{-# LANGUAGE OverloadedStrings #-} module Config.Metadata.Format where import Utils (setLike) -- testing: unique keys balancedBracketTestCases :: [(String, String)] balancedBracketTestCases = setLike [ ("(abc [de] {fg} \"hi\")", "") , ("((abc)", "((abc)") , ("[abc]]", "]") , ("{[(abc)]}", "") , ("(abc]def)", "]def)") , ("\"abc \"def\" ghi\"", "") , ("\"abc", "\"abc") , ("", "") , ("{[()]}]", "]") , ("({\"[abc (def) 'ghi']\"})", "") , ("(((", "(((") , ("{\"abc [de}f]\"", "}f]\"") , ("abc", "") , ("\"\"", "") , ("\"\"abc\"\"", "") , ("(abc(def)ghi)", "") , ("[\"abc(def)ghi\"]", "") , ("{\"key\": \"value\"}", "") , ("(abc(def]ghi)", "]ghi)") , ("(abc{def)ghi}", ")ghi}") , ("abc\"", "\"") , ("[abc", "[abc") , ("abc]", "]") , ("{abc", "{abc") , ("abc}", "}") , ("(abc\"def)ghi\"", ")ghi\"") , ("\"abc(def\"ghi)", ")") ] -- testing: none; no `isUniqueKeys` check for zeros because keys are not unique by value (eg. −0.0 == 0 == 0.00 etc), but we need to test that they print out the same in the test-suite anyway printDoubleTests :: [(Double, Int, String)] printDoubleTests = setLike [ (-0, 0, "0") , (-0.0, 0, "0") , (-0.00, 0, "0") , (0, 0, "0") , (0.0, 0, "0") , (0.00, 0, "0") ] ++ [ (1.0, 0, "1") , (1.1, 1, "1.1") , (10.01, 2, "10.01") , (1000000.01, 2, "1,000,000.01") , (123456789.123456789, 15, "123,456,789.12345679") , (1.000000000000001, 15, "1.000000000000001") , (3.141592653589793, 15, "3.141592653589793") , (-3.141592653589793, 15, "-3.141592653589793") , (-1.000000000000001, 15, "-1.000000000000001") , (-123456789.123456789, 15, "-123,456,789.12345679") , (-1000000.01, 2, "-1,000,000.01") , (-10.01, 2, "-10.01") , (-1.1, 2, "-1.1") , (-1.0, 2, "-1") , (0.000000000000001, 15, "0.000000000000001") , (-0.000000000000001, 15, "-0.000000000000001") , (0.9999999999999999, 15, "1") , (-0.9999999999999999, 15, "-1") , (1.0000000000000002, 15, "1") , (-1.0000000000000002, 15, "-1") , (0.224, 0, "0") , (0.224, 1, "0.2") , (0.224, 2, "0.22") , (9876543210.98765, 5, "9,876,543,210.98765") -- Large number with decimals , (-9876543210.98765, 5, "-9,876,543,210.98765") -- Negative large number with decimals , (0.0000001, 7, "0.0000001") -- Very small positive number , (-0.0000001, 7, "-0.0000001") -- Very small negative number , (1234567890123456, 0, "1,234,567,890,123,456") -- Very large integer , (-1234567890123456, 0, "-1,234,567,890,123,456") -- Very large negative integer , (0.1234567890123456, 16, "0.1234567890123456") -- Many decimal places , (-0.1234567890123456, 16, "-0.1234567890123456") -- Negative with many decimal places , (999999.999999, 6, "999,999.999999") -- Edge case for comma placement , (-999999.999999, 6, "-999,999.999999") -- Negative edge case for comma placement , (1000000.000001, 6, "1,000,000.000001") -- Just over million with small decimal , (-1000000.000001, 6, "-1,000,000.000001") -- Negative just over million with small decimal , (-1.23e-10, 15, "-0.000000000123") -- Negative small scientific notation , (pi, 15, "3.141592653589793") -- Pi , (-pi, 15, "-3.141592653589793") -- Negative Pi ] -- infix rewrites -- Testing: unique keys, test keys for regexp validity cleanAuthorsRegexps, cleanAuthorsFixedRewrites :: [(String,String)] cleanAuthorsRegexps = [ ("([a-zA-Z]+),([A-Z][a-z]+)", "\\1, \\2") -- "Foo Bar,Quuz Baz" → "Foo Bar, Quuz Baz" , (",$", "") , (", +", ", ") , ("^([A-Z][a-z]+), ([A-Z]\\.)$", "\\2 \\1") -- "Smith, J." → "J. Smith"; for single words followed by a single letter, we can assume that it is a 'surname, initial' rather than 2 authors, 'surname1, surname2' , ("^([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.)$", "\\2 \\1, \\4 \\3") -- likewise, but for the 2-author case: 'Smith, J.; Doe, J.' , ("^([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.)$", "\\2 \\1, \\4 \\3, \\6 \\5") -- 3-author , ("^([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.); ([A-Z][a-z]+), ([A-Z]\\.)$", "\\2 \\1, \\4 \\3, \\6 \\5, \\8 \\7") -- 4-author, and I won't try for more , ("([A-Z]\\.)([A-Za-z]+)", "\\1 \\2") -- "A.Smith" → "A. Smith" , (" ([A-Z])([A-Z]) ([A-Za-z]+)", " \\1. \\2. \\3") -- " LK Barnes" → " L. K. Barnes" , ("([A-Z]\\.)([A-Z]\\.) ([A-Za-z]+)", "\\1 \\2 \\3") -- "A.B. Smith" → "A. B. Smith" , ("([A-Z]\\.)([A-Z]\\.)([A-Z]\\.) ([A-Za-z]+)", "\\1 \\2 \\3 \\4") -- "C.A.B. Smith" → "C. A. B. Smith" , (" ([A-Z])([A-Z])([A-Z]) ", " \\1. \\2. \\3. ") -- "John HAB Smith" → "John H. A. B. Smith" , (" ([A-Z])([A-Z]) ", " \\1. \\2. ") -- "John HA Smith" → "John H. A. Smith" , (" ([A-Z]\\.) ([A-Z]) ", " \\1 \\2. ") -- "John H. A Smith" → "John H. A. Smith" , (" ([A-Z]) ([A-Z]\\.) ", " \\1. \\2 ") -- "John H A. Smith" → "John H. A. Smith" , (" ([A-Z]) ", " \\1. ") -- "John H Smith" → "John H. Smith" ] cleanAuthorsFixedRewrites = [(". . ", ". "), ("?",""), (",,", ","), (", ,", ", "), (" MA,", ","), (", MA,", ","), (" MS,", ","), (" ScD MPH", ""), (" ScD,", ",") , ("Dr. ", "") , ("Dr ", ""), (" Eh.D.", ""), (" PhD", ""), (" Ph.D.", ""), (" MRCGP", ""), (" OTR/L", ""), (" OTS", "") , (" FMedSci", ""), ("Prof ", ""), (" FRCPE", ""), (" FRCP", ""), (" FRS", ""), (" MD", "") , (",, ,", ", "), ("; ", ", "), (" ; ", ", "), (" , ", ", "), (" and ", ", "), (", & ", ", ") , (", and ", ", "), (" MD,", " ,"), (" M. D.,", " ,"), (" MSc,", " ,"), (" M. Sc.", ""), (" B. Sc.", "") , (" PhD,", " ,"), (" Ph.D.,", " ,"), (" BSc,", ","), (" BSc(Hons)", ""), (" MHSc,", ",") , (" BScMSc,", ","), (" ,,", ","), (" PhD1", ""), (" BA(Hons),1", ""), (" , BSc(Hons),1", ",") , (" , MHSc,", ","), ("PhD,1,2 ", ""), ("PhD,1", ""), (" , BSc", ", "), (",1 ", ","), (" & ", ", ") , ("BA(Hons),", ","), (", (Hons),", ","), (", ,2 ", ","), (",2", ","), (" MSc", ","), (" , PhD,", ",") , (" JD,", ","), ("MS,", ","), (" BS,", ","), (" MB,", ","), (" ChB", ""), ("Meena", "M."), (", PhD1", ",") , (" DMSc", ""), (",, ", ", "), (", ,,", ", "), ("\"", ""), ("'", "’"), ("OpenAI, :, ", ""), (" et al", "") , (" et al.", ""), (", et al.", ""), ("Jr.", "Junior"), (", Jr.", " Junior"), (", Junior", " Junior") , (" DO,", ","), ("M. D. MPH", ""), (" ", " "), (" M. D. MBA", ""), (" Esq.", ""), (" Esq,", ",") , (" CAAB,", ","), (" DVM,", ","), (" D.V.M.", ","), (" M. D. M. P. H.", "") , (" M. D. MMM", ""), (" M. D. MHS", "")] -- 'author' metadata to be blacklisted: usually either nonsense, a third party, software tool, etc -- testing: unique list filterMetaBadSubstrings, filterMetaBadWholes :: [String] filterMetaBadSubstrings = setLike ["ABBYY", "Adobe", "InDesign", "Arbortext", "Unicode", "Total Publishing", "pdftk", "aBBYY" , "FineReader", "LaTeX", "hyperref", "Microsoft", "Office Word", "Acrobat", "Plug-in", "Capture", "ocrmypdf" , "tesseract", "Windows", "JstorPdfGenerator", "Linux", "Mozilla", "Chromium", "Gecko", "QuarkXPress", "AppleWorks" , "Apache", ".tif", "2001", "2014", "3628", "4713", "AR PPG", "ActivePDF", "Administrator" , "Administratör", "American Association for the Advancement of Science", "Appligent", "BAMAC6", "CDPUBLICATIONS", "CDPublications", "Chennai India", "Copyright", "DesktopOperator" , "Emacs", "G42", "GmbH", "IEEE", "Image2PDF", "J-00", "JN-00", "LSA User", "LaserWriter" , "Org-mode", "PDF Generator", "PScript5.dll", "PageMaker", "PdfCompressor", "Penta", "Preview", "PrimoPDF", "PrincetonImaging.com" , "Print Plant", "Radical Eye", "RealPage", "SDK", "SYSTEM400", "Sci Publ Svcs", "Scientific American", "Springer", "TIF" , "Unknown", "Utilities", "XPP", "apark", "bhanson", "cairo 1", "cairographics.org", "dvips", "easyPDF" , "eguise", "epfeifer", "fdz", "ftfy", "gscan2pdf", "jsalvatier", "jwh1975", "kdx", "pdf" , " OVID ", "imogenes", "firefox", "Firefox", "Mac1", "EBSCO", "faculty.vp", ".book", "PII" , "Typeset", ".pmd", "affiliations", "list of authors", ".doc", "untitled", "Untitled", "FrameMaker", "PSPrinter" , "qxd", "INTEGRA", "Xyvision", "CAJUN", "PPT Extended", "Secure Data Services", "MGS V", "mgs;", "COPSING" , "- AAAS", "Science Journals", "Serif Affinity", "Google Analytics", "rnvb085", ".indd", "hred_", "penta@", "WorkStation" , "ORDINATO+", ":Gold:", "XeTeX", "Aspose", "Abbyy", "Archetype Publishing Inc.", "AmornrutS", "OVID-DS", "PAPER Template" , "IATED", "TECHBOOKS", "Word 6.01", "TID Print Plant", "8.indd", "pdftk-java", "OP-ESRJ", "JRC5", "klynch" , "pruich", "Micron", "Anonymous Submission", "Asterisk", "KBarry2", ",-0", "fi-5530C2dj", "FUJIT S. U." , "LEVET_Layout", "Digitized by the ", "shaniahl", ".orig.pdf", ".dvi", ".qxd", ".ps", "doi:10", "DOI" , ".tmp", ".pdf", ".eps", ".PDF", "APA template", "Author Guidelines", "156x234mm", "C:\\", "D:\\" , "CUP_JBS", ".vp", ".wpd", "EBSCOhost", ".docx", ".qxp", "PDF_Banner", "MergedFile", "No Job Name" , "PII: ", "ProQuest Dissertation", "ScanGate", "Science Magazine", ".CHP", ".chp", ".tex", ".fm", "http://content.nejm.org/cgi/content/" , "stdin", "Corel PHOTO-PAINT", "Thomson Press India", "B L Ganju", "Meta˚Analytic", "RealObjects", "PDFreactor(R)", "Licensed for: Oxford University", "CoVantage" , "RYALS327-SCAN", "WWS-5ZM9", "", "[ M1C44 ]", "WWS-5ZM", "html2ps ", "version 1.0 beta2", "jason.richwine", "jmaynard" , "jmcfadde", "k.albert", "kstange", "macftz01", "markj", "mcdonaldm", "mchahino", "meiersa", "mkc43" , "pilc2501", "pm016", "pm025", "pm054", "pubdat", "randerer", "renee.lojewski", "tiff2ps", "yeh" , "Admin", "C U. P. Printing", "Debenu ", "Quick P. D. F. Library 9.12", "www.debenu.com", "JPL 99", "MinnickD", "Office", "Owner" , "SPDF", "Writer", "jcpham", "DLE4<8", "8AB@0B>", "Paperless", "psjoin 0.2", "Apex", "Elsevier Science" , "PsycINFO", "kristine gallo", "TeX", "PDFplus", "Elsevier", "N/A", "OmniPage", "scansoft", "Articlizer" , "ARTICLIZER", "c:/ncn", "1QS4P", "2-0crc", "Trove", "REV_ISS", "WEB_CDEV", "HelenMartin" , "DALiM", "HP PDF", "PDF Formatter", "Xerox D125", "Copier-Printer", "PubTeX" , "C:My Documents", ".wp", "Nova India", "/var/www", "oup_cercor" , "oup_humrep", "Print Publisher", "11.1.4012/W", "PDFium" , "Internet Archive (Scribe Version", "4.0-initial-155-gbba175a5" , "Asura Version", "(SR 3)", "EPSON", "Perfection 3170", "Nature User", "DVIPSONE" , "(32) 2.1.3", "http://www.YandY. com"] filterMetaBadWholes = setLike ["P", "b", "cretu", "user", "yeh", "Canon", "times", "is2020", "downes", "American Medical Association" , "om", "lhf", "comp", "Science Magazine", "Josh Lerner, Scott Stern (Editors)", "arsalan", "rssa_a0157 469..482", "Schniederjans_lo" , "mcdonaldm", "ET35-4G.vp", "spco_037.fm", "LaTeX2e", "Paperless", "fulvio", "Winter", "markj" , "Vahrenhorst", "vahrenhorst", "Vahrenhorst 2004", "Vahrenhorst 2008", "pilc2501", "yeh 2008", "markj 2009", "021186U129", "02_ASQ523602 1..33" , "03_gbb155 240..248", "1)", "1.0b", "110s(6) Science. 555-", "1247", "2913 | 01 Chorney", "301246", "378787 1100..1105", "4559" , "459119", "4AD004/Prov9 FMV/4P", "52457938", "7.0 psym 7#1 2002", "72508-danigelis.q41", "9757 van Stuijvenberg", "99202", "BBS1200319 661..726", "BBS1300119 297..350" , "Backtalk", "Backups", "BatesTalk", "Brookings draft v", "CAM200", "CDP370136 177..182", "CMMI10", "COLLINCH01", "COMM34$U44" , "COPSINGOLEVET", "DO00010384 643..650", "DP 14-009", "Digestion", "Final_EXIT_text", "Gerontotherapeutics", "Harrison J", "II", "IMD JATS" , "ISO/IEC 9899:yyyy", "Information", "JC162160 1642..1651", "JEOBP_14_2_2011", "JMCB16U208", "Journal06-04b.cdr", "Latvala", "Layout 1", "MASTER THESIS 5" , "MIT-LCS:MIT/LCS/TR-164", "MSS21283 927..934", "Masters' Thesis", "Nowicka, R", "OP-ESRJ170071 1..13", "OP-QJEC150001 571..614 ++", "P:TEXSICOMP 9-1 8849 8849", "PEDS20142707_pap_peds 1..9" , "PEDS_20173872 1..11", "S0747-5632(00)00043-1", "PME00042", "PSCI13124", "Print", "RAAG_A_1310021_O", "RULES-2014-P-CON", "Review", "SIA" , "Slide 1", "Standards 05-06", "TF-TPDR120086 1..8 ++", "Title", "Title:", "Tobler_CameraReady", "US020180204116A120180719", "Unknown", "VJMB_A_1327416_O" , "Ventura - 12JBR8", "Vol 9#5", "WR02015.fm", "Wildcats", "ZP577", "ajps_461_HR", "anp060-79 407..506", "bhm211 1737..1747", "btn127 1381..1385" , "c011.tex", "cns_317_LR", "ddl206 2721..2731", "default", "desc_745.fm", "e08:9", "ejn_5217 3532..3540", "emon-84-04-01 3..28", "es-2013-03688w 1..9" , "foo", "hcrj901068 151..157", "hred_91_110.42_66", "inhy_60_205.213_218", "ipg1200217a", "jasar08282 841..854", "jcp20186 373..378", "jcp25202 175..179", "jcpp_1798 1192..1199" , "jn169326 872..877", "khan", "mbev_16_1218.1791_1798", "mgs;01jan95", "osteo-1203 257..264", "oup_cercor_bhy157 1..11 ++", "pnas201201895 1..8", "pnp06457 1125..1128", "s00221-005-2334-6ca-web 23..30" , "stdin", "template", "title", "vsp0092 187..211", "ÿþ1", "ÿþ14-226", "“Alt", "chowe", "comp5" , "dan", "decosta", "gottfredson", "van den Hurk", "Word", "pdftk-java 3.0.9" , "bar", "tmp", "jvore", "ÿþ", "I.R.I.S.", "C&M", "C&M", "()", "[]", "{}" , "Gundars Strads", "Error - CORE file server", "comp2", "u2ps", "mac2" , "Chrome", "Chromium", "Firefox", "Safari", "Author", "Binsbench" , "Western Publishing", "John Wiley, Sons", "40505-40237-1-PB.pdf"] -- tests: unique-all htmlRewriteTestCases :: [(String, String)] htmlRewriteTestCases = setLike [("when moving from 8 to 256 GPUs", "when moving 8 → 256 GPUs") , ("*foo* bar", "foo bar") , ("Code is available at github.com/microsoft/SPACH.

