@mailwoman/corpus 10.6.0 → 10.7.0

package/data/training-manifests/v0.7.10-gb-county.effective.json

@@ -0,0 +1,2335 @@
+{
+	"manifestID": "corpus-effective-training-manifest",
+	"schemaVersion": 2,
+	"drawEvidence": "replayed-epoch-audit",
+	"labelSet": null,
+	"requiredAttributions": [
+		{
+			"license": "BAN (Base Adresse Nationale) commune+postcode tuples, rendered admin-split — see ingest SOURCE",
+			"sources": ["rendered-fr-admin-split"],
+			"statement": null
+		},
+		{
+			"license": "CC-BY-4.0",
+			"sources": ["cordis", "gbpa-bs", "gnaf", "lv-varis", "ro-retea-scolara", "ryhti-ax"],
+			"statement": null
+		},
+		{
+			"license": "CDLA-Permissive-2.0",
+			"sources": ["overture", "overture-latam"],
+			"statement": null
+		},
+		{
+			"license": "CDLA-Permissive-2.0 — Overture Maps addresses over the Singapore Open Data Licence 1.0 (OneMap / Singapore Land Authority)",
+			"sources": ["rendered-sg-register"],
+			"statement": null
+		},
+		{
+			"license": "Licence Ouverte 1.0",
+			"sources": ["fr-finess-overseas"],
+			"statement": null
+		},
+		{
+			"license": "Licence Ouverte 2.0",
+			"sources": [
+				"ban",
+				"ban-bl",
+				"ban-gf",
+				"ban-gp",
+				"ban-mf",
+				"ban-mq",
+				"ban-nc",
+				"ban-pf",
+				"ban-pm",
+				"ban-re",
+				"ban-yt",
+				"fr-annuaire-education-overseas"
+			],
+			"statement": null
+		},
+		{
+			"license": "LicenseRef-CC-BY-unstated-version",
+			"sources": ["opendata-az"],
+			"statement": null
+		},
+		{
+			"license": "LicenseRef-FO-Umhvorvisstovan-Brukstreytir",
+			"sources": ["adressur-fo"],
+			"statement": null
+		},
+		{
+			"license": "LicenseRef-IM-OGL",
+			"sources": ["landregistry-im"],
+			"statement": null
+		},
+		{
+			"license": "LicenseRef-LI-ABI-OGD-2",
+			"sources": ["llv-li"],
+			"statement": null
+		},
+		{
+			"license": "LicenseRef-Licencia-Datos-Abiertos-Uruguay-0.1",
+			"sources": ["ide-uy"],
+			"statement": null
+		},
+		{
+			"license": "none-recorded-on-rows",
+			"sources": ["invented-anchor-absorption"],
+			"statement": null
+		},
+		{
+			"license": "ODbL-1.0",
+			"sources": [
+				"osm-ae",
+				"osm-al",
+				"osm-am",
+				"osm-ao",
+				"osm-ar",
+				"osm-aw",
+				"osm-az",
+				"osm-ba",
+				"osm-bb",
+				"osm-bd",
+				"osm-bh",
+				"osm-bm",
+				"osm-bn",
+				"osm-bs",
+				"osm-bt",
+				"osm-bw",
+				"osm-by",
+				"osm-bz",
+				"osm-cd",
+				"osm-ci",
+				"osm-cl",
+				"osm-co",
+				"osm-cr",
+				"osm-cu",
+				"osm-cw",
+				"osm-do",
+				"osm-dz",
+				"osm-ec",
+				"osm-eg",
+				"osm-ge",
+				"osm-gg",
+				"osm-gh",
+				"osm-gl",
+				"osm-gt",
+				"osm-hk",
+				"osm-ht",
+				"osm-id",
+				"osm-in",
+				"osm-iq",
+				"osm-ir",
+				"osm-je",
+				"osm-jm",
+				"osm-jo",
+				"osm-ke",
+				"osm-kg",
+				"osm-kh",
+				"osm-kw",
+				"osm-kz",
+				"osm-lb",
+				"osm-lk",
+				"osm-lr",
+				"osm-ma",
+				"osm-md",
+				"osm-me",
+				"osm-mg",
+				"osm-mk",
+				"osm-mm",
+				"osm-mn",
+				"osm-mo",
+				"osm-mt",
+				"osm-mv",
+				"osm-my",
+				"osm-mz",
+				"osm-na",
+				"osm-ng",
+				"osm-np",
+				"osm-om",
+				"osm-pa",
+				"osm-pe",
+				"osm-pf",
+				"osm-ph",
+				"osm-pk",
+				"osm-pr",
+				"osm-py",
+				"osm-qa",
+				"osm-rs",
+				"osm-ru",
+				"osm-rw",
+				"osm-sa",
+				"osm-sm",
+				"osm-sn",
+				"osm-sr",
+				"osm-sv",
+				"osm-th",
+				"osm-tj",
+				"osm-tm",
+				"osm-tn",
+				"osm-tt",
+				"osm-tz",
+				"osm-ua",
+				"osm-ug",
+				"osm-uz",
+				"osm-ve",
+				"osm-vi",
+				"osm-vn",
+				"osm-zm",
+				"osm-zw",
+				"rendered-bd-register",
+				"rendered-pk-register",
+				"spliced-sub-venue"
+			],
+			"statement": "© OpenStreetMap contributors. Data licensed under the Open Database License (ODbL) 1.0 (https://opendatacommons.org/licenses/odbl/1-0/); see https://www.openstreetmap.org/copyright."
