@mailwoman/neural-weights-it-it 9.2.0 → 9.4.0

package/README.md

@@ -5,6 +5,12 @@ it-IT weights overlay for [mailwoman](https://mailwoman.ai).
 **Data-only.** Declares `mailwoman.baseWeights` and shares the base model and tokenizer with
 `@mailwoman/neural-weights-en-us`; what it adds is `pair-index-it.bin`.
 
+It also ships the four evidence lexicons the base model was trained against — `anchor-lexicon-v1.json`,
+`country-surface-lexicon-v1.json`, `street-type-lexicon-v3.json`, `locality-surface-lexicon-v7.json` — and
+its `model-card.json` carries the base card's `requires` block, so a consumer runs the same channels the
+board grades. A data-only overlay without them ran gazetteer, country and both evidence channels OFF
+against a model trained with them (#2115).
+
 ```sh
 npm install @mailwoman/neural-weights-it-it
 ```

package/anchor-lexicon-v1.json

@@ -0,0 +1,681 @@
+{
+	"version": 1,
+	"generated_by": "scripts/build-gazetteer-anchor-lexicon.mjs (source: @mailwoman/codex)",
+	"feature_dim": 5,
+	"slots": ["country", "region", "po_box", "cedex", "homograph"],
+	"bits": {
+		"country": 1,
+		"region": 2,
+		"po_box": 4,
+		"cedex": 8,
+		"homograph": 16
+	},
+	"max_ngram": 7,
+	"rules": {
+		"word_norm": "per whitespace-word: strip leading/trailing chars that are not Unicode letters/digits (keep internal: 'timor-leste', 'u.s.a'); rejoin single-spaced. Applied to BOTH entry keys and scanned tokens.",
+		"entries": "case-insensitive; key = word_norm lowercased",
+		"code_entries": "case-SENSITIVE exact: word_norm(token) == key (keys uppercase; the surface must already BE uppercase, so 'in' the word ≠ 'IN' the code). n-gram length 1 only.",
+		"scan": "longest-first n-gram over whitespace words, left to right, non-overlapping"
+	},
+	"entries": {
+		"afghanistan": 1,
+		"alabama": 2,
+		"åland islands": 1,
+		"alaska": 2,
+		"albania": 1,
+		"algeria": 1,
+		"america": 1,
+		"american samoa": 19,
+		"andorra": 1,
+		"angola": 1,
+		"anguilla": 1,
+		"antarctica": 1,
+		"antigua and barbuda": 1,
+		"argentina": 1,
+		"arizona": 2,
+		"arkansas": 2,
+		"armenia": 1,
+		"aruba": 1,
+		"australia": 1,
+		"austria": 1,
+		"azerbaijan": 1,
+		"bahamas": 1,
+		"bahrain": 1,
+		"bangladesh": 1,
+		"barbados": 1,
+		"belarus": 1,
+		"belgië": 1,
+		"belgique": 1,
+		"belgium": 1,
+		"belize": 1,
+		"benin": 1,
+		"bermuda": 1,
+		"bhutan": 1,
+		"bolivia": 1,
+		"bonaire sint eustatius and saba": 1,
+		"bosnia and herzegovina": 1,
+		"botswana": 1,
+		"bouvet island": 1,
+		"box": 4,
+		"brazil": 1,
+		"britain": 1,
