Spaces:

Rasheed
/

Test_AI_writing

Running

140 kB

Ctrl+K

4 contributors

unknown

Claude Opus 5.5

Faster long documents: Smart Humanize uses the fast engine at any length (FAST_MAX_WORDS default 0; a 22,000-word part took 13 min on the sentence-by-sentence engine, the fast engine reached 0% in about 4); report-guided runs at 0% stop when a round rewords fewer than 3 (or 5%) of the highlighted sentences left (5 of 12 minutes went on taking 80 to 72); wallet usual cost of long fast runs from live measurements; pricing table rows all on the fast engine

d14dbe0 about 12 hours ago

conftest.py

470 Bytes
Accounts database kept off the storage mount and repaired at start; honest result when the AI score is not lowered 13 days ago
test_app_rephrase_anyway.py

9.64 kB
Faster and steadier: jobs survive silent connection drops, Journal Finder warm start, parallel lookups and caches, fast engine up to FAST_MAX_WORDS 6 days ago
test_around_fields.py

4.84 kB
Sentences with citation fields (Zotero / Mendeley / EndNote), links or superscript citations inside are now rewritten around them: the language model sees markers ([REF1] ...), a version is used only if it keeps every marker once and in order, and its words go into the plain text around the untouched fields (citations stay live); choosing, the faithfulness check and the report read the real text. In a thesis a third of the highlighted sentences were locked before (FAST_AROUND_FIELDS=0 = old behaviour) about 13 hours ago
test_auth_store.py

5.25 kB
Smart Humanize falls back to a full rewrite when stuck; log-in throttling; pay-per-use loophole closed 12 days ago
test_clarity.py

1.31 kB
Harden rewrite integrity, stop the final polish undoing humanization, add tests 13 days ago
test_cost.py

5.59 kB
Accounts database kept off the storage mount and repaired at start; honest result when the AI score is not lowered 13 days ago
test_dashboard.py

4.07 kB
Remove "Open in Overleaf"; dashboard covers every tool and pay per use 13 days ago
test_detector.py

2.68 kB
Add meaning check, Groq model fallback and subject test run; close guard gaps 13 days ago
test_docx_edit.py

3.46 kB
Harden rewrite integrity, stop the final polish undoing humanization, add tests 13 days ago
test_fast_engine.py

9.22 kB
Faster long documents: Smart Humanize uses the fast engine at any length (FAST_MAX_WORDS default 0; a 22,000-word part took 13 min on the sentence-by-sentence engine, the fast engine reached 0% in about 4); report-guided runs at 0% stop when a round rewords fewer than 3 (or 5%) of the highlighted sentences left (5 of 12 minutes went on taking 80 to 72); wallet usual cost of long fast runs from live measurements; pricing table rows all on the fast engine about 12 hours ago
test_finder_wos_conferences.py

4.29 kB
Journal Finder: conference search (Scopus proceedings, CORE rank, open calls) and Web of Science SCIE/SSCI/ESCI filters 6 days ago
test_finish_to_zero.py

6.11 kB
Report-guided runs: highlighted sentences reworded round by round (more new wording each round) until little original wording is left (AI report 35%, similarity 15%); AI-report estimate from how our detector reads those sentences in the finished document; report table records each rewrite; stop after one round without progress at 0% about 14 hours ago
test_formatter_quality.py

4.33 kB
Journal Formatter: footnotes, web references, books and reports, author marks, cleaner LaTeX 6 days ago
test_groqai.py

4.26 kB
Merge the Space's 8-9 October work (origin/main) into the local changes 13 days ago
test_mail_relay.py

3.97 kB
Email without a third-party service: own mail relay on your hosting 6 days ago
test_polish_guard.py

3.04 kB
Harden rewrite integrity, stop the final polish undoing humanization, add tests 13 days ago
test_pricing.py

12.1 kB
Pay as you go only: prepaid wallet with PhonePe top-ups; every run reserved before it starts, capped (Groq + deadline) and charged its actual price with a 300% margin after GST and fees; admin profit report 6 days ago
test_proofread_fallback.py

2.31 kB
Proofread: basic check instead of an error when no language model is reachable 13 days ago
test_pubrules.py

2.58 kB
Harden rewrite integrity, stop the final polish undoing humanization, add tests 13 days ago
test_reilaa.py

13.1 kB
Turnitin report parts follow Turnitin's 40,000-word limit (balanced parts; size alone never adds a paid part, pictures only shrunk in the copy sent); split works with tables of contents (namespace error live); a file that cannot be split is not sent about 17 hours ago
test_signup_verify.py

2.74 kB
Sign-up confirms the email address with a 6-digit code before the account is created 6 days ago
test_textparse.py

11.9 kB
Add meaning check, Groq model fallback and subject test run; close guard gaps 13 days ago
test_tokenizer_threads.py

1.09 kB
Fix 'Already borrowed': every fast tokenizer gets its own lock, so jobs running at the same time can share a model 5 days ago
test_tools_tabs.py

16.2 kB
Journal Finder: title-only search, journals or conferences in one step, conference location, result cards 6 days ago
test_wallet.py

5.29 kB
PhonePe webhook (POST /phonepe/webhook): checks the SHA256 username:password header and settles the order from PhonePe's status 6 days ago