+		},
+		{
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons + injected USPS Pub-28 C2 unit designators",
+			"sources": ["spliced-unit-v30"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons + USPS Pub-28 §29 PO-box designators (codex/corpus templates)",
+			"sources": ["invented-po-box-cedex"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons, street split via USPS Pub-28 C1/C2 (codex)",
+			"sources": ["spliced-affix"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons; terminal suffix labels via USPS Pub-28 codex; venue shell from HRSA site names (US public domain)",
+			"sources": ["spliced-suffix-boundary"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses CH tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-ch"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses DE tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-de"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses FR countrywide tuples, rendered canonical + reversed-order — see ingest SOURCE",
+			"sources": ["rendered-fr-order"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses HR tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-hr"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses LU tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-lu"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses multi-locale and National Address Database US skeletons + injected ISO-3166 country surface forms (codex)",
+			"sources": ["spliced-country"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses PT tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-pt"],
+			"statement": null
+		},
+		{
+			"license": "OpenAddresses SK tuples, rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-sk"],
+			"statement": null
+		},
+		{
+			"license": "OS OpenData GB tuples (OGL-UK-3.0), rendered native-order — see ingest SOURCES",
+			"sources": ["rendered-gb-os-open"],
+			"statement": null
+		},
+		{
+			"license": "Public Domain",
+			"sources": [
+				"bsp-gu",
+				"state-ny-notaries",
+				"state-tx-notaries",
+				"tiger",
+				"usgov-hrsa-fqhc",
+				"usgov-nad",
+				"usgov-nppes"
+			],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — bare-postcode; postcodes from OpenAddresses (per-source attribution in the model card)",
+			"sources": ["codex-bare-postcode"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — cz-pcfirst-preposition; (street, number, postcode, city) from OpenAddresses CZ (per-source attribution in the model card)",
+			"sources": ["rendered-cz-pcfirst-preposition-v21"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — derived from CC-BY / public-domain input tuples",
+			"sources": ["invented-house-venue", "invented-po-box-military"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — fr-bare-street; (street, number, city) from BAN (Base Adresse Nationale, Licence Ouverte)",
+			"sources": ["fragment-fr-bare-street-v22"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — fr-fragment; (street, commune) from BAN (Base Adresse Nationale, Licence Ouverte)",
+			"sources": ["fragment-fr"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — fragment-assay; street/number/city from OpenAddresses no",
+			"sources": ["fragment-assay"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — nl-postcode; (street, number, postcode, city) from OpenAddresses NL (per-source attribution in the model card)",
+			"sources": ["rendered-nl-postcode"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — no-fragment; (street, number, postcode, city) from OpenAddresses NO / Kartverket",
+			"sources": ["fragment-no"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — OpenStreetMap venue + sub-venue names (ODbL, © OpenStreetMap contributors) and Overture Places names (CDLA-Permissive-2.0) over OpenAddresses / BAN / US situs / OS OpenData (OGL-UK-3.0) address skeletons",
+			"sources": ["spliced-sub-venue"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — si-bare-village; (village, number, postcode) from OpenAddresses SI (per-source attribution in the model card)",
+			"sources": ["rendered-si-bare-village"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic — trailing-region; (locality, region) ancestor pairs from WOF (CC0/ODC-By per source)",
+			"sources": ["spliced-trailing-region-ca-bare", "spliced-trailing-region-es-v28", "spliced-trailing-region-us"],
+			"statement": null
+		},
+		{
+			"license": "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
+			"sources": ["deepseek-kryptonite"],
+			"statement": null
+		},
+		{
+			"license": "TIGER/Line 2023 EDGES (US Census, public domain) real street pairs; National Address Database (public domain) Cook IL and Morris NJ zip-to-city tails",
+			"sources": ["invented-intersection"],
+			"statement": null
+		}
+	],
+	"corpusVersion": "v0.7.10-gb-county",
+	"corpusManifestDigest": "7230a0abf9b0b49c4f8c8274a9c38062eb2e20c96cf25ae23236d8db1e104223",
+	"config": "corpus-python/src/mailwoman_train/configs/v7.10.0-gb-county-60k.yaml",
+	"seed": 43,
+	"drawsRequested": 1000000,
+	"drawsRealized": 1000000,
+	"admittedCountries": 215,
+	"countriesDrawingRows": 166,
+	"admittedCountriesDrawingZero": [
+		"AD",
+		"AF",
+		"AG",
+		"AI",
+		"AS",
+		"BI",
+		"BJ",