", "Code is available at github.com/microsoft/SPACH.

") , ("...biochemical programs (preconditioning)2,3,4. Under...", "...biochemical programs (preconditioning)2,3,4. Under...") , ("or strokes (n = 7). Both presurgical and", "or strokes (n = 7). Both presurgical and") ] -- testing: unique keys, valid regex keys; used with `sedMany` htmlRewriteRegexpAfter, htmlRewriteRegexpBefore, htmlRewriteFixed :: [(String, String)] htmlRewriteRegexpAfter = [ ("from ([0-9\\.]+) to ([0-9\\.]+)", "\\1 → \\2") -- "when moving from 8 to 256 GPUs" → "when moving 8 → 256 GPUs" , ("\\(-([0-9])", "(−\\1") -- "5.5 (-10 to +10)" → "5.5 (−10 to +10)" , ("^(

\\[Keywords: .+\\]

)$", "\n") -- NOTE: we do *not* do `("(.*)([a-zA-Z0-9].*[^>])", "

  • \\1

    • ") -- work around Pandoc generating naked-text list items, which causes perennial downstream errors in the JS , ("([0-9.]+)E10[-−–—]([0-9]+)", "\\1 × 10−\\2") , ("([0-9])- (millisecond|second|minute|hour|day|week|month|year)", "\\1-\\2") -- line-break errors like 'we observed the mice for 2- minutes or 10-minutes afterwards' , ("\\\\emph\\{([a-zA-Z0-9-]+)\\}", "\\1") , ("\\\\textit\\{([a-zA-Z0-9-]+)\\}", "\\1") -- rewrite *Markdown italics* to HTML italics, and strong/bold: , ("(.*)\\*(.+)\\*(.*)", "\\1\\2\\3") , ("(.*)\\*\\*(.+)\\*\\*(.*)", "\\1\\2\\3") , ("

    This paper was accepted by [A-Z][a-z]+ [A-Z][a-z]+, .*\\.

    ", "") , (" ### Author Declarations .*$", "") , (" ### Competing Interest Statement .*$", "") , (" Study ([0-9][a-z]?)", " Study \\1") , (" Experiment ([0-9][a-z]?)", " Experiment \\1") , ("Section ([a-zA-Z0-9.-]+)", "§\\1") , ("\\*\\*Section ([a-zA-Z0-9.-]+)\\*\\*", "§\\1") -- , (" (NCT[0-9]+)", "\\1") , (" (NCT[0-9]+)

    ", "\\1.

    ") -- cleanup bare URLs (particularly common in Arxiv abstracts when linking to Github): , (" (https?://[a-zA-Z0-9_\\.\\?/-]+)$", " \\1$") , (" (https?://[a-zA-Z0-9_\\.\\?/-]+)

    ", " \\1

    ") , (" (https?://[a-zA-Z0-9_\\.\\?/-]+)\\)", " \\1 )") , (" (https?://[a-zA-Z0-9_\\.\\?/-]+) \\.", " \\1.") , (" (https?://[a-zA-Z0-9_\\.\\?/-]+) ?\\.

    ", " \\1.

    ") , ("at:? (github.com/.*).

    ", "at \\1.

    ") -- "Code is available at github.com/microsoft/SPACH.

    " / "Code will be released at: github.com/NVlabs/SegFormer.

    " , (" (https://github.com/[a-zA-Z0-9_\\.\\?/-]+) ?\\.

    ", " Github.

    ") -- citations: eg '...biochemical programs (preconditioning)2,3,4. Under...'; we require 2 because 1 number is ambiguous & collides with chemistry/genetics. , ("([a-z[:punct:]])([0-9]+,[0-9]+)\\.", "\\1\\2.") , ("([a-z[:punct:]])([0-9]+,[0-9]+,[0-9]+)\\.", "\\1\\2.") -- '2,3,4.' , ("([a-z[:punct:]])([0-9]+,[0-9]+,[0-9]+,[0-9]+)\\.", "\\1\\2.") , ("([a-z[:punct:]])([0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+)\\.", "\\1\\2.") , ("([a-z[:punct:]])([0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+)\\.", "\\1\\2.") , ("([a-z[:punct:]])([0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+,[0-9]+)\\.", "\\1\\2.") , ("([0-9]) x ([0-9]+)\\(([0-9−-]+)\\)", "\\1 × \\2\\3") -- '~2.5 x 10(13)' → '~2.5 × 1013' -- common spelling error, 'a' → 'an': , (" a ([aeio][a-z]+)", " an \\1") -- - comma-separate at thousands for consistency: -- skip thousands, since clobbers citations like 'Herring 2009' (which turns into 'Herring 2,009') , (" ([0-9]+)([0-9][0-9][0-9])([0-9][0-9][0-9])", " \\1,\\2,\\3") -- millions , (" ([0-9]+)([0-9][0-9][0-9])([0-9][0-9][0-9])([0-9][0-9][0-9])", " \\1,\\2,\\3,\\4") -- billions , (" ([0-9]+)([0-9][0-9][0-9])([0-9][0-9][0-9])([0-9][0-9][0-9])([0-9][0-9][0-9])", " \\1,\\2,\\3,\\4,\\5") -- trillions , ("([0-9]+) ([0-9]+)", "\\1,\\2") -- '50 000' → '50,000' , ("([0-9]+) percent([ [:punct:]])", "\\1%\\2") -- eg '$22,000 (46 percent) higher annual early-career wages than they would' , ("\\(([0-9\\.]+)[xX] ", "(\\1× ") -- "we are faster (10.1x faster) than a competitor" → "we are faster (10.1× faster) than a competitor" , ("\\(([0-9\\.]+)[xX],", "(\\1×,") -- "to more than 3,000x," , ("([0-9][0-9]+) [xX] ([0-9][0-9]+) ", "\\1×\\2") -- "high fidelity generation of 1024 x 1024 images" / "0.85 X 30 mEq/kg" , ("([0-9][0-9]+) ?[xX] ?([0-9][0-9]+) ?px", "\\1×\\2px") -- "Alexnet performance for 16 x16 px features)." , ("([0-9]+)[ -]fold", "\\1×") , ("([0-9]+)[ -]times", "\\1×") , ("
    ([A-Z][a-z]+)<\\/strong>

    ", "

    \\1: ") --
    Background

    , ("

    ([A-Z][a-z]+)<\\/strong>

    ", "

    \\1: ") , ("

    ([A-Z][a-z]+)<\\/strong>:

    ", "

    \\1: ") , ("

    ([A-Z][a-z]+ [A-Za-z]+)<\\/strong>:

    ", "

    \\1: ") , ("

    ([A-Z][a-z]+ [A-Za-z]+ [A-Za-z]+)<\\/strong>:

    ", "

    \\1: ") , ("

    ([A-Z][a-z]+ [A-Za-z]+ [A-Za-z]+ [A-Za-z]+)<\\/strong>:

    ", "

