Pkg Paper Rewriter Claw
Academic writing style toolkit, bilingual CN/EN: paper rewriting with AI-flavor self-check and style naturalization (scan reports are detection only), deterministic cleanup (model artifacts, punctuation, filler phrases), integrity guardrails (numbers, DOIs, PMIDs, terminology must survive untouched)
as observed 2026-11-19T03:34:19.174Z- Identifier
paper-rewriter- Source
- ClawHub
- Version observed
- 5.15.1
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-24T00:36:14.127Z
- Observations recorded
- 36
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 2,268
- Declared license
- MIT-0
Observation history
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.14.0: CN newsy-register word family + EN sweep symmetry. The CN library gains 6 newsy/summary phrases and one 「提供了有力的支撑」 regex with per-rule rationale; legitimate academic CN w | "v5.15.1: mirror brand-residue closure. The mirror-slug copy of the in-package selfcheck and the customization doc are now brand-consistent (two residual sibling-tool names were us |
latestVersion |
"5.14.0" | "5.15.1" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.12.0: verifiable claims + EN signal library v3. Capability claims in the main docs are now mechanically verifiable locally (zero-edit behavior of the cleanup re-runnable via -- | "v5.14.0: CN newsy-register word family + EN sweep symmetry. The CN library gains 6 newsy/summary phrases and one 「提供了有力的支撑」 regex with per-rule rationale; legitimate academic CN w |
latestVersion |
"5.12.0" | "5.14.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.11.0: reading-map as grouped lists + external lexicon. The main-doc 30-second routing is now four grouped lists (start/troubleshoot - flow/scenarios - limits/compliance - refer | "v5.12.0: verifiable claims + EN signal library v3. Capability claims in the main docs are now mechanically verifiable locally (zero-edit behavior of the cleanup re-runnable via -- |
latestVersion |
"5.11.0" | "5.12.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.10.0: CN scan sensitivity + verify output grading. Per real-usage feedback on thin CN weak-signal coverage, patterns_zh gains an 8-word AI-frequency family (plus a fifth densit | "v5.11.0: reading-map as grouped lists + external lexicon. The main-doc 30-second routing is now four grouped lists (start/troubleshoot - flow/scenarios - limits/compliance - refer |
latestVersion |
"5.10.0" | "5.11.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.8.0: in-package selfcheck + guard prescription in the bundle. New scripts/selfcheck.py runs four checks (environment / structure / core-feature smoke / doc reconciliation) in o | "v5.10.0: CN scan sensitivity + verify output grading. Per real-usage feedback on thin CN weak-signal coverage, patterns_zh gains an 8-word AI-frequency family (plus a fifth densit |
latestVersion |
"5.8.0" | "5.10.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.7.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.8.0: in-package selfcheck + guard prescription in the bundle. New scripts/selfcheck.py runs four checks (environment / structure / core-feature smoke / doc reconciliation) in o |
latestVersion |
"5.7.0" | "5.8.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.6.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.7.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"5.6.0" | "5.7.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.5.1: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.6.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"5.5.1" | "5.6.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.4.1: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.5.1: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"5.4.1" | "5.5.1" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v5.2.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.4.1: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"5.2.0" | "5.4.1" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v4.4.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi | "v5.2.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"4.4.0" | "5.2.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v4.2.0: batch degradation completion + language-aware handoff. pipeline --batch now wires in chunk degradation - oversized files inside a batch no longer fail whole; degraded chun | "v4.4.0: docx write-back + term unification. -o on pipeline/transform/compare now writes Word files when the path ends in .docx (minimal OOXML plain paragraphs, closing the loop wi |
latestVersion |
"4.2.0" | "4.4.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v4.1.0: displayName updated to 论文降AI率·去AI味改写 (paper AI-detection-rate reduction & de-AI-flavor rewriting) - the five-character phrase 论文降AI率 now covers four search phrasings (论文降A | "v4.2.0: batch degradation completion + language-aware handoff. pipeline --batch now wires in chunk degradation - oversized files inside a batch no longer fail whole; degraded chun |
latestVersion |
"4.1.0" | "4.2.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v4.0.0: encoding auto-detection. Text inputs no longer need to be pre-converted to UTF-8 - UTF-16 (with BOM) and GBK/GB2312/GB18030 encodings are recognized and transparently tran | "v4.1.0: displayName updated to 论文降AI率·去AI味改写 (paper AI-detection-rate reduction & de-AI-flavor rewriting) - the five-character phrase 论文降AI率 now covers four search phrasings (论文降A |
