUROC bit-identical to baseline (0.9022) and hu "v4.2.0: batch recursion (--recursive walks subdirectories, relative paths); GitHub README landing page (description, quick start, family table, compliance statement); gate layer-3
latestVersion "4.1.0" "4.2.0"
2026-09-29T04:47:03.526Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "v3.11.0: batch detection (--batch DIR — per-file scores + aggregate stats, deterministic, >5MB skipped) built for thesis-scale self-review; paragraph report now carries the academ "v4.1.0: smoothness layer (L13 surprisal-variation) fused into the score at 0.06 weight across all length bands — held-out A/B shows AUROC bit-identical to baseline (0.9022) and hu
latestVersion "3.11.0" "4.1.0"
summary "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli
2026-09-28T03:46:57.521Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "v3.9.0: honest-boundary guardrails — mixed-register signal (mixed_signal + per-paragraph guidance), register hint, encoding warning, gate layer-divergence disclosure. Includes v3. "v3.11.0: batch detection (--batch DIR — per-file scores + aggregate stats, deterministic, >5MB skipped) built for thesis-scale self-review; paragraph report now carries the academ
latestVersion "3.10.0" "3.11.0"
summary "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 metaph "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeli
2026-09-27T02:45:50.156Z

Fields that differed: latestVersion summary

FieldBeforeAfter
latestVersion "3.9.0" "3.10.0"
summary "AI-rate self-check for academic writing, polish guidance (style, terminology, guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance lab "AI-rate self-check for academic writing, polish guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 metaph
2026-09-26T01:46:07.395Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v3.8.0: honest-boundary guardrails — mixed-register signal (mixed_signal + per-paragraph guidance), register hint, encoding warning, gate layer-divergence disclosure. Includes v3. "v3.9.0: honest-boundary guardrails — mixed-register signal (mixed_signal + per-paragraph guidance), register hint, encoding warning, gate layer-divergence disclosure. Includes v3.
latestVersion "3.8.0" "3.9.0"
2026-09-25T00:46:42.104Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "v3.7.0: evaluation-driven docs upgrade — centralized FAQ section (9 answers), per-script cheat-sheet table, clearer style_distance edge-case errors. Targets TRACE C/R dimension fe "v3.8.0: honest-boundary guardrails — mixed-register signal (mixed_signal + per-paragraph guidance), register hint, encoding warning, gate layer-divergence disclosure. Includes v3.
latestVersion "3.7.0" "3.8.0"
summary "AI writing detection (AI-rate self-check for authors), academic polishing guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label c "AI-rate self-check for academic writing, polish guidance (style, terminology, guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance lab
2026-09-24T00:36:14.127Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v3.6.0: academic-integrity guardrails (explicit integrity_notice in every report, new Academic Integrity section; positioning = author self-review and disclosure compliance, not d "v3.7.0: evaluation-driven docs upgrade — centralized FAQ section (9 answers), per-script cheat-sheet table, clearer style_distance edge-case errors. Targets TRACE C/R dimension fe
latestVersion "3.6.0" "3.7.0"
2026-09-20T22:20:20.811Z

Fields that differed: changelog displayName latestVersion summary

FieldBeforeAfter
changelog "v3.5.0: supervised v3 line first public release (base engine AUROC 0.9187 held-out; optional supervised layer up to 1.0). New: degraded-mode disclosure, <100-char no-verdict iron "v3.6.0: academic-integrity guardrails (explicit integrity_notice in every report, new Academic Integrity section; positioning = author self-review and disclosure compliance, not d
displayName "Pkg Paper Polisher Pro Claw" "Paper Polisher Pro — AI Detector & Academic Polishing"
latestVersion "3.5.0" "3.6.0"
summary "AI-rate detection (AI writing detector), de-AI rewriting, terminology check, metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeling rules), paragraph- "AI writing detection (AI-rate self-check for authors), academic polishing guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label c
2026-09-19T21:21:32.220Z

Fields that differed: changelog displayName latestVersion summary

FieldBeforeAfter
changelog "English SKILL.md for ClawHub (was incorrectly in Chinese), streamlined descriptions, SEO keyword optimization, 3 Xiaohongshu promo posts" "v3.5.0: supervised v3 line first public release (base engine AUROC 0.9187 held-out; optional supervised layer up to 1.0). New: degraded-mode disclosure, <100-char no-verdict iron
displayName "paper-polisher-pro" "Pkg Paper Polisher Pro Claw"
latestVersion "1.0.1" "3.5.0"
summary null "AI-rate detection (AI writing detector), de-AI rewriting, terminology check, metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeling rules), paragraph-
2026-09-17T19:21:46.965Z

Fields that differed: license

FieldBeforeAfter
license null "MIT-0"

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.