    \\1: ") , ("([A-Za-z]+ [0-9]+)", "\\1") -- PLOS: 'Experiment 3' etc. , ("^en$", "") , (" ([0-9]) h ", " \\1h ") -- hour abbreviation , ("aged ([0-9.]+) to ([0-9.]+)", "aged \\1–\\2") -- eg "aged 39 to 73" → "aged 39–73" , (" ([0-9.]+)-([0-9.]+)", " \\1–\\2") -- CI EN DASH: "CI: 0.10-0.28" → "CI: 0.10–0.28" , (" \\.([0-9])", " 0.\\1") -- restore missing zero: "CI: .91-1.28" → "CI: 0.91-1.28" , (" 0\\.([0-9.]+)-\\.([0-9.]+)", " 0.\\1–0.\\2") -- restore missing zero: "CI: 0.10-.28" → "CI: 0.10-0.28" , (" \\.([0-9.]+)-\\.([0-9.]+)", " 0.\\1–0.\\2") -- restore missing zeros: "CI: .10-.28" → "CI: 0.10-0.28" , ("range: ([0-9%.]+) to ([0-9%.]+)", "range: \\1–\\2") -- eg. "range: 0.59 to 43.89" , ("between ([0-9%]+) and ([0-9]+)", "\\1–\\2") -- "range between 2 and 10" → "range 2–10" , ("([0-9%]) – ([0-9])", "\\1–\\2") -- space-separated en-dash ranges eg. "with a range of ~0.60 – 0.71 for height" , ("([0-9%]) – ([a-z])", "\\1—\\2") -- a number-alphabet en-dash is usually an em-dash eg. "a Fréchet Inception Distance (FID) of 10.59 – beating the baseline BigGAN model—at" , ("([a-zA-Z]) – ([[:punct:]])", "\\1—\\2") -- en dash errors in WP abstracts: usually meant em-dash. eg. 'disc format – Universal' , ("([[:punct:]]) – ([a-zA-Z])", "\\1—\\2") , ("([a-zA-Z’]) – ([a-zA-Z])", "\\1—\\2") -- eg: "Aspects of General Intelligence – a Deep Phenotyping Approach" , ("([a-zA-Z’]) - ([a-zA-Z])", "\\1—\\2") -- spaced hyphens: also usually em dashes: "Towards personalized human AI interaction - adapting the behavior of AI agents" , (" -([0-9])", " −\\1") -- eg. 'β = -0.08', HYPHEN to MINUS SIGN; review of annotations shows that this is almost always safe to do except in a few very rare cases like a psychiatry paper abbreviating 'DSM-3, -4, and -5'. , ("×10[-–—]([0-9]+)", " × 10−\\1") , (" × 10[-–—]([0-9]+)", " × 10−\\1") -- the Unicode '×' seems to never match when used inside a range...? , ("([0-9]) [x×X] 10[-–—]([0-9]+)", "\\1 × 10−\\2") , ("([0-9]) [x×X] 10\\([-–—]([0-9]+)\\)", "\\1 × 10−\\2") , ("-([0-9]+)", "−\\1") -- eg. '10-7', HYPHEN to MINUS SIGN , ("([0-9]+)\\^([0-9\\.]+)", "\\1\\2") -- eg '(p<10^4)' , ("([0-9]+)\\^[-−]([0-9\\.]+)", "\\1−\\2") -- eg '(p<10^-4)' , (" ([0-9]+)%-([0-9]+%) ", " \\1–\\2 ") -- " of 95%-99%" → " 95–99%" , (" ([0-9]+)-([0-9]+%) ", " \\1–\\2 ") -- " of 95-99%" → " 95–99%" , ("([0-9]) %", "\\1%") , (" ([0-9]+) out of the ([0-9]+) ", " \\1⁄\\2 ") , (" ([0-9]+) out of ([0-9]+) ", " \\1⁄\\2 ") -- need space-separation due to examples like 'smartphones are now used by 5.8 out of 7.0 billion people on earth' , (" ([0-9][0-9]?[0-9]?) of ([0-9][0-9]?[0-9]?) ", " \\1⁄\\2 ") , ("([0-9]+) of ([0-9]+)", "\\1⁄\\2") , (" ([~.0-9]+)[xX]", " \\1×") , ("=-\\.([.0-9]+)", " = -0.\\1") , ("([0-9]*[02456789])th ", "\\1th ") , ("([0-9]*[1])st ", "\\1st ") , ("([0-9]*[3])rd ", "\\1rd ") , ("CI=([.0-9])", "CI = \\1") -- 'CI=0.90' → 'CI = 0.90' , ("RR=([.0-9])", "RR = \\1") -- 'RR=2.9' → 'RR = 2.09' , ("OR=([.0-9])", "OR = \\1") -- 'OR=2.9' → 'OR = 2.09' , ("AOR=([.0-9])", "AOR = \\1") -- 'AOR=2.9' → 'AOR = 2.09' -- NOTE TO SELF: all math-inline expressions may be deletable if the OA API latex2unicode.py script works out well. -- math regexes , ("\\\\\\(([a-zA-Z])\\\\\\)", "\\1") -- '\(d\)', 'the state matrix \(A\)' , ("\\\\\\(([0-9.]+)\\\\\\)", "\\1") -- '\(30\)' , ("\\\\\\(\\(\\\\leq ([0-9.]+)\\)\\\\\\)", "(≤\\1)") -- "\\((\\leq 500)\\)" -> '(≤500)' , ("\\$([.0-9]+) \\\\cdot ([.0-9]+)\\^([.0-9]+)\\$", "\\1 × \\2^\\3^") , ("\\$([.0-9]+) \\\\cdot ([.0-9]+)\\^\\{([.0-9]+)\\}\\$", "\\1 × \\2^\\3^") , ("\\\\\\(([0-9.]+) ?\\\\times\\\\\\)", "\\1×") -- '\(1.5\times\)' , ("\\\\\\(([0-9.]+) ?\\\\times ([0-9.]+)\\\\\\)", "\\1×\\2") -- '\(224\times\ 224)' , ("\\\\\\(([0-9.]+) \\\\\\%\\\\\\)", "\\1%") -- '\(90 \%\)' , ("\\\\\\(([0-9.]+)\\\\\\%\\\\\\)", "\\1%") -- '\\(83.6\\%\\)' , ("\\\\\\(\\\\texttt\\{([A-Za-z]+)\\}\\\\\\)", "\\1") -- 'we present the \\(\\texttt{GamePhysics}\\) dataset' , ("\\\\\\(\\\\textbf\\{([A-Za-z]+)\\}\\\\\\)", "\\1") -- 'We dub ρ the \(\textbf{polarity}\) parameter' , ("\\\\\\(\\\\times\\\\\\)", "×") -- '\(\times\)' , ("\\\\\\(([0-9]*)\\^([0-9]*)\\\\\\)", "\\1\\2") -- '\(10^4\)' , ("\\\\\\(([0-9]*)\\^\\{([0-9]*)\\}\\\\\\)", "\\1\\2") -- '\(10^{40}\)' , ("([A-z][a-z]+) ?et ?al ?\\(([0-9][0-9][0-9][0-9])\\)", "\\1 et al \\2") -- 'Dette et al (2013)' , ("([A-Z][a-z]+) and ([A-Z][a-z]+),? ([0-9]+)", "\\1 & \\2 \\3") -- 'Foo and Bar 1999', 'Foo and Bar, 1999' → 'Foo & Bar 1999'; 'et al' is handled by Pandoc already , ("([A-Z][a-z]+) & ([A-Z][a-z]+), ([12][0-9][0-9][0-9])", "\\1 & \\2 \\3") , ("([A-Z][a-z]+) & ([A-Z][a-z]+), ([12][0-9][0-9][0-9])", "\\1 & \\2 \\3") , ("\\. Copyright.*[12][0-9][0-9][0-9] John .* Ltd\\.", ".") -- 'Copyright © 2013 John Wiley & Sons, Ltd.' , ("
    ([a-zA-Z]+)

    ", "

    \\1: ") , ("([a-zA-Z0-9_]+):

    ", "

    \\1: ") , ("([a-zA-Z0-9_]+):", "

    \\1: ") , ("([a-zA-Z0-9_]+)\\.", "

    \\1: ") , ("([A-Z.]+)", "\\1") -- odd acronym markup , ("", "") , ("", "") , ("", "") , (" © [0-9]+ European Association of Personality Psychology.*$", "") , ("☆$", "") , (" *", " ") -- squeeze whitespace , ("
    *

    ", "

    ") , ("

    *", "

    ") , (" *

    ", "

    ") , (" ,$", "") ] -- simple string substitutions: -- testing: unique keys htmlRewriteFixed = [ ("One Sentence Summary

    \n

    ", "One Sentence Summary: ") , ("One Sentence Summary

    ", "One Sentence Summary: ") , ("R2D2", "R2D2") , ("", "") , ("", "") , ("

    ", "

    ") , ("

    ", "

    ") , ("

    ?

    ", "

    \n

    ") , ("

    ", "

    \n

    ") , ("

    ", "\n

    ") , ("

    ", "\n

    ") , ("

    ", "\n

    ") , ("

    \n \n

    ", "

    \n

    ") , (" \\( ", " (") , (" \\) ", " )") , (" 

    ", "

    ") , ("

    ", ".

    ") , ("R *2", "R2") , (" ", "") , ("href=\"github.com", "href=\"https://github.com") , ("https://github.com/deepmind/ deepmind-research/", "https://github.com/deepmind/deepmind-research/") , ("i . e .,", "ie.") , ("

    Conclusion

    \n

    ", "

    Conclusion: ") , ("

    Motivation

    \n

    ", "

    Motivation: ") , ("

    Availability

    \n

    ", "

    Availability: ") , ("

    Importance

    \n

    ", "

    Motivation: ") , ("

    Main Outcomes & Measures

    \n

    ", "

    Outcomes & Measures: ") , ("

    [Keywords: ]