+		"BQ",
+		"CF",
+		"CG",
+		"CK",
+		"DJ",
+		"DM",
+		"ER",
+		"FK",
+		"FM",
+		"GD",
+		"GM",
+		"GN",
+		"GW",
+		"HN",
+		"IO",
+		"KM",
+		"KN",
+		"KY",
+		"LA",
+		"LC",
+		"LS",
+		"ML",
+		"MP",
+		"MS",
+		"MU",
+		"NE",
+		"NI",
+		"PG",
+		"SB",
+		"SC",
+		"SH",
+		"SO",
+		"ST",
+		"SX",
+		"TC",
+		"TK",
+		"TO",
+		"UM",
+		"VA",
+		"VC",
+		"VG",
+		"VU"
+	],
+	"sources": [
+		{
+			"source": "osm-ru",
+			"corpusRows": 2000177,
+			"license": "ODbL-1.0",
+			"weight": 0.2,
+			"drawnRows": 52169,
+			"emittedRows": 52180,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-sub-venue",
+			"corpusRows": 120000,
+			"license": "Synthetic — OpenStreetMap venue + sub-venue names (ODbL, © OpenStreetMap contributors) and Overture Places names (CDLA-Permissive-2.0) over OpenAddresses / BAN / US situs / OS OpenData (OGL-UK-3.0) address skeletons",
+			"weight": 12,
+			"drawnRows": 44361,
+			"emittedRows": 44937,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-cz-pcfirst-preposition-v21",
+			"corpusRows": 51037,
+			"license": "Synthetic — cz-pcfirst-preposition; (street, number, postcode, city) from OpenAddresses CZ (per-source attribution in the model card)",
+			"weight": 12,
+			"drawnRows": 44395,
+			"emittedRows": 44707,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-si-bare-village",
+			"corpusRows": 6285,
+			"license": "Synthetic — si-bare-village; (village, number, postcode) from OpenAddresses SI (per-source attribution in the model card)",
+			"weight": 12,
+			"drawnRows": 44282,
+			"emittedRows": 44523,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fragment-fr-bare-street-v22",
+			"corpusRows": 64122,
+			"license": "Synthetic — fr-bare-street; (street, number, city) from BAN (Base Adresse Nationale, Licence Ouverte)",
+			"weight": 12,
+			"drawnRows": 44115,
+			"emittedRows": 36972,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fragment-no",
+			"corpusRows": 33203,
+			"license": "Synthetic — no-fragment; (street, number, postcode, city) from OpenAddresses NO / Kartverket",
+			"weight": 12,
+			"drawnRows": 44333,
+			"emittedRows": 34928,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fragment-fr",
+			"corpusRows": 144865,
+			"license": "Synthetic — fr-fragment; (street, commune) from BAN (Base Adresse Nationale, Licence Ouverte)",
+			"weight": 12,
+			"drawnRows": 44817,
+			"emittedRows": 34460,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "invented-anchor-absorption",
+			"corpusRows": 50000,
+			"license": "none-recorded-on-rows",
+			"weight": 6,
+			"drawnRows": 22235,
+			"emittedRows": 27227,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "gleif-lei",
+			"corpusRows": 1355135,
+			"license": "CC0-1.0",
+			"weight": 0.15,
+			"drawnRows": 26341,
+			"emittedRows": 26869,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "gnaf",
+			"corpusRows": 149969,
+			"license": "CC-BY-4.0",
+			"weight": 6,
+			"drawnRows": 22100,
+			"emittedRows": 23940,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-de",
+			"corpusRows": 204000,
+			"license": "OpenAddresses DE tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22540,
+			"emittedRows": 23865,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-ch",
+			"corpusRows": 500000,
+			"license": "OpenAddresses CH tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22123,
+			"emittedRows": 23391,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-nl-postcode",
+			"corpusRows": 10000,
+			"license": "Synthetic — nl-postcode; (street, number, postcode, city) from OpenAddresses NL (per-source attribution in the model card)",
+			"weight": 6,
+			"drawnRows": 22367,
+			"emittedRows": 22785,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-gb-os-open",
+			"corpusRows": 800000,
+			"license": "OS OpenData GB tuples (OGL-UK-3.0), rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22313,
+			"emittedRows": 22668,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-hr",
+			"corpusRows": 300000,
+			"license": "OpenAddresses HR tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22104,
+			"emittedRows": 22511,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "overture-latam",
+			"corpusRows": 3771982,
+			"license": "CDLA-Permissive-2.0",
+			"weight": 6,
+			"drawnRows": 22091,
+			"emittedRows": 22463,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-pt",
+			"corpusRows": 800000,
+			"license": "OpenAddresses PT tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22197,
+			"emittedRows": 22407,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-sk",
+			"corpusRows": 150000,
+			"license": "OpenAddresses SK tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22287,
+			"emittedRows": 22226,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-lu",
+			"corpusRows": 150000,
+			"license": "OpenAddresses LU tuples, rendered native-order — see ingest SOURCES",
+			"weight": 6,
+			"drawnRows": 22208,
+			"emittedRows": 22136,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-fr-admin-split",
+			"corpusRows": 60000,
+			"license": "BAN (Base Adresse Nationale) commune+postcode tuples, rendered admin-split — see ingest SOURCE",
+			"weight": 6,
+			"drawnRows": 22375,