+		"british indian ocean territory": 1,
+		"brunei darussalam": 1,
+		"bulgaria": 1,
+		"burkina faso": 1,
+		"burundi": 1,
+		"california": 2,
+		"caller": 4,
+		"cambodia": 1,
+		"cameroon": 1,
+		"canada": 1,
+		"cape verde": 1,
+		"cayman islands": 1,
+		"cedex": 8,
+		"central african republic": 1,
+		"chad": 1,
+		"chile": 1,
+		"china": 1,
+		"christmas island": 1,
+		"cocos keeling islands": 1,
+		"colombia": 1,
+		"colorado": 2,
+		"comoros": 1,
+		"congo": 1,
+		"congo the democratic republic of the": 1,
+		"connecticut": 2,
+		"cook islands": 1,
+		"costa rica": 1,
+		"cote divoire": 1,
+		"croatia": 1,
+		"cuba": 1,
+		"curaçao": 1,
+		"cyprus": 1,
+		"czech republic": 1,
+		"delaware": 2,
+		"denmark": 1,
+		"deutschland": 1,
+		"district of columbia": 2,
+		"djibouti": 1,
+		"dominica": 1,
+		"dominican republic": 1,
+		"drawer": 4,
+		"ecuador": 1,
+		"egypt": 1,
+		"éire": 1,
+		"el salvador": 1,
+		"england": 1,
+		"equatorial guinea": 1,
+		"eritrea": 1,
+		"espana": 1,
+		"españa": 1,
+		"estonia": 1,
+		"ethiopia": 1,
+		"falkland islands malvinas": 1,
+		"faroe islands": 1,
+		"federal republic of germany": 1,
+		"fiji": 1,
+		"finland": 1,
+		"firm caller": 4,
+		"florida": 2,
+		"france": 1,
+		"french guiana": 1,
+		"french polynesia": 1,
+		"french republic": 1,
+		"french southern territories": 1,
+		"gabon": 1,
+		"gambia": 1,
+		"georgia": 19,
+		"germany": 1,
+		"ghana": 1,
+		"gibraltar": 1,
+		"great britain": 1,
+		"greece": 1,
+		"greenland": 1,
+		"grenada": 1,
+		"guadeloupe": 1,
+		"guam": 19,
+		"guatemala": 1,
+		"guernsey": 1,
+		"guinea": 1,
+		"guinea-bissau": 1,
+		"guyana": 1,
+		"haiti": 1,
+		"hawaii": 2,
+		"heard island and mcdonald islands": 1,
+		"holland": 1,
+		"holy see vatican city state": 1,
+		"honduras": 1,
+		"hong kong": 1,
+		"hungary": 1,
+		"iceland": 1,
+		"idaho": 2,
+		"illinois": 2,
+		"india": 1,
+		"indiana": 2,
+		"indonesia": 1,
+		"iowa": 2,
+		"iran islamic republic of": 1,
+		"iraq": 1,
+		"ireland": 1,
+		"isle of man": 1,
+		"israel": 1,
+		"italia": 1,
+		"italy": 1,
+		"jamaica": 1,
+		"japan": 1,
+		"jersey": 1,
+		"jordan": 1,
+		"kansas": 2,
+		"kazakhstan": 1,
+		"kentucky": 2,
+		"kenya": 1,
+		"kiribati": 1,
+		"korea democratic people's republic of": 1,
+		"korea republic of": 1,
+		"kuwait": 1,
+		"kyrgyzstan": 1,
+		"lao people's democratic republic": 1,
+		"latvia": 1,
+		"lebanon": 1,
+		"lesotho": 1,
+		"liberia": 1,
+		"libya": 1,
+		"liechtenstein": 1,
+		"lithuania": 1,
+		"lockbox": 4,
+		"louisiana": 2,
+		"luxembourg": 1,