latestVersion |
"4.0.0" | "4.1.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.8.0: PDF safe gate + deep-rewrite handoff sheet. The PDF extraction-confidence gate now defaults to medium - garbled-typical extractions are rejected by default with actionable | "v4.0.0: encoding auto-detection. Text inputs no longer need to be pre-converted to UTF-8 - UTF-16 (with BOM) and GBK/GB2312/GB18030 encodings are recognized and transparently tran |
latestVersion |
"3.8.0" | "4.0.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.5.0: checklist and doc-architecture edition. A merged capability-x-boundary table puts what each capability does, what it does NOT do, and where to run it on one row. Every ref | "v3.8.0: PDF safe gate + deep-rewrite handoff sheet. The PDF extraction-confidence gate now defaults to medium - garbled-typical extractions are rejected by default with actionable |
latestVersion |
"3.5.0" | "3.8.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v3.4.0: submission self-check bundle edition. New pipeline --bundle DIR generates a dated self-check package in one command - six files: style self-check report, revision audit lo | "v3.5.0: checklist and doc-architecture edition. A merged capability-x-boundary table puts what each capability does, what it does NOT do, and where to run it on one row. Every ref |
latestVersion |
"3.4.0" | "3.5.0" |
summary |
"Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts | "Academic writing style toolkit, bilingual CN/EN: paper rewriting with AI-flavor self-check and style naturalization (scan reports are detection only), deterministic cleanup (model |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.2.0: statistical consistency guard. New check_stats.py catches three classes of numbers that fight each other: percent lists not summing to 100 (only sentences with partition c | "v3.4.0: submission self-check bundle edition. New pipeline --bundle DIR generates a dated self-check package in one command - six files: style self-check report, revision audit lo |
latestVersion |
"3.2.0" | "3.4.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.1.0: say-it-right release. Term guards upgrade to variant groups - one group can hold more than two forms (HF / 心力衰竭 / 心衰 reported as a single row), 8 domains / 27 groups / 55 | "v3.2.0: statistical consistency guard. New check_stats.py catches three classes of numbers that fight each other: percent lists not summing to 100 (only sentences with partition c |
latestVersion |
"3.1.0" | "3.2.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.0.0: demand-word repositioning + operational deep-rewrite. displayName updated to match what you actually search for. PDF direct-read recalibrated: embedded-font (ToUnicode) PD | "v3.1.0: say-it-right release. Term guards upgrade to variant groups - one group can hold more than two forms (HF / 心力衰竭 / 心衰 reported as a single row), 8 domains / 27 groups / 55 |
latestVersion |
"3.0.0" | "3.1.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.9.0: substantive release. NEW fullwidth alnum normalization (transform/pipeline automatic): Chinese input methods silently turn 2025 into fullwidth 2025 - the v2.8.0 E_NUM_WIDT | "v3.0.0: demand-word repositioning + operational deep-rewrite. displayName updated to match what you actually search for. PDF direct-read recalibrated: embedded-font (ToUnicode) PD |
latestVersion |
"2.9.0" | "3.0.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.8.0: substantive release, targeting the official evaluation's accuracy note head-on. NEW PDF extraction confidence self-report (read_text_ex): four heuristics - common-word hit | "v2.9.0: substantive release. NEW fullwidth alnum normalization (transform/pipeline automatic): Chinese input methods silently turn 2025 into fullwidth 2025 - the v2.8.0 E_NUM_WIDT |
latestVersion |
"2.8.0" | "2.9.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.7.0: substantive release. NEW best-practices handbook (references/best_practices.md): seven real scenarios - journal submission, thesis chapters, reviewer responses, batch tria | "v2.8.0: substantive release, targeting the official evaluation's accuracy note head-on. NEW PDF extraction confidence self-report (read_text_ex): four heuristics - common-word hit |
latestVersion |
"2.7.0" | "2.8.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.6.0: substantive release. NEW style profile (stylecheck.py): the quantified acceptance lens for the style guide - per-paragraph jargon hits located with samples, sentence-rhyth | "v2.7.0: substantive release. NEW best-practices handbook (references/best_practices.md): seven real scenarios - journal submission, thesis chapters, reviewer responses, batch tria |
latestVersion |
"2.6.0" | "2.7.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.5.0: substantive release. NEW centralized error layer: all nine CLIs enter through one handler - user-facing failures print two Chinese lines (what went wrong + what to do) and | "v2.6.0: substantive release. NEW style profile (stylecheck.py): the quantified acceptance lens for the style guide - per-paragraph jargon hits located with samples, sentence-rhyth |