+			"emittedRows": 21497,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "tiger",
+			"corpusRows": 40240695,
+			"license": "Public Domain",
+			"weight": 4,
+			"drawnRows": 14870,
+			"emittedRows": 19614,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fragment-assay",
+			"corpusRows": 221335,
+			"license": "Synthetic — fragment-assay; street/number/city from OpenAddresses no",
+			"weight": 6,
+			"drawnRows": 22169,
+			"emittedRows": 17732,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "deepseek-kryptonite",
+			"corpusRows": 4822,
+			"license": "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
+			"weight": 3,
+			"drawnRows": 11205,
+			"emittedRows": 15757,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-sg-register",
+			"corpusRows": 142083,
+			"license": "CDLA-Permissive-2.0 — Overture Maps addresses over the Singapore Open Data Licence 1.0 (OneMap / Singapore Land Authority)",
+			"weight": 1,
+			"drawnRows": 18696,
+			"emittedRows": 15444,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-in",
+			"corpusRows": 57604,
+			"license": "ODbL-1.0",
+			"weight": 2,
+			"drawnRows": 13627,
+			"emittedRows": 13956,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-id",
+			"corpusRows": 56396,
+			"license": "ODbL-1.0",
+			"weight": 2,
+			"drawnRows": 13844,
+			"emittedRows": 13112,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "overture",
+			"corpusRows": 2400000,
+			"license": "CDLA-Permissive-2.0",
+			"weight": 3,
+			"drawnRows": 11096,
+			"emittedRows": 11591,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-pk-register",
+			"corpusRows": 80081,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 10575,
+			"emittedRows": 10912,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-fr-order",
+			"corpusRows": 50000,
+			"license": "OpenAddresses FR countrywide tuples, rendered canonical + reversed-order — see ingest SOURCE",
+			"weight": 3,
+			"drawnRows": 11112,
+			"emittedRows": 10712,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-pk",
+			"corpusRows": 81501,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 10427,
+			"emittedRows": 10647,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban",
+			"corpusRows": 145193536,
+			"license": "Licence Ouverte 2.0",
+			"weight": 3,
+			"drawnRows": 10900,
+			"emittedRows": 10612,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "usgov-hrsa-fqhc",
+			"corpusRows": 150894,
+			"license": "Public Domain",
+			"weight": 2,
+			"drawnRows": 7412,
+			"emittedRows": 10526,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "usgov-nppes",
+			"corpusRows": 53629629,
+			"license": "Public Domain",
+			"weight": 2,
+			"drawnRows": 7426,
+			"emittedRows": 10365,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "state-ny-notaries",
+			"corpusRows": 180606,
+			"license": "Public Domain",
+			"weight": 2,
+			"drawnRows": 7440,
+			"emittedRows": 9996,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-country",
+			"corpusRows": 50000,
+			"license": "OpenAddresses multi-locale and National Address Database US skeletons + injected ISO-3166 country surface forms (codex)",
+			"weight": 2,
+			"drawnRows": 7371,
+			"emittedRows": 9745,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-affix",
+			"corpusRows": 90000,
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons, street split via USPS Pub-28 C1/C2 (codex)",
+			"weight": 2,
+			"drawnRows": 7136,
+			"emittedRows": 8871,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-vn",
+			"corpusRows": 68971,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 9032,
+			"emittedRows": 7744,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-eg",
+			"corpusRows": 50000,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 6311,
+			"emittedRows": 7726,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "cordis",
+			"corpusRows": 57918,
+			"license": "CC-BY-4.0",
+			"weight": 1,
+			"drawnRows": 7628,
+			"emittedRows": 7568,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "state-tx-notaries",
+			"corpusRows": 3453329,
+			"license": "Public Domain",
+			"weight": 1.5,
+			"drawnRows": 5613,
+			"emittedRows": 7354,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "invented-house-venue",
+			"corpusRows": 138000,
+			"license": "Synthetic — derived from CC-BY / public-domain input tuples",
+			"weight": 2,
+			"drawnRows": 7395,
+			"emittedRows": 7343,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-suffix-boundary",
+			"corpusRows": 30000,
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons; terminal suffix labels via USPS Pub-28 codex; venue shell from HRSA site names (US public domain)",
+			"weight": 2.5,
+			"drawnRows": 9050,
+			"emittedRows": 7250,
+			"augmentExcluded": true,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-trailing-region-ca-bare",
+			"corpusRows": 13740,
+			"license": "Synthetic — trailing-region; (locality, region) ancestor pairs from WOF (CC0/ODC-By per source)",
+			"weight": 4,
+			"drawnRows": 7115,
+			"emittedRows": 7197,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-unit-v30",
+			"corpusRows": 50000,
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons + injected USPS Pub-28 C2 unit designators",