+		"macao": 1,
+		"macedonia the former yugoslav republic of": 1,
+		"madagascar": 1,
+		"maine": 2,
+		"malawi": 1,
+		"malaysia": 1,
+		"maldives": 1,
+		"mali": 1,
+		"malta": 1,
+		"marshall islands": 1,
+		"martinique": 1,
+		"maryland": 2,
+		"massachusetts": 2,
+		"mauritania": 1,
+		"mauritius": 1,
+		"mayotte": 1,
+		"mexico": 1,
+		"méxico": 1,
+		"michigan": 2,
+		"micronesia federated states of": 1,
+		"minnesota": 2,
+		"mississippi": 2,
+		"missouri": 2,
+		"moldova republic of": 1,
+		"monaco": 1,
+		"mongolia": 1,
+		"montana": 2,
+		"montenegro": 1,
+		"montserrat": 1,
+		"morocco": 1,
+		"mozambique": 1,
+		"myanmar": 1,
+		"namibia": 1,
+		"nauru": 1,
+		"nebraska": 2,
+		"nederland": 1,
+		"nepal": 1,
+		"netherlands": 1,
+		"nevada": 2,
+		"new caledonia": 1,
+		"new hampshire": 2,
+		"new jersey": 2,
+		"new mexico": 2,
+		"new york": 2,
+		"new zealand": 1,
+		"nicaragua": 1,
+		"niger": 1,
+		"nigeria": 1,
+		"nippon": 1,
+		"niue": 1,
+		"norfolk island": 1,
+		"north carolina": 2,
+		"north dakota": 2,
+		"northern mariana islands": 19,
+		"norway": 1,
+		"ohio": 2,
+		"oklahoma": 2,
+		"oman": 1,
+		"oregon": 2,
+		"osterreich": 1,
+		"österreich": 1,
+		"p o box": 4,
+		"pakistan": 1,
+		"palau": 1,
+		"palestine state of": 1,
+		"panama": 1,
+		"papua new guinea": 1,
+		"paraguay": 1,
+		"pennsylvania": 2,
+		"peru": 1,
+		"philippines": 1,
+		"pitcairn": 1,
+		"po box": 4,
+		"poland": 1,
+		"portugal": 1,
+		"post office box": 4,
+		"puerto rico": 19,
+		"qatar": 1,
+		"reunion": 1,
+		"rhode island": 2,
+		"romania": 1,
+		"russian federation": 1,
+		"rwanda": 1,
+		"saint barthélemy": 1,
+		"saint helena ascension and tristan da cunha": 1,
+		"saint kitts and nevis": 1,
+		"saint lucia": 1,
+		"saint martin french part": 1,
+		"saint pierre and miquelon": 1,
+		"saint vincent and the grenadines": 1,
+		"samoa": 1,
+		"san marino": 1,
+		"sao tome and principe": 1,
+		"saudi arabia": 1,
+		"schweiz": 1,
+		"senegal": 1,
+		"serbia": 1,
+		"seychelles": 1,
+		"sierra leone": 1,
+		"singapore": 1,
+		"sint maarten dutch part": 1,
+		"slovakia": 1,
+		"slovenia": 1,
+		"solomon islands": 1,
+		"somalia": 1,
+		"south africa": 1,
+		"south carolina": 2,
+		"south dakota": 2,
+		"south georgia and the south sandwich islands": 1,
+		"south sudan": 1,
+		"spain": 1,
+		"sri lanka": 1,
+		"sudan": 1,
+		"suisse": 1,
+		"suriname": 1,
+		"svalbard and jan mayen": 1,
+		"svizzera": 1,
+		"swaziland": 1,
+		"sweden": 1,
+		"switzerland": 1,
+		"syrian arab republic": 1,
+		"taiwan province of china": 1,