latestVersion |
"2.5.0" | "2.6.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.4.0: substantive release. NEW deterministic deep polish (--deep on transform/pipeline): sentence-level automatic transforms - canned opener deletion at sentence starts only, ex | "v2.5.0: substantive release. NEW centralized error layer: all nine CLIs enter through one handler - user-facing failures print two Chinese lines (what went wrong + what to do) and |
latestVersion |
"2.4.0" | "2.5.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.3.0: substantive release. NEW plan.py - sentence-level rewrite priority queue: ranks sentences by weighted pattern contribution, with section attribution, handling advice and a | "v2.4.0: substantive release. NEW deterministic deep polish (--deep on transform/pipeline): sentence-level automatic transforms - canned opener deletion at sentence starts only, ex |
latestVersion |
"2.3.0" | "2.4.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.1.0: fixes from real-document testing - word boundary correction so abbreviations adjacent to CJK characters are correctly recognized by the integrity guard (TNF after fullwidt | "v2.3.0: substantive release. NEW plan.py - sentence-level rewrite priority queue: ranks sentences by weighted pattern contribution, with section attribution, handling advice and a |
latestVersion |
"2.1.1" | "2.3.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.9.0: terminology consistency checker (scripts/check_terms.py) - detects the same concept referred to by different terms within a document; built-in CN/EN pairs + user-defined p | "v2.1.0: fixes from real-document testing - word boundary correction so abbreviations adjacent to CJK characters are correctly recognized by the integrity guard (TNF after fullwidt |
latestVersion |
"1.9.0" | "2.1.1" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v1.7.0: structure-aware scanning via --structure (detects IMRaD sections - abstract/introduction/methods/results/discussion/conclusion/references, bilingual; per-section scoring w | "v1.9.0: terminology consistency checker (scripts/check_terms.py) - detects the same concept referred to by different terms within a document; built-in CN/EN pairs + user-defined p |
latestVersion |
"1.7.0" | "1.9.0" |
summary |
"Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts | "Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.6.0: revision tracking via --track (every mechanical-layer change recorded to base.md+base.json: rules, counts, deleted sentences, flagged-for-review); experimental PDF text in | "v1.7.0: structure-aware scanning via --structure (detects IMRaD sections - abstract/introduction/methods/results/discussion/conclusion/references, bilingual; per-section scoring w |
latestVersion |
"1.6.0" | "1.7.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v1.5.0: self-contained HTML reports via --html in detect/pipeline/compare (score cards, category tables, revision worksheet, integrity verdict); sentence-level add/delete diff vie | "v1.6.0: revision tracking via --track (every mechanical-layer change recorded to base.md+base.json: rules, counts, deleted sentences, flagged-for-review); experimental PDF text in |
latestVersion |
"1.5.0" | "1.6.0" |
summary |
"Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts | "Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.4.0: added Permissions & environment statement section (reads only user-specified input files, writes only -o output paths, zero network, zero third-party dependencies, no env | "v1.5.0: self-contained HTML reports via --html in detect/pipeline/compare (score cards, category tables, revision worksheet, integrity verdict); sentence-level add/delete diff vie |
latestVersion |
"1.4.0" | "1.5.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.3.0: added Permissions & environment statement section (reads only user-specified input files, writes only -o output paths, zero network, zero third-party dependencies, no env | "v1.4.0: added Permissions & environment statement section (reads only user-specified input files, writes only -o output paths, zero network, zero third-party dependencies, no env |
latestVersion |
"1.3.0" | "1.4.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v1.2.0: added Permissions & environment statement section (reads only user-specified input files, writes only -o output paths, zero network, zero third-party dependencies, no env | "v1.3.0: added Permissions & environment statement section (reads only user-specified input files, writes only -o output paths, zero network, zero third-party dependencies, no env |
latestVersion |
"1.2.0" | "1.3.0" |
summary |
"Academic writing style toolkit, bilingual CN/EN: style-pattern self-check report, deterministic text cleanup (model artifacts, punctuation, filler phrases), integrity guardrails ( | "Academic writing style toolkit, bilingual CN/EN: AI flavor scan and style-pattern self-check reports (scan reports are detection only), deterministic text cleanup (model artifacts |
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.