+			"weight": 1.5,
+			"drawnRows": 5627,
+			"emittedRows": 6921,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-md",
+			"corpusRows": 50000,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 6405,
+			"emittedRows": 6642,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-rs",
+			"corpusRows": 50000,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 6363,
+			"emittedRows": 6432,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ads",
+			"corpusRows": 50000,
+			"license": "CC0-1.0",
+			"weight": 1,
+			"drawnRows": 6354,
+			"emittedRows": 6404,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "lv-varis",
+			"corpusRows": 550632,
+			"license": "CC-BY-4.0",
+			"weight": 0.1,
+			"drawnRows": 6501,
+			"emittedRows": 6359,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "wof-admin",
+			"corpusRows": 53815886,
+			"license": "CC0-1.0",
+			"weight": 2,
+			"drawnRows": 7307,
+			"emittedRows": 6183,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "invented-po-box-cedex",
+			"corpusRows": 50000,
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons + USPS Pub-28 §29 PO-box designators (codex/corpus templates)",
+			"weight": 1.5,
+			"drawnRows": 5635,
+			"emittedRows": 6088,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ar",
+			"corpusRows": 45623,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 5810,
+			"emittedRows": 5942,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "wof-postalcode",
+			"corpusRows": 15206200,
+			"license": "CC0-1.0",
+			"weight": 2,
+			"drawnRows": 7307,
+			"emittedRows": 5656,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "invented-po-box-military",
+			"corpusRows": 5279,
+			"license": "Synthetic — derived from CC-BY / public-domain input tuples",
+			"weight": 8,
+			"drawnRows": 5516,
+			"emittedRows": 5481,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-trailing-region-es-v28",
+			"corpusRows": 4944,
+			"license": "Synthetic — trailing-region; (locality, region) ancestor pairs from WOF (CC0/ODC-By per source)",
+			"weight": 8,
+			"drawnRows": 5301,
+			"emittedRows": 5092,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "usgov-nad",
+			"corpusRows": 380800563,
+			"license": "Public Domain",
+			"weight": 1,
+			"drawnRows": 3583,
+			"emittedRows": 5016,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "rendered-bd-register",
+			"corpusRows": 4551,
+			"license": "ODbL-1.0",
+			"weight": 8,
+			"drawnRows": 4659,
+			"emittedRows": 4734,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "invented-intersection",
+			"corpusRows": 40000,
+			"license": "TIGER/Line 2023 EDGES (US Census, public domain) real street pairs; National Address Database (public domain) Cook IL and Morris NJ zip-to-city tails",
+			"weight": 1,
+			"drawnRows": 3728,
+			"emittedRows": 4279,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ro-retea-scolara",
+			"corpusRows": 17533,
+			"license": "CC-BY-4.0",
+			"weight": 2,
+			"drawnRows": 4153,
+			"emittedRows": 4241,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-cl",
+			"corpusRows": 28225,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 3713,
+			"emittedRows": 3590,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-re",
+			"corpusRows": 352335,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.08,
+			"drawnRows": 3090,
+			"emittedRows": 3223,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-by",
+			"corpusRows": 25511,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 3211,
+			"emittedRows": 3174,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-gp",
+			"corpusRows": 161409,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.15,
+			"drawnRows": 2851,
+			"emittedRows": 2902,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ae",
+			"corpusRows": 22565,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 2851,
+			"emittedRows": 2894,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ng",
+			"corpusRows": 6762,
+			"license": "ODbL-1.0",
+			"weight": 4,
+			"drawnRows": 3517,
+			"emittedRows": 2818,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-tt",
+			"corpusRows": 21086,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 2759,
+			"emittedRows": 2696,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "spliced-trailing-region-us",
+			"corpusRows": 15976,
+			"license": "Synthetic — trailing-region; (locality, region) ancestor pairs from WOF (CC0/ODC-By per source)",
+			"weight": 1,
+			"drawnRows": 1954,
+			"emittedRows": 2640,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bd",
+			"corpusRows": 11371,
+			"license": "ODbL-1.0",
+			"weight": 2,
+			"drawnRows": 3004,
+			"emittedRows": 2582,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ide-uy",
+			"corpusRows": 20479,
+			"license": "LicenseRef-Licencia-Datos-Abiertos-Uruguay-0.1",
+			"weight": 1,
+			"drawnRows": 2626,
+			"emittedRows": 2561,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-mq",
+			"corpusRows": 138873,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.15,
+			"drawnRows": 2364,
+			"emittedRows": 2442,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-gf",