    ", "") , ("Null: ", "") , ("&gt;", ">") , ("  = ", " = ") , ("<=", "≤") , (">=", "≥") , (" >= ", " ≥ ") , (" =< ", " ≤ ") , ("P=", "p = ") , ("p=", "p = ") , ("β=", "β = ") , ("\8217=", "\8217 = ") , (" the the ", " the ") , (" a imbalance", " an imbalance") , ("
    ", "") , ("+", "⁺") , ("=", " = ") -- eg. 'rA=0.28' , ("", "") , ("", "") , ("", "") , ("", "") -- math substitutions: , ("$e=mc^2$", "e = mc2") , ("$\frac{4}{3} \\cdot \\pi \\cdot r^3$", "4⁄3 × π × _r_^3^") , ("$f(x; x_0,\\gamma)$", "f(x; x0,γ") , ("$\\mathcal{O}(log n)$", "𝒪(log n)") , ("$\\mathrm{sinc}(0)=1$", "sinc(0) = 1") , ("$\\mathrm{sinc}(ax)$", "sinc(ax)") , ("$\\mathrm{sinc}(x)=\\sin(x)/x$", "sinc(x) = sin(x)⁄x") , ("$\\mu$", "μ") , ("$O(log n)$", "𝒪(log n)") , ("$x$", "x") , ("$(x_0,\\gamma)$", "(x0, γ)") , ("a n layer", "a n layer") , ("{\\epsilon}-greedy", "ε-greedy") , (" L0", " 𝓁0") , ("l1-distance", "𝓁1-distance") , ("L1 loss", "𝓁1 loss") , (" L1", " 𝓁1") , ("L1-penalized", "𝓁1-penalized") , ("L1-regularized", "𝓁1-regularized") , ("l2-distance", "𝓁2-distance") , (" L2", " 𝓁2") , ("({\\lambda})", "(λ)") , (" L-infinity", " 𝓁∞") , (" L-∞", " 𝓁∞") , (" L∞", " 𝓁∞") , (" Lp", " 𝓁p") , ("A", "A") , ("B", "B") , ("C", "C") , ("S", "S") , (" N pixels", " N pixels") , (" n-step", " n-step") , (" O(1)", " 𝒪(1)") , (" On log n)", " 𝒪(n log n)") , ("O((log n log log n)^2)", "𝒪(log2 n log log n)") , (" O(log n)", " 𝒪(log n)") , ("O(log n) ", "𝒪(log n) ") , ("O(m log^2 n)", "𝒪(m log n + n log2 n)") , ("O(n^2)", "𝒪(n2)") , ("O(n log n)", "𝒪(n log n)") , ("O(n log n)", "𝒪(n log n)") , ("O(log n)", "𝒪(log n)") , ("O(nm)", "𝒪(n×m)") , ("O(n)", "𝒪(n)") , (" O(N)", " 𝒪(N)") , ("O(N) ", "𝒪(N) ") , ("O(\\(L^2\\)", "𝒪(L2)") , ("O(\\(L\\log L\\)", "𝒪(L log L)") , (" O(sqrt(n)) ", " 𝒪(√n) ") , (" O(T)", " 𝒪(T)") , ("\\(10^{-16}—10^{-10} \\sim \\textrm{M}_\\odot\\)", "10−16–10−10M☉") , ("\\(0.15{-}1.3 {\\rm M}_{\\odot}\\)", "0.15–1.3M☉") , ("\\([0,1]\\)", "[0,1]") , ("\\(0.96\\)", "0.96") , ("\\(0<p<1\\)", "0 < p < 1") , ("\\(100,\\!000\\)", "100,000") , ("\\(1,\\!000\\times\\)", "1,000×") , ("\\(1,000\\times\\)", "1,000×") , ("\\(10^5\\times\\)", "105×") , ("\\(\119978(n2)\\)", "𝒪(n2)") , ("\\(124/144\\)", "124⁄144") , ("\\(128/255\\)", "128⁄255") , ("\\(1/2 H_n\\)", "1⁄2Hn") , ("\\(1/(3n)\\)", "1⁄(3n)") , ("\\(1.644934\\approx \\pi^2/6\\)", "1.644934 ≈ π2⁄6") , ("\\(_{16}\\)", "16") , ("\\(1 - \\frac{1}{e}\\)", "1 − 1⁄e") , ("\\(1/n\\)", "1⁄n") , ("\\(1,...,n\\)", "1,...,n") , ("\\(1-\\tilde \\Omega(n^{-1/3})\\)", "1 − Ω̃(n−1⁄3)") , ("\\(1-\\tilde O(n^{-1/3})\\)", "1 − 𝑂̃(n−1⁄3)") , ("\\(2.4\\)", "2.4") , ("\\(2\\cdot \\mathtt{OPT}\\)", "2 · OPT") , ("\\(2^{\\Omega(k)}\\)", "2Ω(k)") , ("\\(2^S \\to \\mathbb{R}\\)", "2S ⟶ ℝ") , ("\\(3,\\!000\\times\\)", "3,000×") , ("\\(42.5\\)", "42.5") , ("\\(4.5\\%\\)", "4.5%") , ("\\(47.1\\)", "47.1") , ("\\(4\\sim 16\\times\\)", "4–16×") , ("\\(_{50}\\)", "50") , ("\\(5\\%-35\\%\\)", "5%–35%") , ("\\(6\\times 10^{-6}\\)", "6×10−6") , ("\\(7.5\\sim9.5\\times\\)", "7.5–9.5×") , ("\\(8/255\\)", "8⁄255") , ("\\(86\\%\\)", "86%") , ("\\(9.3\\%\\)", "9.3%") , ("\\9r > 1", "r > 1") , ("\\(\\alpha > 0\\)", "α > 0") , ("\\(\\alpha\\)", "α") , ("\\(a^nb^{2n}\\)", "anb2n") , ("\\(a^nb^mc^{n+m}\\)", "anbmcn+m") , ("\\(a^nb^nc^n\\)", "anbncn") , ("\\(a^nb^n\\)", "anbn") , ("\\(\\approx\\)", "~") , ("\\(\\beta>0\\)", "β > 0") , ("\\(\\boldsymbol{sponge} \\sim\\boldsymbol{examples}\\)", "sponge examples") , ("\\(B(u,u)\\)", "B(u, u)") , ("\\(c>0\\)", "c > 0") , ("\\(C > 1\\)", "C > 1") , ("\\(^\\circ\\)", "°") , ("\\(c n^{1/3}\\)", "cn1⁄3") , ("\\(c\\)", "c") , ("\\(d^{3/2}\\)", "d3⁄2") , ("\\(d^{5/4}\\)", "d5⁄5") , ("\\(\\Delta^0_n\\)", "Δ0n") , ("\\(\\dot{M}\\)", "̇M") , ("\\(\\dot{x} = Ax + Bu, y = Cx + Du\\)", "͘x = Ax + Bu, y = Cx + Du") , ("\\(D\\)", "D") , ("\\(e^{-kq^2}.\\)", "e−kq2") , ("\\(\\ell_1/\\ell_2\\)", "𝓁1/𝓁2") , ("\\(\\ell_1\\)", "𝓁1") , ("\\(\\ell_2\\)", "𝓁2") , ("\\(\\ell_\\infty\\)", "𝓁∞") , ("\\(\\ell_p\\)", "𝓁p") , ("\\n \\geq 3f+1\\)", "n ≥ 3f + 1") , ("\\n \\geq 6f+1\\)", "n ≥ 6f + 1") , ("\\(r = 0.99\\)", "r = 0.99") , ("\\(\\epsilon n \\log n + \\U0001D4AA(n)\\)", "ε n log n + 𝒪(n)") , ("\\(\\epsilon=\\epsilon(\\eta)\\)", "ε = ε(η)") , ("\\(\\epsilon \\leq C\\cdot\\mathtt{OPT} + O(\\mathtt{VC}(\\mathcal{H})\\cdot \\eta)\\)", "ε ≤ C · OPT + 𝒪(VC(ℋ) · η)") , ("\\(\\epsilon\\)", "ε") , ("\\(\\epsilon=\\Theta_{\\mathcal{H}}(\\eta)\\)", "ε = Θℋ(η)") , ("\\(\\epsilon=\\Theta(\\mathtt{VC}(\\mathcal{H})\\cdot \\eta)\\)", "ε = Θ(VC(ℋ)·η)") , ("\\(\\eta\\)", "η") , ("\\(\\exp({\\mathcal{O}}(k))\\)", "exp(𝒪(k))") , ("\\(\\exp({\\Omega}(d))\\)", "exp(Ω(d))") , ("\\(F(G(X)) \\approx X\\)", "F(G(X)) ≈ X") , ("\\(f < n\\)", "f < n") , ("\\(f_\\theta\\)", "fθ") , ("\\(f(x) = x \\cdot \\text{sigmoid}(\\beta x)\\)", "f(x) = x × sigmoid(β x)") , ("\\(F: Y \\rightarrow X\\)", "F : Y → X") , ("\\(\\gamma = 0.999\\)", "γ = 0.999") , ("\\(\\gamma = 0.99\\)", "γ = 0.99") , ("\\(G\\)", "G") , ("\\(>\\)", ">") , ("\\(G: X \\rightarrow Y\\)", "G : X → Y") , ("\\(G(X)\\)", "G(X)") , ("\\(\\hbar\\)", "ℏ") , ("\\(H_n \\sim \\ln n\\)", "Hn ln n") , ("\\(iii\\)", "3") , ("\\(ii\\)", "2") , ("\\(i\\)", "1") , ("\\(\\infty\\)", "∞") , ("\\(\\it and\\)", "\\(\\it also\\) and also") , ("\\(\\it
    performance\\)    ", "performance") , ("\\(iv\\)", "4") , ("\\(k=2\\)", "k = 2") , ("\\(k=3\\)", "k = 3") , ("\\(\\kappa\\)", "𝜅") , ("\\(k \\leq d\\)", "k ≤ d") , ("\\(k \\ll d\\)", "k ≪ d") , ("\\(k = \\log n\\)", "k = log n") , ("\\(k \\rightarrow \\infty\\)", "k → ∞") , ("\\(k\\)", "k") , ("\\(K\\)", "K") , ("\\(L_0\\)", "L0") , ("\\(L_1\\)", "L1") , ("\\(l_1\\)", "𝓁1") , ("\\(L_2\\)", "L2") , ("\\(\\langle B(u,u), u\\rangle=0\\)", "〈B(u, u), u〉 = 0") , ("\\(\\leftarrow\\)", "←") , ("\\(L_\\infty\\)", "𝓁∞") , ("\\(\\log n\\)", "log n") , ("\\(L\\)", "L") , ("\\(<2\\%\\)", "<2%") , ("\\(<4\\%\\)", "<4%") , ("\\(m^{1+o(1)}\\)", "m1+o(1)") , ("\\(\\mathbf{R}^3\\)", "𝐑3") , ("\\(\\mathcal{H}\\)", "ℋ") , ("\\(\\mathcal{M}\\)", "𝓜") , ("\\(\\mathcal{O}(100)\\)", "𝒪(100)") , ("\\(\\mathcal{O}(1)\\)", "𝒪(1)") , ("\\(\\mathcal{O}(1/\\sqrt{d})\\)", "𝒪(1⁄√d)") , ("\\(\\mathcal{O}(L^2)\\)", "𝒪(L2)") , ("\\(\\mathcal{O}(L\\log(L))\\)", "𝒪(log L)") , ("\\(\\mathcal{O}(L\\sqrt{L})\\)", "𝒪(√L)") , ("\\(\\mathcal{O}(n\\log n)\\)", "𝒪(n log n)") , ("\\(\\mathsf L = \\mathsf P\\)", "L = P") , ("\\(\\mathsf{TC}^0\\)", "TC0") , ("\\(\\mathtt{VC}(\\mathcal{H})\\)", "VC(ℋ)") , ("\\(\\mu\\)", "μ") , ("\\mu", "μ") , ("\\(n^{-1/2}\\)", "n−1⁄2") , ("\\(n^{1/2}\\)", "n1⁄2") , ("\\(n^{1/3}\\)", "n1⁄3") , ("\\(n^{1/4}\\)", "n1⁄4") , ("\\(n^{-1}\\)", "n−1") , ("\\(n^3{(n^2)}^n\\)", "n3(n3)n") , ("\\(\\nabla \\log p_t\\)", "∇ log pt") , ("\\(N_A \\ll N_B\\)", "NA ≪ NB") , ("\\(n^{-\\alpha}\\)", "n−α") , ("\\(N_A/(N_A+N_B)\\)", "Na / (NA + NB)") , ("\\(n \\approx d^p\\)", "n ≈ dp") , ("\\(n \\approx d\\)", "n ≈ d") , ("\\(N_A\\)", "NA") , ("\\(n^{-\beta}\\)", "n−β") , ("\\(N_B\\)", "NB") , ("\\(n^{n^{n^{n^{n^n}}}}\\)", "nnnnnn") , ("\\(n^{O(k)}\\)", "n𝒪(k)") , ("\\(n\\)", "n") , ("\\(N\\)", "N") , ("\\(N \\times T\\)", "N × T") , ("\\(\\nu\\)", "ν") , ("\\(O(1)\\)", "𝒪(1)") , ("\\(O(C)\\)", "𝒪(C)") , ("\\(O(D^3)\\)", "𝒪(D3)") , ("\\(O(n \\log n)\\)", "𝒪(n log n)") , ("\\(O(n2)\\)", "𝒪(n2)") , ("\\(O(K^2 \\log T)\\)", "𝒪(K2 log T)") , ("\\(O(k\\cdot n\\log (n/k))\\)", " 𝒪(k × log(n⁄k))") , ("\\(O(K \\log T + K^2 \\log \\log T)\\)", "𝒪(K log T + K2 log log T)") , ("\\(O(L(\\log L)^{2})\\)", "𝒪(L(log L)2)") , ("\\(O(\\log n)\\)", "𝒪(log n)") , ("\\(O(\\log T)\\)", "𝒪(log T)") , ("\\(O(n^2 \\log T)\\)", "𝒪(n2 logT") , ("\\(O(n^2)\\)", "𝒪(n2)") , ("\\(O(N^2)\\)", "𝒪(n2)") , ("𝒪(n^2)", "𝒪(n2)") , ("\\(O(n \\sqrt{n})\\)", "𝒪(n √n)") , ("\\(\\operatorname{bessel0}(10)\\approx \\frac{\\sin(10)+\\cos(10)}{\\sqrt{\\pi x}}\\)", "bessel0(x) ≈ sin(x)+cos(x) / √πx") , ("\\(O\\sqrt{n})\\)", "𝒪(√n)") , ("\\\\(O(\\\\sqrt{n})\\\\)", "𝒪(√n)") , ("\\(O(\\sqrt{nT})\\)", "𝒪(√nT)") , ("\\(O(\\sqrt{T})\\)", "𝒪(√T)") , ("\\(O(l)\\)", "𝒪(l)") , ("\\(O(l^2)\\)", "𝒪(l2    ") , ("\\(O(l \\log_{2} l)\\)", "𝒪(l log2 l") , ("\\(o(T)\\)", "o(T)") , ("\\(\\partial_t u = \\Delta u + B(u,u)\\)", "∂tu = Δu + B(u, u)") , ("\\(\\partial_t u = \\Delta u + \\tilde B(u,u)\\)", "∂tu = Δu + B̃(u, u)") , ("\\(P_B(f\\mid S)\\)", "Pb(f|S)") , ("\\(\\perp\\)", "⟂") , ("\\(^{\\perp}\\)", "⟂") , ("\\(\\Phi(10)\\)", "Φ(x)") , ("\\(\\pi_1\\)", "π1") , ("\\(\\pi\\)", "π") , ("\\(\\pi^*\\)", "π✱") , ("\\(\\Pr(\text{text} | \\alpha)\\)", "Pr(text | α)") , ("\\(P_{SGD}(f\\mid S)\\)", "PSGD(f|S)") , ("\\(p_T\\)", "pT") , ("\\(Q\\)", "Q") , ("\\(R^2\\)", "R2") , ("\\({\\raise.17ex\\hbox{~}}\\)", "~") , ("\\(rho > 0\\)", "ρ > 0") , ("\\(rho < 0\\)", "ρ < 0") , ("\\(rho\\)", "ρ") , ("\\(\\rightarrow\\)", "→") , ("\\({\\rm M}_{\\odot}\\)", "M☉") , ("\\(_r\\)", "r") , ("\\(r \\to\\infty\\)", "r → ∞") , ("\\(S'\\)", "S′") , ("\\(S' \\subset S\\)", "S′ ⊂ S") , ("\\(S^3\\)", "S3") , ("\\(S^    (0.8)\\)    ", "S✱(0.8)") , ("\\(S^(0)\\)", "S✱(0)") , ("\\(S^(0)\\)", "S✱(0)") , ("\\({\\sim}0.02 {\\rm M}_{\\mathrm{Ceres}}\\)", "~0.02MCeres") , ("\\({\\sim} 0.3 {\\rm M}_{\\odot}\\)", "~0.3M☉") , ("\\(\\sim 10^3\\)", "~103") , ("\\(\\sim5\\%\\)", "~5%") , ("\\(\\sim 6\\)", "~6") , ("\\(\\sim\\)", "~") , ("\\({\\sim}\\)", "~") , ("\\(\\sin\\Theta\\)", "sinΘ") , (" \\(-\\) ", "—") , ("\\(\\sqrt{H}\\)", "√H") , ("\\(\\sqrt{n/k}\\)", "√n⁄k") , ("\\(\\sqrt{T}\\)", "√T") , ("\\(tanh\\)", "tanh") , ("\\(TC^0\\)", "TC0") , ("\\(\\textit{Embedded agents}\\)", "Embedded agents") , ("\\(\\textit{Magic}\\)", "Magic") , ("\\(\\textit{Magic: The Gathering}\\)", "Magic: The Gathering") , ("\\(\\textit{wirehead}\\)", "wirehead") , ("\\(\textit{zero-shot}\\)", "zero-shot") , ("\\(\\text{RL}^2\\)", "RL2") , ("\\(\\Theta_{\\mathcal{H}}\\)", "Θℋ") , ("\\(\\tilde B\\)", "B̃") , ("\\(\\tilde O(n^{-1/4})\\)", "1 − 𝑂̃(n−1⁄4)") , ("\\(\\tilde{O}(\\sqrt{H^3 SAT})\\)", "𝒪(√H3SAT)") , ("\\(\\times\\)", "×") , ("\times", "×") , ("\\(\\tt KRISSBERT\\)", "KRISSBERT") , ("\\(\\tt KRISS\\)", "KRISS") , ("\\(u \\mapsto y\\)", "u ↦ y") , (" \\(\\unicode{x2014}\\) ", "—") , ("\\(\\unicode{x2014}\\)", "—") , ("\\(\\varphi\\)", "ϕ") , ("\\(W \\in {\\mathbb R}^{p \\times d}\\)", "W ∈ ℝp×d") , ("\\(W z_i\\)", "Wzi") , ("\\(X_1,\\ldots,X_p\\)", "X1,...,Xp") , ("\\(x'(t) = Ax(t) + Bu(t), y(t) = Cx(t) + Du(t)\\)", "x'(t) = Ax(t) + Bu(t), y(t) = Cx(t) + Du(t)") , ("\\((x, f(10))\\)", "(x, f(10))") , ("\\(x_i \\in {\\mathbb R}^p\\)", "xi ∈ ℝp") , ("\\(x_i = \\Sigma^{1/2} z_i\\)", "xi = ∑1⁄2zi") , ("\\(x_i = \\varphi(W z_i)\\)", "xi = ϕ(Wzi") , ("\\(x < 1\\)", "x < 1") , ("\\(x\\mathbf{1}_{x>0}\\)", "x1x>0") , ("\\(x\\Phi(10)\\)", "xΦ(x)") , ("\\(z=0\\)", "z = 0") , ("\\(z_i \\in {\\mathbb R}^d\\)", "zi ∈ ℝd") , ("\\(z_i \\in {\\mathbb R}^p\\)", "zi ∈ ℝp") , ("\\(μ\\)", "𝜇") , ("2 + 3i", "2 + 3i") , ("ℂ", "ℂ") , ("a + b i", "a + b i") , ("X = exp(Y)", "X = exp(Y)") , ("x2 + 1 = 0", "x2 + 1 = 0") , ("Y = ln(X)", "Y = ln(X)") , ("\\mathcal{O}(log n)", "𝒪(log n)") , ("\\mathrm{sinc}(ax)", "sinc(ax)") , ("a", "a") , ("b", "b") , ("c", "c") , ("i", "i") , ("n", "n") , ("p", "p") , ("c", "c") , ("x", "x") , ("Y", "Y") , ("π", "π") , ("O(log n)", "𝒪(log n)") , ("C", "C") , ("π", "π") , ("-greedy", "ε-greedy") , (" A* ", " A✱ ") -- rewrite A-star to a form which avoids lints & any Markdown interpretation , ("*", "✱") , (" TD()", " TD(λ)") -- rest: , ("", "
    ") , ("
    ", "
    ") , ("
    ", "
    ") , ("(PsycINFO Database Record", "") , ("

