Spaces:
Running
Running
Commit History
3 days ago
-
Smart Humanize faster: setting groups of a pass rewritten at once (GPU), rescue rewrites requested at the start of each call, vocabulary step alongside Parrot; job time in the log
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>82a89bf -
Journal Finder: SCIE / SSCI / AHCI / ESCI lists from Wikidata (open, partial) until Clarivate's lists are added
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>ee1736c -
Journal Formatter: footnotes, web references, books and reports, author marks, cleaner LaTeX
unknown +1: Claude Opus 5.5Found with a new tester (devtools/fmt_corpus.py + fmt_audit.py: 3 realistic manuscripts x 8 journal styles, Word and LaTeX checked against the source and the journal's rules, every LaTeX project compiled): - Footnotes were dropped everywhere: now real Word footnotes and \footnote in LaTeX. - Web references lost their URL ('Available' was read as the journal); every style now prints the URL its way. - Books and reports: IEEE / APA / Harvard / Vancouver / Chicago forms are read (edition, place, publisher) and formatted per style; an APA book is no longer turned into a journal article with 'Wiley' as the journal. - '(ISO, 2018)' resolves to 'International Organization for Standardization' (abbreviation / initials). - Elsevier LaTeX: author marks '1,*' no longer split into '?', the corresponding-author line is not an affiliation, no trailing commas; table captions get room above the table. - LaTeX: author-year reference lists unnumbered with a hanging indent; MDPI / Vancouver lists '1.…2eb3609 -
Stronger AI detector: two more paraphrase-robust models averaged into the score
unknown +1: Claude Opus 5.5Nine public detectors were tested (devtools/compare_detectors.py) on 18 AI-written academic samples, 21 human abstracts from 2008 and 16 paragraphs our humanizer had rewritten. Added: ShantanuT01/vanguard-ai-text-detector (ModernBERT-large, MIT) and Oxidane/tmr-ai-text-detector (RoBERTa, MIT). The final score is the mean of the previous ensemble and the two: AI 18/18, human 0/21, humanized 11/16 flagged (was 6/16). Rejected: PirateXX (flagged every human text), AICodexLab ModernBERT (18/21 human), desklib academic (13/21), econ-distilroberta (7/21), vraj33 (flagged nothing). DETECTOR_EXTRA sets the extra models ("" = none). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>dc37bdf
4 days ago
-
Fast engine on CPU about a third faster: versions pre-ranked by the two small detector models
unknown +1: Claude Opus 5.5On a CPU the large DeBERTa detector was about 2/3 of the detector time. Every version is now ranked by the two small models (on its own), the fluency check runs on the shortlist, and only the 2 best per sentence go to the full three-model detector; the document's AI score is still always the full detector's. Benchmark (4 AI paragraphs, laptop CPU): 100% -> 0% in 3 rounds in 218 s (was 320-350 s). int8 quantisation of the detector was tested and rejected: it changed 8 of 77 verdicts (devtools/bench_int8_detector.py). Capping versions per model at 2 was tested and rejected: it stalled at 23%. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>bc66a36 -
Fast engine: stronger first round, rounds 2+ judged in context, never builds on a worse round, stock AI phrases always rewritten
unknown +1: Claude Opus 5.5Benchmark (devtools/bench_fast.py, 4 AI paragraphs, 3-model detector): 100% -> 0% in 3 rounds and 100% -> 6% in 4 (was 4 rounds for 0%, first round 100% -> 79%). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>0cb108c -
Stronger AI detector: paraphrase-robust third model in the ensemble
unknown +1: Claude Opus 5.5fakespot-ai/roberta-base-ai-text-detection-v1 averaged with the current coai + desklib score. Measured (devtools/compare_detectors.py): AI samples 18/18 flagged, human abstracts from 2008 0/21, paragraphs our own humanizer had brought to 6%: 6/16 flagged (was 1/16). RADAR was tested and rejected (separation 0.72 on academic text). DETECTOR_MODEL3="" turns it off; DETECTOR_WEIGHT3 sets its share (0.5). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>eebf465 -
Fast engine: versions from several models at once (Gemini 3.5 Flash-Lite + Qwen 3.8 by default, gpt-oss-20b as fallback), checked inside the worker threads; generator benchmark