+		"tajikistan": 1,
+		"tanzania united republic of": 1,
+		"tennessee": 2,
+		"texas": 2,
+		"thailand": 1,
+		"the netherlands": 1,
+		"timor-leste": 1,
+		"togo": 1,
+		"tokelau": 1,
+		"tonga": 1,
+		"trinidad and tobago": 1,
+		"tunisia": 1,
+		"turkey": 1,
+		"turkmenistan": 1,
+		"turks and caicos islands": 1,
+		"tuvalu": 1,
+		"uganda": 1,
+		"ukraine": 1,
+		"united arab emirates": 1,
+		"united kingdom": 1,
+		"united states": 1,
+		"united states minor outlying islands": 1,
+		"united states of america": 1,
+		"uruguay": 1,
+		"us virgin islands": 2,
+		"utah": 2,
+		"uzbekistan": 1,
+		"vanuatu": 1,
+		"venezuela": 1,
+		"vermont": 2,
+		"viet nam": 1,
+		"virgin islands british": 1,
+		"virgin islands u.s": 1,
+		"virginia": 2,
+		"wallis and futuna": 1,
+		"washington": 2,
+		"west virginia": 2,
+		"western sahara": 1,
+		"wisconsin": 2,
+		"wyoming": 2,
+		"yemen": 1,
+		"zambia": 1,
+		"zimbabwe": 1
+	},
+	"code_entries": {
+		"ABW": 1,
+		"AFG": 1,
+		"AGO": 1,
+		"AIA": 1,
+		"AK": 2,
+		"AL": 2,
+		"ALA": 1,
+		"ALB": 1,
+		"AND": 1,
+		"AR": 2,
+		"ARE": 1,
+		"ARG": 1,
+		"ARM": 1,
+		"AS": 2,
+		"ASM": 1,
+		"AT": 1,
+		"ATA": 1,
+		"ATF": 1,
+		"ATG": 1,
+		"AU": 1,
+		"AUS": 1,
+		"AUT": 1,
+		"AZ": 2,
+		"AZE": 1,
+		"BDI": 1,
+		"BE": 1,
+		"BEL": 1,
+		"BEN": 1,
+		"BES": 1,
+		"BFA": 1,
+		"BGD": 1,
+		"BGR": 1,
+		"BHR": 1,
+		"BHS": 1,
+		"BIH": 1,
+		"BLM": 1,
+		"BLR": 1,
+		"BLZ": 1,
+		"BMU": 1,
+		"BOL": 1,
+		"BRA": 1,
+		"BRB": 1,
+		"BRN": 1,
+		"BTN": 1,
+		"BVT": 1,
+		"BWA": 1,
+		"CA": 19,
+		"CAF": 1,
+		"CAN": 1,
+		"CCK": 1,
+		"CH": 1,
+		"CHE": 1,
+		"CHL": 1,
+		"CHN": 1,
+		"CIV": 1,
+		"CMR": 1,
+		"CO": 2,
+		"COD": 1,
+		"COG": 1,
+		"COK": 1,
+		"COL": 1,
+		"COM": 1,
+		"CPV": 1,
+		"CRI": 1,
+		"CT": 2,
+		"CUB": 1,
+		"CUW": 1,
+		"CXR": 1,
+		"CYM": 1,
+		"CYP": 1,
+		"CZE": 1,
+		"DC": 2,
+		"DE": 19,
+		"DEU": 1,
+		"DJI": 1,
+		"DMA": 1,
+		"DNK": 1,
+		"DOM": 1,
+		"DZA": 1,
+		"ECU": 1,
+		"EGY": 1,
+		"ERI": 1,
+		"ES": 1,
+		"ESH": 1,
+		"ESP": 1,
+		"EST": 1,
+		"ETH": 1,
+		"FIN": 1,
+		"FJI": 1,
+		"FL": 2,
+		"FLK": 1,
+		"FR": 1,
+		"FRA": 1,
+		"FRO": 1,
+		"FSM": 1,
+		"GA": 2,
+		"GAB": 1,
+		"GB": 1,
+		"GBR": 1,
+		"GEO": 1,
+		"GER": 1,
+		"GGY": 1,
+		"GHA": 1,
+		"GIB": 1,
+		"GIN": 1,
+		"GLP": 1,
+		"GMB": 1,
+		"GNB": 1,
+		"GNQ": 1,
+		"GRC": 1,
+		"GRD": 1,
+		"GRL": 1,
+		"GTM": 1,
+		"GU": 2,
+		"GUF": 1,
+		"GUM": 1,
+		"GUY": 1,
+		"HI": 2,
+		"HKG": 1,
+		"HMD": 1,
+		"HND": 1,
+		"HRV": 1,
+		"HTI": 1,
+		"HUN": 1,