    . ", ".

    ") , ("

    ", "

    ") , ("

  • ", "
    • \n
  • ") , ("

    ", "

    \n
    ") , ("

    ", "

    \n

    ") , ("/>\n ", "

    \n
    ") , ("

    ", "\n

    ") , ("

    \nAbstract:T", "

    T") , ("ABSTRACT: ", "") , ("Abstract:

    ", "

    ") , ("

    ABSTRACT

    ", "") , ("

    Abstract

    ", "") , (":", ":") , (":

    ", ": ") , (" :", ":") , (" ", "") , (" <p>", "<p>") , (" <p>", "<p>") , ("<em>k</em>^2 ", "<em>k</em><sup>2</sup> ") , ("I^2 =", "I<sup>2</sup> =") , ("I(2)", "I<sup>2</sup>") , (" h2", " <em>h</em><sup>2</sup>") , ("h(2)", "<em>h</em><sup>2</sup>") , ("</h2>", "</strong></p>") , ("<h2>", "<p><strong>") , ("</h3>", "</strong></p>") , ("<h3>", "<p><strong>") , ("</p>\\n<p>", "</p> <p>") , ("<br><br>", "</p> <p>") , ("Alzheimer9", "Alzheimer'") , ("<br> <br>", "<br>") , ("1.<p>", "<p>") , ("<li> <p>➢ ", "<li>") , ("<p><ul></p>", "<ul>") , ("</strong> :</p>", "</strong>:</p>") , ("</strong> :</p> <p>", "</strong>: ") , ("</strong> :</p>\n<p>", "</strong>: ") , ("<list list-type=\"bullet\">", "<ul>") , ("</list>", "</ul>") , ("</list-item>", "</li>") , ("<list-item>", "<li>") , ("<list list-type=\"simple\">", "<ul>") , ("<p> ", "<p>") , (" <p>", "<p>") , ("</p> ", "</p>") , (" </p>", "</p>") , ("</p><br>", "</p>") , ("</p> <br>", "</p>") , ("<p><br>", "<p>") , ("<p></p>", "") , ("<p></li> </ul> </p>", "</li> </ul>") , ("</li><br>", "</li>") , ("<jats:sec>", "") , ("<jats:sec>\n ", "") , ("</p>\n\n<jats:sec>\n<strong>", "</p> <p><strong>") , ("</p>\n \n <jats:sec><p>", "</p> <p>") , ("</p>\n \n <jats:sec>\n<p>", "</p> <p>") , ("<strong>Abstract</strong>\n <jats:sec>\n<p>", "<p>") , ("<sec>", "") , ("</sec>", "") , (" </sec><br> ", "") , ("<sec><br> ", "") , ("</jats:sec>", "") , ("<jats:sec><br>", "") , ("</jats:sec><br>", "") , (" </sec> <br>", "") , ("<sec id=\"sec001\">", "") , ("<sec id=\"sec002\">", "") , ("<sec id=\"sec003\">", "") , ("<sec id=\"sec004\">", "") , ("<sec id=\"sec005\">", "") , ("<sec id=\"sec006\">", "") , ("<sec id=\"sec007\">", "") , ("<sec id=\"sec008\">", "") , ("<sec id=\"sec009\">", "") , ("<sec id=\"sec010\">", "") , ("<sec id=\"english\">", "") , ("<sec id=\"st1\">", "") , ("<sec id=\"st2\">", "") , ("<sec id=\"st3\">", "") , ("<sec id=\"sb1a\">", "") , ("<sec id=\"sb1b\">", "") , ("<sec id=\"sb1c\">", "") , ("<sec id=\"sb1d\">", "") , ("<sec id=\"sb1e\">", "") , ("<sec sec-type=\"headed\">", "") , ("<p><sec sec-type=\"headed\"></p>", "") , ("<strong>Abstract</strong>\n<jats:sec>\n<strong>", "<p><strong>") , ("</strong></p> <p>", "</strong> ") , ("", ":

    ") , ("", "") , ("<title>", "<p><strong>") , ("
    ", "") , ("

    \n\n", "

    ") , ("

    ", "

    ") , ("\n
    \n", "") , ("

    ", "

    ") , ("non–", "non-") , ("---", "—") , (" - ", "—") , (" —", "—") , ("— ", "—") , (" — ", "—") , (" -- ", "—") -- eg. 'Darknet Data Mining -- A Canadian Cyber-crime Perspective' , (" statistically insignificant", " non-statistically-significant") , ("was significantly diminished", "was statistically-significantly diminished") , ("decreased significantly", "decreased statistically-significantly") , ("is significantly better than", "is statistically-significantly better than") , (" significant increase", " statistically-significant increase") , (" significantly less", " statistically-significantly less") , (" significantly more", " statistically-significantly more") , ("boundary of significance", "boundary of statistical-significance") , ("robustly significant", "robustly statistically-significant") , (" significant trend", " statistically-significant trend") , (" non-significant trend", " non-statistically-significant trend") , (" significant difference", " statistically-significant difference") , (" significant genetic correlation", " statistically-significant genetic correlation") , (" significant allele-phenotype associations", " statistically-significant allele-phenotype associations") , (" significant association", " statistically-significant association") , (" significant correlation", " statistically-significant correlation") , ("the significant SNPs", "the statistically-significant SNPs") , (" significantly associated", " statistically-significantly associated") , (" significantly correlated", " statistically-significantly correlated") , (" significantly higher (", " statistically-significantly higher (") , (" significant interaction effect", " statistically-significant interaction effect") , (" significant effect", " statistically-significant effect") , (" significance testing", " statistical-significance testing") , ("nominally significant", "nominally statistically-significant") , (" nonsignificant result", " non-statistically-significant result") , (" significant excess", " statistically-significant excess") , (" significantly enriched", " statistically-significantly enriched") , (" significant at the ", " statistically-significant at the ") , ("statistically significant", "statistically-significant") , ("genome-wide significance", "genome-wide statistical-significance") , ("genome-wide significant", "genome-wide statistically-significant") , ("statistical significance", "statistical-significance") , ("clinical significance", "clinical-significance") , ("clinically significant", "clinically-significant") , ("

    Significance Statement

    \n

    ", "

    Significance Statement: ") , ("

    CONCLUSIONS. ", "

    Conclusions: ") , (". Conclusion: ", ".

    Conclusio: ") , (". Conclusions: ", ".

    Conclusion: ") , ("Conclusions & Significance", "Conclusion") , ("Conclusions and Significance", "Conclusion") , ("Conclusions\n

    ", "

    Conclusion: ") , ("

    Conclusions: ", "

    Conclusion: ") , ("\n Conclusion\n

    ", "

    Conclusion: ") , ("CONCLUSIONS", "Conclusion") , ("

    RESULTS. ", "

    Results: ") , (". Results: ", ".

    Results: ") , ("\n Results\n

    ", "

    Results: ") , ("

    Results: ", "

    Results: ") , ("

    Aims: ", "

    Aims: ") , ("

    BACKGROUND. ", "

    Background: ") , ("BACKGROUND", "Background") , ("

    AbstractBackground & Aims:

    \n

    ", "

    Background: ") , ("AbstractBackground and Aim", "Background & Aim") , ("

    Background. ", "

    Background: ") , ("Background\n

    ", "

    Background: ") , ("

    Background: ", "

    Background: ") , (" Interpretation. ", "

    Interpretation: ") , (" Findings. ", "

    Results: ") , ("

    METHODS. ", "

    Methods: ") , ("Methods and Findings", "Method & Findings") , ("Methods and findings", "Method & Findings") , ("Methods And Findings", "Method & Findings") , ("Methods\n

    ", "

    Method: ") , (" Methods. ", "

    Method: ") , (". Methods: ", ".