+			"corpusRows": 59871,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.3,
+			"drawnRows": 2074,
+			"emittedRows": 2160,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-nc",
+			"corpusRows": 51701,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.3,
+			"drawnRows": 1895,
+			"emittedRows": 1916,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "codex-bare-postcode",
+			"corpusRows": 17398,
+			"license": "Synthetic — bare-postcode; postcodes from OpenAddresses (per-source attribution in the model card)",
+			"weight": 1,
+			"drawnRows": 2239,
+			"emittedRows": 1775,
+			"augmentExcluded": true,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-yt",
+			"corpusRows": 51705,
+			"license": "Licence Ouverte 2.0",
+			"weight": 0.3,
+			"drawnRows": 1775,
+			"emittedRows": 1768,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-kz",
+			"corpusRows": 12781,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 1586,
+			"emittedRows": 1712,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fr-annuaire-education-overseas",
+			"corpusRows": 2825,
+			"license": "Licence Ouverte 2.0",
+			"weight": 4,
+			"drawnRows": 1484,
+			"emittedRows": 1493,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ua",
+			"corpusRows": 11730,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 1497,
+			"emittedRows": 1448,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-th",
+			"corpusRows": 8901,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 1155,
+			"emittedRows": 1295,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "fr-finess-overseas",
+			"corpusRows": 2395,
+			"license": "Licence Ouverte 1.0",
+			"weight": 4,
+			"drawnRows": 1250,
+			"emittedRows": 1281,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-mf",
+			"corpusRows": 7360,
+			"license": "Licence Ouverte 2.0",
+			"weight": 1,
+			"drawnRows": 953,
+			"emittedRows": 941,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ph",
+			"corpusRows": 7303,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 907,
+			"emittedRows": 893,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-pe",
+			"corpusRows": 6497,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 859,
+			"emittedRows": 840,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-dz",
+			"corpusRows": 6154,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 738,
+			"emittedRows": 833,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-my",
+			"corpusRows": 5948,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 713,
+			"emittedRows": 815,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-kw",
+			"corpusRows": 6403,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 794,
+			"emittedRows": 803,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-am",
+			"corpusRows": 5949,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 773,
+			"emittedRows": 775,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-co",
+			"corpusRows": 6290,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 850,
+			"emittedRows": 773,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-bl",
+			"corpusRows": 5545,
+			"license": "Licence Ouverte 2.0",
+			"weight": 1,
+			"drawnRows": 725,
+			"emittedRows": 769,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-pm",
+			"corpusRows": 3049,
+			"license": "Licence Ouverte 2.0",
+			"weight": 2,
+			"drawnRows": 715,
+			"emittedRows": 716,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ba",
+			"corpusRows": 5254,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 676,
+			"emittedRows": 688,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ban-pf",
+			"corpusRows": 6755,
+			"license": "Licence Ouverte 2.0",
+			"weight": 1,
+			"drawnRows": 663,
+			"emittedRows": 670,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bn",
+			"corpusRows": 3987,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 540,
+			"emittedRows": 510,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-uz",
+			"corpusRows": 3840,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 449,
+			"emittedRows": 505,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ir",
+			"corpusRows": 3731,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 487,
+			"emittedRows": 494,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "landregistry-im",
+			"corpusRows": 4156,
+			"license": "LicenseRef-IM-OGL",
+			"weight": 1,
+			"drawnRows": 441,
+			"emittedRows": 437,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "adressur-fo",
+			"corpusRows": 2776,
+			"license": "LicenseRef-FO-Umhvorvisstovan-Brukstreytir",
+			"weight": 1,
+			"drawnRows": 321,
+			"emittedRows": 358,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ge",
+			"corpusRows": 2759,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 355,
+			"emittedRows": 326,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-cu",
+			"corpusRows": 2383,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 316,
+			"emittedRows": 326,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-kg",
+			"corpusRows": 2531,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 284,
+			"emittedRows": 302,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "ryhti-ax",
+			"corpusRows": 2464,