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>01f5654 -
Fast engine (opt-in with ?engine=fast) and one-step document upload
unknown +1: Claude Opus 5.5- fast.py: the whole document at once. The detector reads it once; every flagged sentence is rewritten in parallel by the language model (keep-every-detail prompt); versions must keep terms / numbers / citations, the meaning (embeddings + an independent faithfulness reading) and read as fluent English; the detector picks the most human version in context. Rounds repeat on what is still flagged within a time budget (FAST_BUDGET, 50 s). Live engine unchanged unless SMART_ENGINE=fast or the page is opened with ?engine=fast. - Smart Humanize opens on the Word upload, and dropping a file starts the run; the separate Humanizer tab is hidden. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>4a7a056
10 days ago
-
Journal Formatter and Journal Finder as native tabs of the suite (work in progress)
unknown +1: Claude Opus 5.5Both tools were separate Streamlit apps shown in a frame. Their engines now live in this repository and the tabs are built in Gradio. Journal Formatter (formatter_tab.py, formatmatch/) - FormatMatch engine copied from github.com/rasheedsbp/Formatmatch. - Manuscript + journal name / publisher style / Word template / author guidelines -> Word file, LaTeX project zip, formatting report. - Overleaf: the zip has main.tex at its top level; "Open in Overleaf" hands it over by its public address on the Space (SPACE_HOST), with upload instructions otherwise. Journal Finder (finder_tab.py, finder/) - journal_traffic pipeline copied from github.com/rasheedsbp/ catalyst-submit, with its data lists in finder/data (Git LFS): Scopus source list, SCImago 2025, ABDC 2025, PubMed serials, CORE ranks. - finder/run_job.py runs every search as its own process with its own result folder: the pipeline prints, calls input() and writes to a shared ./output, which is not safe for several users i…7ee2a84 -
Add meaning check, Groq model fallback and subject test run; close guard gaps
unknown +1: Claude Opus 5.5Found by running Smart Humanize on 16 subject samples (devtools/batch.py). - groqai: on a rate limit the request moves to the next model in GROQ_MODELS (limits are per model), then back when the limit has passed. - groqai.verify + humanizer: every rewritten sentence is read against the author's sentence; one that changed the meaning (moved p-value, reversed comparison, dropped method, "but" -> "so") gets the next version that passes, else the original (HUM_VERIFY, HUM_VERIFY_ALTS). - textparse.guard: integrity rules now apply to every version; damaged citations are repaired or the rewrite rejected; each citation exactly once; bracket spacing normalised before the checks. - basic_grammar no longer treats "(Mishra and Mishra, 2012)" as a doubled word. - Sentence splitting: initials and case names ("Justice K.S. Puttaswamy v. Union of India") no longer end a sentence; detector and humanizer share one rule. - pubrules: micro-prefixed and compound units (ug/m3, mmol/g, MP…689da70 -
Harden rewrite integrity, stop the final polish undoing humanization, add tests
unknown +1: Claude Opus 5.5Integrity (textparse, pubrules) - Guard rejects lost relation signs (p < 0.01 -> p 0.01), duplicated or invented citations and unbalanced brackets; closes sentences left open. - New rules: no added cause, no added "we"; mediate/moderate/correlate/ regress protected in any word form. - Fewer false rejections: "indicate" is a reporting verb, not a hedge; another form of an author's name is not invented. - Author's typography kept (no-break hyphens, curly quotes, minus sign); fragments keep their open ending and lower-case start. - strict_check() returns the rejection reason. Humanizer / Smart Humanize - Final polish repairs only sentences that fail the clarity checks; a clear humanized sentence is no longer reverted to the original, with a paragraph-level check on optional edits. - Rescue versions are written in four distinct manners and chosen next to their neighbours' current wording. - Word: bold/italic runs inside a rewritten sentence keep their format; no full stop …585f232