    Method: ") , (" \n Methods\n

    ", "

    Method: ") , ("

    Methods: ", "

    Method: ") , ("

    Outcomes: ", "

    Outcomes: ") , ("

    Interpretation: ", "

    Interpretation: ") , ("

    Funding: ", "

    Funding: ") , (" N1 =", " n1 =") , (" N2 =", " n2 =") , ("(N1 =", "(n1 =") , ("(N2 =", "(n2 =") , ("M full-scale", "Mfull-scale") , (" M age", " Mage") , ("( n =", "(n =") , ("N =", "n =") , ("N = ", "N = ") , ("n = ", "n = ") , (" (x) ", " (10) ") , (" (ix) ", " (9) ") , (" (viii) "," (8) ") , (" (vii) ", " (7) ") , (" (vi) ", " (6) ") , (" (v) ", " (5) ") , (" (iv) ", " (4) ") , (" (iii) ", " (3) ") , (" (ii) ", " (2) ") , (" (i) ", " (1) ") , ("(i)", "(1)") , (" i)", " (1)") , ("(ii)", "(2)") , (" ii)", " (2)") , ("(iii)", "(3)") , (" iii)", " (3)") , ("(iv)", "(4)") , (" iv)", " (4)") , ("(v)", "(5)") , (" v)", " (5)") , ("(vi)", "(6)") , (" vi)", " (6)") , ("(vii)", "(7)") , (" vii)", " (7)") , ("(viii)", "(8)") , (" viii)", " (8)") , ("(ix)", "(9)") , (" ix)", " (9)") , ("(x)", "(10)") , (" x)", " (10)") , (" a) ", " (1) ") , (" b) ", " (2) ") , (" c) ", " (3) ") , (" d) ", " (4) ") , (" e) ", " (5) ") , (" f) ", " (6) ") , (" h) ", " (7) ") -- i excluded due to ambiguity with Roman numeral i/ii/iii etc numbering , (" j) ", " (9) ") , (" k) ", " (10) ") , (" = ", " = ") , ("\n

    ", ": ") , ("< /b>", "") , ("", "") , ("", "") , ("", "") , ("Abstract
    ", "") , ("", "

    ") , ("< sub>", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , (".", "") , ("", "

    ") , ("", "

    ") , ("", "") , ("", "") , (" ", " ") -- Wikipedia {{ety}} weirdness, but just in Ancient Greek instances? , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("< /italic>", "") , ("", "") , ("< /i>", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("Abstract\n\t ", "

    ") , ("AbstractThe", "") , ("AUTHOR SUMMARY", "Author Summary") , ("

    Author Summary

    ", "

    Author Summary: ") , ("

    Author Summary

    \n

    ", "

    Author Summary: ") , ("Author Summary :", "Author Summary:") , ("strong>Author summary", "strong>Author Summary") , ("SUMMARY", "") , ("Summary", "") , ("", "") , ("

    ", ":

    ") , ("", "") , ("", "") , ("
    ", "") , ("", "") , ("", "") , ("", "") , ("\n ", "") , ("

    ABSTRACT

    ", "") , ("

    Abstract:

    ", "") , ("

    Abstract

    ", "") , ("

    SUMMARY

    ", "") , ("

    Summary/Abstract

    ", "") , ("

    Summary

    ", "") , ("

    ", "") , ("

    ", "") , ("

    Abstract: ", "

    ") , ("

    Abstract: Objective: ", "

    Objective: ") , ("

    Abstract

    ", "") , ("

    \nAuthor summary\n:

    \n

    \n", "

    \nAuthor summary\n: ") , ("

    Abstract. ", "

    ") , ("ABSTRACT

    ", "

    ") , ("ABSTRACT
    ", "") , ("Abstract", "") , ("Abstract: ", "") , ("Abstract: ", "") , ("Abstract:

    ", "

    ") , ("Abstract
    ", "") , ("Abstract\n \n ", "") , ("Abstract\n

    ", "

    ") , ("SUMMARY", "") , ("\n", "") , ("▪ Abstract", "") , ("AIM:", "Aim:") , ("METHODS:", "Method:") , ("RESULTS:", "Results:") , ("CONCLUSION:", "Conclusion:") , ("AIM:", "Aim:") , ("METHODS:", "Method:") , ("RESULTS:", "Results:") , ("CONCLUSION:", "Conclusion:") , ("Background and Aims", "Background & Aims") , ("\nHighlights: ", "\nHighlights: ") , ("\nBackground: ", "\nBackground: ") , ("\nAbstract: ", "\nAbstract: ") , ("

    Abstract: ", "

    ") , ("\nContext: ", "\nContext: ") , ("Purpose\n

    ", "

    Purpose: ") , ("\nPurpose: ", "\nPurpose: ") , ("

    Purpose. ", "\nPurpose: ") , ("\nRationale: ", "\nRationale: ") , ("ANIMALS: ", "Animals: ") , ("OBJECTIVE: ", "Objective: ") , ("METHOD: ", "Method: ") , ("RESULTS: ", "Results: ") , ("CONCLUSIONS: ", "Conclusion: ") , ("CLINICAL RELEVANCE: ", "Clinical Relevance: ") , ("PROCEDURES: ", "Procedures: ") , ("

    Setting & Participants:

    ", "

    Setting & Participants: ") , ("OBJECTIVE

    \n", "Objective: ") , ("METHOD

    \n", "Method: ") , ("RESULTS

    \n", "Results: ") , ("CONCLUSIONS

    \n ", "Conclusion: ") , ("CLINICAL RELEVANCE

    \n ", "Clinical Relevance: ") , ("

    OBJECTIVE

    \n

    ", "

    Objective: ") , ("

    METHOD

    \n

    ", "

    Method: ") , ("

    RESULTS

    \n

    ", "

    Results: ") , ("

    CONCLUSIONS

    \n

    ", "

    Conclusion: ") , ("

    CLINICAL RELEVANCE

    \n

    ", "

    Clinical Relevance: ") , ("\nObjective: ", "\nObjective: ") , ("\nObjectives: ", "\nObjectives: ") , ("\nQuestion: ", "\nQuestion: ") , ("\nDescription: ", "\nDescription: ") , ("Design and

    \n

    Methods: ", "

    Method: ") , ("\nDesign: ", "\nMethod: ") , ("\nMethods: ", "\nMethod: ") , ("\nDesign and Methods: ", "\nMethod: ") , ("Materials and Methods", "Method") , ("Materials and methods", "Method") , ("\nSetting: ", "\nSetting: ") , ("\nParticipants: ", "\nParticipants: ") , ("\nMeaning: ", "\nMeaning: ") , ("Setting and Participants", "Setting & Participants") , ("\nDesign, Setting, and Participants: ", "\nMethods, Setting, & Participants: ") , ("\nIntervention: ", "\nIntervention: ") , ("\nData Sources: ", "\nData Sources: ") , ("\nMain Outcomes & Measures: ", "\nMain Outcomes & Measures: ") , ("Main Outcomes and MeasuresMain Outcomes & MeasuresMeasurements: ") , (". Results. ", ".

    Results: ") , ("\nResults: ", "\nResults: ") , ("\nSignificance: ", "\nSignificance: ") , (". Conclusions. ", ".

    Conclusion: ") , ("\nConclusion: ", "\nConclusion: ") , ("\nConclusions: ", "\nConclusion: ") , ("\nConclusions & Relevance: ", "\nConclusion & Relevance: ") , ("\nIntroduction: ", "\nBackground: ") , ("\nTrial Registration: ", "\nTrial Registration: ") , ("

    Highlights

    \n

    ", "

    Highlights: ") , ("

    Background

    \n

    ", "

    Background: ") , ("

    Abstract

    \n

    ", "

    Abstract: ") , ("

    Context

    \n

    ", "

    Context: ") , ("

    Purpose

    \n

    ", "

    Purpose: ") , ("

    Rationale

    \n

    ", "

    Rationale: ") , ("

    Objective

    \n

    ", "

    Objective: ") , ("

    Objectives

    \n

    ", "

    Objectives: ") , ("

    Question

    \n

    ", "

    Question: ") , ("

    Description

    \n

    ", "

    Description: ") , ("

    Design

    \n

    ", "

    Method: ") , ("

    Methods

    \n

    ", "

    Method: ") , ("

    Setting

    \n

    ", "

    Setting: ") , ("

    Participants

    \n

    ", "

    Participants: ") , ("

    Meaning

    \n

    ", "

    Meaning: ") , ("

    Design, Setting, and Participants

    \n

    ", "

    Methods, Setting, & Participants: ") , ("Design, Setting, and Participants", "Methods, Setting, & Participants") , ("

    Intervention

    \n

    ", "

    Intervention: ") , ("

    Data Sources

    \n

    ", "

    Data Sources: ") , ("

    Main Outcomes & Measures

    \n

    ", "

    Main Outcomes & Measures: ") , ("

    Measurements

    \n

    ", "

    Measurements: ") , ("

    Results

    \n

    ", "

    Results: ") , ("

    Significance

    \n

    ", "

    Significance: ") , ("

    Conclusion

    \n

    ", "

    Conclusion: ") , ("

    Conclusions

    \n

    ", "

    Conclusion: ") , ("

    Conclusions & relevance

    \n

    ", "

    Conclusion & Relevance: ") , ("

    Conclusions & Relevance

    \n

    ", "

    Conclusion & Relevance: ") , ("

    Trial Registration

    \n

    ", "

    Trial Registration: ") , ("
    ", "") , ("

    ", "

    ") , ("Background:", "Background:") , ("Objective: ", "Objective:") , ("Results: ", "Results:") , ("Conclusions:", "Conclusion:") , ("Originality/value", "Conclusion:") , ("Conclusions and Relevance", "Conclusion:") , ("Conclusions and relevance", "Conclusion:") , ("Conclusions and Clinical Relevance", "Conclusion:") , ("Clinical Relevance", "Conclusion:") , ("CLINICAL RELEVANCE

    ", "