+			"license": "CC-BY-4.0",
+			"weight": 1,
+			"drawnRows": 296,
+			"emittedRows": 292,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-lk",
+			"corpusRows": 1909,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 229,
+			"emittedRows": 269,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "bsp-gu",
+			"corpusRows": 1874,
+			"license": "Public Domain",
+			"weight": 1,
+			"drawnRows": 235,
+			"emittedRows": 267,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-hk",
+			"corpusRows": 2485,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 336,
+			"emittedRows": 250,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ma",
+			"corpusRows": 1941,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 251,
+			"emittedRows": 241,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ec",
+			"corpusRows": 1754,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 245,
+			"emittedRows": 233,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-pr",
+			"corpusRows": 1504,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 201,
+			"emittedRows": 218,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-gt",
+			"corpusRows": 1562,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 198,
+			"emittedRows": 204,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "opendata-az",
+			"corpusRows": 1510,
+			"license": "LicenseRef-CC-BY-unstated-version",
+			"weight": 1,
+			"drawnRows": 191,
+			"emittedRows": 191,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-az",
+			"corpusRows": 1338,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 185,
+			"emittedRows": 182,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-iq",
+			"corpusRows": 1295,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 148,
+			"emittedRows": 181,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mk",
+			"corpusRows": 1340,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 173,
+			"emittedRows": 157,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-tj",
+			"corpusRows": 948,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 126,
+			"emittedRows": 152,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bb",
+			"corpusRows": 925,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 126,
+			"emittedRows": 141,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-tn",
+			"corpusRows": 1115,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 131,
+			"emittedRows": 140,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "llv-li",
+			"corpusRows": 1114,
+			"license": "LicenseRef-LI-ABI-OGD-2",
+			"weight": 1,
+			"drawnRows": 165,
+			"emittedRows": 140,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-do",
+			"corpusRows": 1065,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 137,
+			"emittedRows": 139,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ci",
+			"corpusRows": 1346,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 165,
+			"emittedRows": 137,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-np",
+			"corpusRows": 1091,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 153,
+			"emittedRows": 135,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-sv",
+			"corpusRows": 961,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 100,
+			"emittedRows": 135,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-sa",
+			"corpusRows": 921,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 115,
+			"emittedRows": 127,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mn",
+			"corpusRows": 1005,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 115,
+			"emittedRows": 126,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-sm",
+			"corpusRows": 1071,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 135,
+			"emittedRows": 124,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-tm",
+			"corpusRows": 802,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 105,
+			"emittedRows": 124,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-gh",
+			"corpusRows": 1065,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 146,
+			"emittedRows": 120,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-al",
+			"corpusRows": 986,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 120,
+			"emittedRows": 120,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-gl",
+			"corpusRows": 805,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 108,
+			"emittedRows": 115,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mm",
+			"corpusRows": 902,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 103,
+			"emittedRows": 113,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-tz",
+			"corpusRows": 945,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 115,
+			"emittedRows": 109,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-cd",
+			"corpusRows": 990,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 119,
+			"emittedRows": 108,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bz",
+			"corpusRows": 769,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 96,
+			"emittedRows": 105,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-py",
+			"corpusRows": 761,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 81,