+		"IA": 2,
+		"ID": 2,
+		"IDN": 1,
+		"IE": 1,
+		"IL": 2,
+		"IMN": 1,
+		"IN": 2,
+		"IND": 1,
+		"IOT": 1,
+		"IRL": 1,
+		"IRN": 1,
+		"IRQ": 1,
+		"ISL": 1,
+		"ISR": 1,
+		"IT": 1,
+		"ITA": 1,
+		"JAM": 1,
+		"JEY": 1,
+		"JOR": 1,
+		"JP": 1,
+		"JPN": 1,
+		"KAZ": 1,
+		"KEN": 1,
+		"KGZ": 1,
+		"KHM": 1,
+		"KIR": 1,
+		"KNA": 1,
+		"KOR": 1,
+		"KS": 2,
+		"KWT": 1,
+		"KY": 2,
+		"LA": 2,
+		"LAO": 1,
+		"LBN": 1,
+		"LBR": 1,
+		"LBY": 1,
+		"LCA": 1,
+		"LIE": 1,
+		"LKA": 1,
+		"LSO": 1,
+		"LTU": 1,
+		"LUX": 1,
+		"LVA": 1,
+		"MA": 2,
+		"MAC": 1,
+		"MAF": 1,
+		"MAR": 1,
+		"MCO": 1,
+		"MD": 2,
+		"MDA": 1,
+		"MDG": 1,
+		"MDV": 1,
+		"ME": 2,
+		"MEX": 1,
+		"MHL": 1,
+		"MI": 2,
+		"MKD": 1,
+		"MLI": 1,
+		"MLT": 1,
+		"MMR": 1,
+		"MN": 2,
+		"MNE": 1,
+		"MNG": 1,
+		"MNP": 1,
+		"MO": 2,
+		"MOZ": 1,
+		"MP": 2,
+		"MRT": 1,
+		"MS": 2,
+		"MSR": 1,
+		"MT": 2,
+		"MTQ": 1,
+		"MUS": 1,
+		"MWI": 1,
+		"MX": 1,
+		"MYS": 1,
+		"MYT": 1,
+		"NAM": 1,
+		"NC": 2,
+		"NCL": 1,
+		"ND": 2,
+		"NE": 2,
+		"NER": 1,
+		"NFK": 1,
+		"NGA": 1,
+		"NH": 2,
+		"NIC": 1,
+		"NIU": 1,
+		"NJ": 2,
+		"NL": 1,
+		"NLD": 1,
+		"NM": 2,
+		"NOR": 1,
+		"NPL": 1,
+		"NRU": 1,
+		"NV": 2,
+		"NY": 2,
+		"NZL": 1,
+		"OH": 2,
+		"OK": 2,
+		"OMN": 1,
+		"OR": 2,
+		"PA": 2,
+		"PAK": 1,
+		"PAN": 1,
+		"PCN": 1,
+		"PER": 1,
+		"PHL": 1,
+		"PLW": 1,
+		"PNG": 1,
+		"POL": 1,
+		"PR": 2,
+		"PRI": 1,
+		"PRK": 1,
+		"PRT": 1,
+		"PRY": 1,
+		"PSE": 1,
+		"PYF": 1,
+		"QAT": 1,
+		"REU": 1,
+		"RI": 2,
+		"ROM": 1,
+		"RUS": 1,
+		"RWA": 1,
+		"SAU": 1,
+		"SC": 2,
+		"SD": 2,
+		"SDN": 1,
+		"SEN": 1,
+		"SGP": 1,
+		"SGS": 1,
+		"SHN": 1,
+		"SJM": 1,
+		"SLB": 1,
+		"SLE": 1,
+		"SLV": 1,
+		"SMR": 1,
+		"SOM": 1,
+		"SPM": 1,
+		"SRB": 1,
+		"SSD": 1,
+		"STP": 1,
+		"SUR": 1,
+		"SVK": 1,
+		"SVN": 1,
+		"SWE": 1,
+		"SWZ": 1,
+		"SXM": 1,
+		"SYC": 1,
+		"SYR": 1,
+		"TCA": 1,
+		"TCD": 1,
+		"TGO": 1,
+		"THA": 1,
+		"TJK": 1,
+		"TKL": 1,
+		"TKM": 1,
+		"TLS": 1,
+		"TN": 2,
+		"TON": 1,
+		"TTO": 1,
+		"TUN": 1,
+		"TUR": 1,
+		"TUV": 1,
+		"TWN": 1,
+		"TX": 2,
+		"TZA": 1,
+		"U.K": 1,
+		"U.S": 1,
+		"U.S.A": 1,
+		"UGA": 1,
+		"UK": 1,
+		"UKR": 1,
+		"UMI": 1,
+		"URY": 1,
+		"US": 1,
+		"USA": 1,
+		"UT": 2,
+		"UZB": 1,
+		"VA": 2,
+		"VAT": 1,
+		"VCT": 1,
+		"VEN": 1,
+		"VGB": 1,
+		"VI": 2,
+		"VIR": 1,
+		"VNM": 1,
+		"VT": 2,
+		"VUT": 1,
+		"WA": 2,
+		"WI": 2,
+		"WLF": 1,
+		"WSM": 1,
+		"WV": 2,
+		"WY": 2,
+		"YEM": 1,
+		"ZAF": 1,
+		"ZMB": 1,
+		"ZWE": 1,
+		"日本": 1
+	}
+}