    Conclusion: ") , ("\91Keywords: ", "\91Keywords: ") , ("</i></b>", "") , ("<b><i>", "") , ("acc.:", "accuracy:") , (" m/s", " m⁄s") , ("1/3-approximation", "1⁄3-approximation") , (" 1/100 ", " 1⁄100 ") , ("~1/250", "~1⁄250") , (" 2/3 ", " 2⁄3 ") , (" 3/3 ", " 3⁄3 ") , (" 1/10 ", " 1⁄10 ") , (" (4/8 ", " (4⁄8 ") , (" (5/8 ", " (5⁄8 ") , (" 1/2 ", " 1⁄2 ") , (" 1/3 ", " 1⁄3 ") , (" 1/4 ", " 1⁄4 ") , (" 4/5 ", " 4⁄5 ") , (" 5/8 ", " 5⁄8 ") , (" 5/9 ", " 5⁄9 ") , (" 6/13 ", " 6⁄13 ") , (" 7/13 ", " 7⁄13 ") , (" 8/13 ", " 8⁄13 ") , (" 9/13 ", " 9⁄13 ") , (" 15/16 ", " 15⁄16 ") , (" 5/16 ", " 5⁄16 ") , (" 15/20 ", " 15⁄20 ") , (" (23/96) ", " (23⁄96) ") , (" (24/50) ", " (24⁄50) ") , (" (30/96) ", " (30⁄96) ") , (" (35/96) ", " (35⁄96) ") , (" (39/50) ", " (39⁄50) ") , (" (41/50) ", " (41⁄50) ") , (" (43/50) ", " (43⁄50) ") , (" (48/96) ", " (48⁄96) ") , (" (50/96) ", " (50⁄96) ") , (" (6/96), ", " (6⁄96), ") , (" (68/96) ", " (68⁄96) ") , (" (90/96) ", " (90⁄96) ") , (" 11/90 ", " 11⁄90 ") , (" 33/96 ", " 33⁄96 ") , (" 42/50 ", " 42⁄50 ") , ("(11/31)", "(11⁄31)") , ("(9/11)", "(9⁄11)") , ("(2/7)", "(2⁄7)") , ("(28/31)", "(28⁄31)") , ("(9/10)", "(9⁄10)") , ("10(-10)", "10−10") , ("10(-11)", "10−11") , ("10(-13)", "10−13") , ("10(-15)", "10−15") , ("10(-19)", "10−19") , ("10(-26)", "10−26") , ("10(-3)", "10−3") , ("10(-4)", "10−4") , ("10(-5)", "10−5") , ("10(-6)", "10−6") , ("10(-7)", "10−7") , ("10(-8)", "10−8") , ("10(-9)", "10−9") , ("10(-)(3)", "10−3") , ("10(-)(4)", "10−4") , ("10(-)(5)", "10−5") , ("10(-)(6)", "10−6") , ("10(-)(7)", "10−7") , ("10(-)(8)", "10−8") , ("10(-)(9)", "10−9") , ("10(-)(10)", "10−10") , ("10(-16)", "10−16") , ("10(-33)", "10−33") , ("10(-14)", "10−14") , ("R (2) ", "R2 ") , ("CO(2)", "CO2") , ("2^n-1", "2n−1") , ("2^n-1)", "2n−1)") , ("d(-1)", "d−1") , ("min(-1)", "min−1") , (" = .", " = 0.") , ("=−", " = −") , (" gf ", " gf ") , (" gc ", " gc ") , ("( g = ", "(g = ") , (" g-factor", " g-factor") , ("h2", "h2") , ("h2SNP", "hSNP2") , ("h2SNP", "hSNP2") , ("ηp2", "ηp2") , ("h2", "h2") , ("|rA|", "|rA|") , ("|rE|", "|rE|") , ("R 2", "R2") , ("r g =", "rg =") , ("r g", "rg") , ("r(g)", "rg") , (" rg:", " rg:") , (" rg ", " rg ") , (" rg=", " rg = ") , (" rg = ", " rg = ") , ("(rg)", "(rg)") , ("(rg", "(rg") , ("|rg|=", "|rg| = ") , ("U_d=", "Ud") , ("U_d>", "Ud > ") , ("U_d>", "Ud > ") , ("U_d<", "Ud < ") , ("U_d<", "Ud < ") , ("U_d~", "Ud ~ ") , ("->", "→") , (" ≥ .", " ≥ 0.") , (" >> ", " ≫ ") , (" << ", " ≪ ") , (" r = ", " r = ") , (" r=", "r = ") , (" r>", "r > ") , (" r>", "r > ") , (" r<", " r < ") , ("r≥", "r ≥ ") , ("r≤", "r ≤ ") , ("≤n≤", " ≤ n ≤ ") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("", "") , ("​", "") , ("", "") , ("\8203", "") , ("", "") , ("", "") , (" .", ".") , ("", "") , ("", "") , ("beta=", "β = ") , (" = 0", " = 0") , ("cm3", "cm3") , (" cm(3)", " cm3") , ("R2 <", "R2 <") , ("R2 ", "R2 ") , (" R2", " R2") , (" R(2)", " R2") , ("top-k", "top-k") , ("Top-k", "Top-k") , ("Top-K", "Top-k") , (" z = ", " z = ") , ("z-score", "z-score") , ("Z-score", "z-score") , ("z-scores", "z-scores") , (" z-latent", "z-latent") , (" w-latent", "w-latent") , (" < .0", " < 0.0") , (" 5e-8/53", "(5 × 10−8) / 53") -- https://www.biorxiv.org/content/10.1101/2023.09.10.557084v1.full.pdf#page=2 , (" p &gt; ", " p > ") , (" p &lt; ", " p < ") , ("P < ", "p < ") , ("p< ", "p < ") , ("p<\\/em>=", "p = ") , ("P = ", "p = ") , ("P values", "p-values") , (" p value", " p-value") , (" P < .", " p < 0.") , (" P <", " p <") , (" P <", " p <") , ("≤p≤", " ≤ p ≤ ") , ("Cohen’s d", "Cohen’s d") , ("Cohen's d", "Cohen’s d") , (" d = ", " d = ") , ("( d = ", "(d = ") , ("(d = ", "(d = ") , ("(d < ", "(d < ") , ("(d > ", "(d > ") , ("(rs)", "(rs)") , ("(r=", "(r = ") , ("(R=", "(r = ") , ("(R = ", "(r = ") , ("(r = ", "(r = ") , ("(N = ", "(N = ") , ("(n = ", "(n = ") , ("(n=", "(n = ") , ("(N=", "(N = ") , ("(r>", "9r > ") , (" N ~ ", " n ~ ") , ("( N = ", "(n = ") , ("( n = ", "(n = ") , ("( ns = ", "(ns = ") , ("( n = ", "(n = ") , (" n≥", " n≥") , ("n = ", "n = ") , ("(minimum p ", "(minimum p ") , ("P = 0", "p = 0") , ("(p = ", "(p = ") , (" p<", " p < ") , (" p>", " p > ") , (" p>e;", " p ≥ ") , (" p<e;", " p ≤ ") , (" P<", " p < ") , (" P>", " p > ") , (" P>e;", " p ≥ ") , (" P<e;", " p ≤ ") , ("p = .", "p = 0.") , ("p < .", "p < 0.") , (" n-vertex", " n-vertex") , ("(N~", "(n ≈ ") , (" n)", " n)") , (" n ", " n ") , ("(n ", "(n ") -- it's safe to replace 'n', but not 'N' because 'N' is used fairly often in chemistry for nitrogen, and chemical names often have parentheses, so we can't search-and-replace it in general , (" N=", " N = ") , (" N = ", " N = ") , (" n = ", " n = ") , ("(N =", "(N =") , ("(p=", "(p = ") , (" n=", " n = ") , ("( n=", "( n = ") , ("Neff ", "neffective ") , ("Neffective", "neffective") , ("Neffective=", "neffective = ") , ("Padjusted", "padjusted") , ("Padjusted=", "padjusted = ") , (" n-gram", " n-gram") , (" N-gram", " n-gram") , (" k > ", " nk > ") , (" k > ", " k > ") , (" N > ", " n > ") , (" N > ", " n > ") , (" Neffective", " Neffective") , (" N-weighted", " N-weighted") , (" n-back", " n-back") , ("N-back", "N-back") , ("(P &lt;", "(p <") , ("p < .05", "p < 0.05") , (" > .05", " > 0.05") , (" > .01", " > 0.01") , (" -> ", " → ") , ("( p", "(p") , ("p = 0", "p = 0") , (" P=", " p = ") , (" P = ", " p = ") , ("(P = ", "(p = ") , (" p = ", " p = ") , (" p=", " p = ") , (" P<", " p < ") , ("P ≤ ", "p ≤ ") , ("(P<", "(p < ") , ("(P <", "(p <") , ("0,1^n", "{0,1}n") , (" n<", " n < ") , ("(n = ", "(n = ") , ("(n = ", "(n = ") , (" k=2", " k = 2") , ("(p < .", "(p < 0.") , (" r ≥ 0.", " r ≥ 0.") , (" P(t) ", " P(t) ") , (" t ", " t ") , (" t test", " t-test") , ("(P≤", "(p ≤ ") , ("(P<", "(p < ") , ("(P>", "(p > ") , ("(P <", "(p <") , ("(P >", "(p >") , ("(p≤", "(p ≤ ") , ("> >0", "≫0") , ("(p<", "(p < ") , ("(p>", "(p > ") , ("(p <", "(p <") , ("(p >", "(p >") , (" p <", " p <") , (" p >", " p >") , (" P < ", " p < ") , (" p < ", " p < ") , (" p<", " p < ") , (" p<.", " p < 0.") , ("(P < 0.", "(p < 0.") , ("(P < .", "(p < 0.") , ("(P < ", "(p <") , ("(P=", "(p = ") , ("P-value", "p-value") , ("p-value", "p-value") , (" p-level ", " p-level ") , ("P for linear trend", "plinear trend") , ("P for quadratic trend", "pquadratic trend") , ("(95% CI, ", "(95% CI: ") , ("level-k ", "level-k ") , (" level-k", " level-k") , ("b = ", "β = ") , (" ", " ") , (" LaTeX", " LaTeX") , (">LaTeX", ">LaTeX") , (" TeX", " TeX") , (">TeX", ">TeX") , ("DALL-E", "DALL·E") -- many uses of 'approximately' are weasel-wordy which add nothing whatsoever semantically, so we can drop the '~': , ("~linearly", "linearly") , ("~every", "every") , ("~isometrically", "isometrically") , ("~solving", "solving") , ("~simulate", "simulate") , ("~this", "Approximately this") , ("~equivalent", "equivalent") , ("~the", "the") , ("~one ", "~1") , (" one tenth ", " 1⁄10th") , (" two thirds ", " 2⁄4rds") , ("~zero ", "~0") , ("~identical", "near-identical") , ("approximately ", "~") , ("Approximately ", "~") , ("approx ", "~") , ("∼", "~") , ("GxE", "G×E") , (" 10x", " 10×") , (" 100x", " 100×") , (" 2x", " 2×") , (" 3x", " 3×") , ("~twice", "~2×") , ("five times", "5×") , ("fifty-five years", "55 years") , ("Fifty-five years", "55 years") , ("

     ", "

    ") , ("+/-", "±") , (" +- ", "±") , ("~", "~") , ("one-third", "1⁄3rd") , ("one-quarter", "1⁄4th") , ("three and a half", "3.5") , (" 11th", " 11th") , (" 12th", " 12th") , (" 13th", " 13th") , (" 14th", " 14th") , (" 15th", " 15th") , (" 16th", " 16th") , (" 17th", " 17th") , (" 18th", " 18th") , (" 19th", " 19th") , (" 20th", " 20th") , (" 21st", " 21st") , ("\"21st", "\"21st") , ("early-12th", "early-12th") , ("mid-21st", "mid-21st") , ("early-20th-century", "early-20th-century") , ("25th", "25th") , (">15th", ">15th") , ("mid-17th", "mid-17th") , ("mid-16th", "mid-16th") , (">21st", ">21st") , ("–19th", "–19th") , ("late-20th", "late-20th") , ("64,000th", "64,000th") , ("(5th", "(5th") , ("(12th", "(12th") , (" 14th ", " 14th ") , (" 22nd", " 22nd") , (" 30th", " 30th") , (" 50th", " 50th") , (" 1st", " 1st") , (" 2nd", " 2nd") , (" 3rd", " 3rd") , (" 5th", " 5th") , (" 4th", " 4th") , ("", "") , ("ml-1", "ml−1") , ("10(9)", "109") , ("(10(9))", "(109)") , ("kg/m(2)", "kg⁄m2") , ("kg/m2", "kg⁄m2") , ("kg/m^2", "kg⁄m2") , ("cd/m(2)", "cd/m2") , ("Cmax", "Cmax") , ("", "") , ("Hazard Ratio", "hazard ratio") , ("tertile", "third") , ("Prof. ", "Professor ") , (" et al ", " et al ") -- et al: try to ensure no linebreaking of citations , (" et al. ", " et al ") , (" et al., ", " et al ") , ("i.e.,", "ie.") , ("(ie, ", "(ie. ") , ("(ie ", "(ie. ") , ("(i.e.,", "(ie.") , ("(i.e.", "(ie.") , ("e.g.,", "eg.") , (" e.g.", " eg.") , ("(e.g.", "(eg.") , ("(eg ", "(eg. ") , (" eg ", " eg. ") , ("eg., ", "eg. ") , ("e.g., ", "eg. ") , ("e.g. ", "eg. ") , (" back-prop", " backprop") , ("Twitter (now X)", "Twitter") , ("labell", "label") , ( "optimise", "optimize") , ( "optimisation", "optimization") , ("organise", "organize") , ("totall ", "total ") , ("minimis", "minimiz") , ("maximis", "maximiz") , ("heterogenous", "heterogeneous") , (" Homo floresiensis", " Homo floresiensis") , (" Bacopa monnieri", " Bacopa monnieri") , ("(Bacopa monnieri)", "(Bacopa monnieri)") , (" Bacopa Monnieri", " Bacopa monnieri") , ("Streptococcus sanguis", "Streptococcus sanguis") , ("S. sanguis", "S. sanguis") , ("S. mutans", "S. mutans") , (" Streptococcus mutans", "Streptococcus mutans") , ("(Canis Familiaris)", "(Canis Familiaris)") , ("(Canis familiaris)", "(Canis familiaris)") , (" Canis familiaris", " Canis familiaris") , (" Escherichia coli", " Escherichia coli") , ("Escherichia coli ", " Escherichia coli ") , (" E. coli", " E. coli") , ("E. coli ", " E. coli ") , (" Saccharomyces cerevisiae", " Saccharomyces cerevisiae") , ("(Calcarius lapponicus) ", "(Calcarius lapponicus) ") , ("(Corvus brachyrhynchos) ", "(Corvus brachyrhynchos) ") , ("(Felis Catus)", "(Felis Catus)") , ("(Felis catus)", "(Felis catus)") , ("(Felis silvestris catus)", "(Felis silvestris catus)") , ("(Panthera leo)", "(Panthera leo)") , ("(Macaca fascicularis) ", "(Macaca fascicularis) ") , ("(Orcinus orca) ", "(Orcinus orca) ") , ("(Plectrophenax nivalis)", "(Plectrophenax nivalis)") , ("(Poecilia reticulata)", "(Poecilia reticulata)") , (" Pan Troglodytes", " Pan Troglodytes") , ("(Bacopa monniera)", "(Bacopa monniera)") , ("(Canis latrans)", "(Canis latrans)") , ("(Herpestes ichneumon)", "(Herpestes ichneumon)") , ("(Lynx canadensis)", "(Lynx canadensis)") , ("(Mammuthus primigenius)", "(Mammuthus primigenius)") , ("(Pan Troglodytes)", "(Pan Troglodytes)") , ("(Psilocybe cubensis)", "(Psilocybe cubensis)") , ("(Rattus norvegicus) ", "(Rattus norvegicus) ") , ("(Mus musculus)", "(Mus musculus)") , ("(Taxidea taxus)", "(Taxidea taxus)") , ("(Peromyscus leucopus)", "(Peromyscus leucopus)") , ("(Globicephala melas)", "(Globicephala melas)") , (" Arabidopsis thaliana", " Arabidopsis thaliana") , ("(Heterocephalus glaber)", "(Heterocephalus glaber)") , ("(Drosophila melanogaster", "(Drosophila melanogaster") , (" Drosophila melanogaster", " Drosophila melanogaster") , (" Arabidopsis Thaliana", " Arabidopsis Thaliana") , ("C. elegans", "C. elegans") , (" Caenorhabditis elegans", " Caenorhabditis elegans") , (" C. elegans", " C. elegans") , (" Bacillus subtilis", " Bacillus subtilis") , (" Octopus insularis", " Octopus insularis") , (" T. gondii", " T. gondii") , (" Equus ", " Equus ") , ("Lempel–Ziv–Markov", "Lempel-Ziv-Markov") , ("genetically informative", "genetically-informative") , ("Genetically Informative", "Genetically-Informative") , ("learn-ing", "learning") , ("Per- formance", "Performance") , ("per- formance", "performance") , ("Swed-ish", "Swedish") , (" itis ", " it is ") , (" k ", " k ") , (" k-shot", " k-shot") , (" k-nearest", " k-nearest") , ("one- or five-shot", "one-shot or five-shot") , ("lan- guage", "language") , ("pro-posed", "proposed") , ("case- control", "case-control") , ("high- g", "high-g") , ("semi– structured", "semi-structure") , ("ap-proach", "approach") , ("AsRL", "As RL") , ("spaceusing", "space using") , ("withits", "with its") , ("languagemodel", "language model") , ("questiongeneration", "question generation") , ("genomewide", "genome-wide") , ("regularise", "regularize") , (" standardised", " standardized") , (" Standardised", " Standardized") , (" memoise", " memoize") , (" hypothesise" ," hypothesize") , ("factorise" ,"factorize") , ("initialis", "initializ") , (" signalling", " signaling") , ("focussed", "focused") , ("wethen", "we then") , ("successfullylearns", "successfully learns") , ("n-of-1", "n-of-1") , ("“ ", "“") , ("% ,", "%,") , (") ,", "),") , ("\t", "") , ("\t\t", "") , ("\t\t\t\t\t", "") , ("long- term", "long-term") , ("long -term", "long-term") , ("resp. ", "respectively ") , ("longstanding", "long-standing") , ("value- added", "value-added") , ("dis -ambiguate", "disambiguate") , ("chrono- logical", "chronological") , ("co- occurring", "co-occurring") , ("CLIP- based", "CLIP-based") , ("zero- and few-shot", "zero-shot & few-shot") , ("within- and cross", "within & cross") , ("self- and parent-reported", "self & parent-reported") , ("self- and psychiatrist-rated", "self-rated & psychiatrist-rated") , ("full- and half-sibling", "full & half-sibling") , ("full- and half-sibling pairs", "full & half-sibling pairs") , ("Human–Cat", "Human-Cat") , (" wk ", " week ") , ("D1 receptor- and dopamine D2 receptor-expressing", "D1 receptor-expression & dopamine D2 receptor-expressing") , ("sex- and age-matched", "sex & age-matched") , ("signifi- cantly", "significantly") , ("be- tween", "between") , ("self– and informant", "self & informant") , ("quasi–causal", "quasi-causal") , ("self–reported", "self-reported") , ("peer–reported", "peer-reported") , ("profit-able", "profitable") , ("real- world", "real-world") , ("ap- proach", "approach") , (" touse", " to use") , (" Copyright

    ", "") , (" GPT2", " GPT-2") , (" GPT3", " GPT-3") , ("GPT 4", "GPT-4") , ("GPT 2", "GPT-2") , ("GPT 3", "GPT-3") , ("GPT-4V", "GPT-4-V") , (" target=\"_blank\"", "") , ("
    ", "") , (" < jats:sub>", "") , ("", "") , ("\n \n ", "\n") , ("\n k\n ", "k") , ("\n –6\n ", "–6") , ("\n in vitro\n", " in vitro") , ("\n R\n", "R") , ("_X_s", "Xs") , ("x-axis", "x-axis") , ("y-axis", "y-axis") , ("z-axis", "z-axis") , (" metre", " meter") , (" centre ", " center ") , (" Centre ", " Center ") , ("multicentre", "multicenter") , ("Multicentre", "Multicenter") , ("categoris", "categoriz") , ("Yann Le Cun", "Yann LeCun") , ("Oliver Bryne", "Oliver Byrne") , ("UCF-101", "UCF101") , ("WikiText103", "WikiText-103") , (" an universe", " a universe") , ("eyetracking", "eye tracking") , ("PsychINFO", "PsycINFO") , ("teachinga", "teaching a") , ("introducea", "introduce a") , ("andevaluate", "and evaluate") , ("Norbert Weiner", "Norbert Wiener") , ("mulitple", "multiple") , (" a improvement", " an improvement") , (" a enrichment", " an enrichment") , (" a insertional", " an insertional") , (" a overlap", " an overlap") , (" a audio", " an audio") , (" a interaction", " an interaction") , ("non-significant", "non-statistically-significant") , ("non-significance", "non-statistical-significance") , ("statistically statistically-significant", "statistically-significant") , ("GW significance", "genome-wide statistical-significance") , ("Most of the significance for", "Most of the statistical-significance for") , ("a significance test", "a statistical-significance test") , (" significance test", " statistical-significance test") , ("The significance of melatonergic", "The importance of melatonergic") , (", with significance for the ", ", with implications for the") , ("variants of uncertain significance", "variants of uncertain importance") , ("philosophical significance", "philosophical importance") , ("study-wide significance", "study-wide statistical-significance") , (" significance threshold", " statistical-significance threshold") , (" significance measures", " statistical-significance measures") , ("but not significance criteria", "but not statistical-significance criteria") , ("unique biological significance of", "unique biological importance of") , ("epidemiological significance", "epidemiological importance") , ("assess its significance", "assess its importance") , ("nominal significance level", "nominal statistical-significance level") , ("strict significance level", "strict statistical-significance level") , ("levels of significance", "levels of statistical-significance") , ("Excess significance", "Excess statistical-significance") , ("their scientific significance", "their scientific importance") , ("behavioral significance", "behavioral importance") , (" behaviour", " behavior") , (" neighbour", " neighbor") , (" practise", " practice") , (" aesthetic", " esthetic") , (" Utilisation", " Utilization") , (" utilise", "use") , (" utilize", "use") , (" utilising", " using") , (" utilizing", " using") , (" utilisation", " usage") , (" utilization", " usage") , (" summarising", " summarizing") , ("factorisation", "factorization") , ("synthesising", "synthesizing") , (" rivall", " rival") , ("hospitalisation", "hospitalization") , ("apriori", "a priori") , ("nonstationary", "non-stationary") , ("posttraumatic", "post-traumatic") , (" localis", " localiz") , ("antisociality", "anti-sociality") , ("capitalise ", "capitalize ") , ("capitalised", "capitalized") , ("capitalisation", "capitalization") , ("capitalising", "capitalizing") , ("capitalises", "capitalizes") , ("crystallised", "crystallized") , ("discretise", "discretize") , ("memorisation", "memorization") , ("Memorisation", "Memorization") , ("nonnatural", "unnatural") , ("risktaking", "risk-taking") , ("assocation", "association") , ("foscussing", "focusing") , ("areused", "are used") , ("insteaduse", "instead use") , ("humanlike", "human-like") , ("nevermind", "never mind") , ("parametris", "parameteriz") , ("parameterise", "parameterize") , ("normalis", "normaliz") , ("generalizt", "generalist") , ("generalise", "generalize") , ("generalisi", "generalizi") , ("generalisa", "generaliza") , ("Generalisation", "Generalization") , (" visualisation", " visualization") , (" disincentivis", " disincentiviz") , (" incentivis", " incentiviz") , (" randomis", " randomiz") , (" Randomis", " Randomiz") , ("stabilising", "stabilizing") , ("stabilisation", "stabilization") , ("benefitt", "benefit") , ("noninsight", "non-insight") , ("personalised ", "personalized ") , ("favouritism", "favoritism") , ("schizohrenia", "schizophrenia") , ("quantitive", "quantitative") , ("non-institutionalised", "non-institutionalized") , (" datacentre", " datacenter") , ("nonadherence", "non-adherence") , ("Langrangians", "Lagrangians") , ("regularisation", "regularization") , ("urbanisatio", "nurbanization") , ("organisation", "organization") , ("diarisation", "diarization") , (" tokenisation", " tokenization") , ("vectorised", "vectorized") , ("nonspecifically", "non-specifically") , ("attentionless", "attention-less") , ("disfavour", "disfavor") , (" homogeneous", " homogenous") , (" Homogeneous", " Homogenous") , ("nonpredictive", "non-predictive") , ("subquadratic-time", "sub-quadratic-time") , ("nonimmersive", "non-immersive") , ("webscale", "web-scale") , ("tobenchmarks", "to benchmarks") , ("fertilised", "fertilized") , ("systematise", "systematize") , ("contextualise", "contextualize") , ("metabolising", "metabolizing") , ("polygeneti", "cpolygenic") , ("submodels", "sub-models") , ("Nonblind", "Non-blind") , (" colour", " color") , (" Colour", " Color") , (" UNet", " U-Net") , ("PsycArticles", "PsycARTICLES") , ("behaviour", "behavior") , (" rigour", " rigor") , ("de Novo", "De Novo") , ("thususe", "thus use") , ("small saple", "small sample") , (" model s ", " model’s ") , (" ofsmoking", " of smoking") , (" U.S.", " US") , (" u.s. ", " U.S. ") , (" ofthe", " of the") , (" ofdata", " of data") , ("onCIFAR", "on CIFAR") , ("Lee Sidol", "Lee Sedol") , ("DeepBlue", "Deep Blue") , ("thatuse", "that use") , ("paperuses", "paper uses") , ("Weuse", "We use") , ("weuse", "we use") , ("nuture", "nurture") , ("\8201", " ") , ("ADE20k", "ADE20K") , (" XSUM", " XSum") , (" Xsum", " XSum") , (" xsum", " XSum") , (" mid ", " mid-") , ("CityScapes", "Cityscapes") , ("Fr’echet", "Fréchet") , ("Frechet", "Fréchet") , ("h20ttps://", "https://") , ("p16INK4a", "p16INK4a") , ("mm(2)", "mm2") , ("²", "2") , ("₂", "2") , ("\173", "") -- all web browsers now do hyphenation so strip soft-hyphens , ("\8208", "-") -- remove "‐" HYPHEN (yes, really. "-" is "HYPHEN-MINUS") , ("‰", "%") -- PER MILLE SIGN https://en.wikipedia.org/wiki/Per_mille - only example I've ever seen was erroneous , ("FROH", "FROH") , (" Ne ", " Ne ") , (" CO2", " CO2") , (" O2", " O2") , ("NAD+", "NAD⁺") , (" controled", " controlled") , ("amp#x02019;", "’") , ("Oamp#x02019;", "O’") , ("amp#x000ED;", "í") , ("amp#x000E9", "é") , ("amp#x000E9,", "é") , ("amp#x00142;", "ł") , ("amp#x000F6;", "ö") , ("amp#x000E9;", "é") , (" â\200\224 ", "—") , ("\\aka", "a.k.a.") , ("\\xmlpi{\\\\}", "") , (" three ", " 3 ") , (" Three ", " 3 ") , (" four ", " 4 ") , (" Four ", " 4 ") , (" five ", " 5 ") , (" Five ", " 5 ") , (" six ", " 6 ") , (" Six ", " 6 ") , (" seven ", " 7 ") , (" Seven ", " 7 ") , (" eight ", " 8 ") , (" Eight ", " 8 ") , (" nine ", " 9 ") , (" Nine ", " 9 ") , (" ten ", " 10 ") , (" Ten ", " 10 ") , (" eleven", " 11") , (" Eleven", " 11") , (" twelve", " 12") , (" Twelve", " 12") , (" thirteen", " 13") , (" Thirteen", " 13") , (" fourteen", " 14") , (" Fourteen", " 14") , (" fifteen", " 15") , (" Fifteen", " 15") , (" sixteen", " 16") , (" Sixteen", " 16") , (" seventeen", " 17") , (" Seventeen", " 17") , (" eighteen", " 18") , (" Eighteen", " 18") , (" nineteen", " 19") , (" Nineteen", " 19") , (" twenty", " 20") , (" Twenty", " 20") , ("twenty six", "26") , ("
    ", "
    ") , ("
    ", "
    ") , ("", "", "Summary:\8195", "") , ("Summary:", "") , ("", "") , ("ad", "AD") , ("bc", "BC") , (" Imagenet-1k", " ImageNet-1k") , ("â\128", "’") , ("ff", "ff") , ("ffl", "ffl") , ("fi", "fi") , ("fl", "fl") , ("ſt", "ft") , ("ffi", "ffi") , (",”", "”,") , (",’", "’,") , (" (”", " (“") , (". . . ,", "…,") , (", … ,", ", …,") , ("\8236", "") -- POP DIRECTIONAL FORMATTING , ("\8234", "") -- LEFT-TO-RIGHT EMBEDDING , ("\160", " ") -- NO BREAK SPACE , ("�", "") -- REPLACEMENT CHARACTER ] -- regexps we need to run *before* we run the bulk of the fixed-string -- tests: unique keys, valid regexp keys htmlRewriteRegexpBefore = [ ("\\(JEL [A-Z][0-9][0-9]+\\)\\.?", "") , (" \\(JEL [A-Z][0-9][0-9], .* [A-Z][0-9][0-9]\\)", "") -- rm AERA classification tags they stick into the Crossref abstracts; must be run *before* because JEL codes like 'R2' or 'L2' will be rewritten into sub/superscript under the assumption they are the scientific concepts, which then breaks the JEL match. ]