+			"emittedRows": 99,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mt",
+			"corpusRows": 850,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 126,
+			"emittedRows": 93,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ve",
+			"corpusRows": 935,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 123,
+			"emittedRows": 88,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-jm",
+			"corpusRows": 689,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 87,
+			"emittedRows": 86,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-me",
+			"corpusRows": 827,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 116,
+			"emittedRows": 84,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bm",
+			"corpusRows": 658,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 101,
+			"emittedRows": 76,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-pa",
+			"corpusRows": 605,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 78,
+			"emittedRows": 74,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-cr",
+			"corpusRows": 597,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 70,
+			"emittedRows": 74,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-cw",
+			"corpusRows": 535,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 68,
+			"emittedRows": 68,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ke",
+			"corpusRows": 419,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 64,
+			"emittedRows": 67,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ug",
+			"corpusRows": 552,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 73,
+			"emittedRows": 65,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-zw",
+			"corpusRows": 464,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 60,
+			"emittedRows": 59,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-na",
+			"corpusRows": 421,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 49,
+			"emittedRows": 59,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ht",
+			"corpusRows": 415,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 42,
+			"emittedRows": 57,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-kh",
+			"corpusRows": 505,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 53,
+			"emittedRows": 55,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-lb",
+			"corpusRows": 408,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 61,
+			"emittedRows": 55,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mz",
+			"corpusRows": 328,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 50,
+			"emittedRows": 53,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bt",
+			"corpusRows": 324,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 40,
+			"emittedRows": 46,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-aw",
+			"corpusRows": 314,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 35,
+			"emittedRows": 42,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-sn",
+			"corpusRows": 405,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 54,
+			"emittedRows": 41,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-sr",
+			"corpusRows": 385,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 49,
+			"emittedRows": 41,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-qa",
+			"corpusRows": 301,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 42,
+			"emittedRows": 41,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mg",
+			"corpusRows": 335,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 43,
+			"emittedRows": 38,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mv",
+			"corpusRows": 230,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 32,
+			"emittedRows": 35,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-ao",
+			"corpusRows": 350,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 41,
+			"emittedRows": 32,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-jo",
+			"corpusRows": 398,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 57,
+			"emittedRows": 31,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "gbpa-bs",
+			"corpusRows": 200,
+			"license": "CC-BY-4.0",
+			"weight": 1,
+			"drawnRows": 24,
+			"emittedRows": 31,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bh",
+			"corpusRows": 215,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 27,
+			"emittedRows": 29,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-pf",
+			"corpusRows": 308,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 44,
+			"emittedRows": 27,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bs",
+			"corpusRows": 173,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 27,
+			"emittedRows": 27,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-zm",
+			"corpusRows": 298,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 38,
+			"emittedRows": 26,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-je",
+			"corpusRows": 235,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 33,
+			"emittedRows": 26,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-rw",
+			"corpusRows": 228,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 28,
+			"emittedRows": 26,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-om",
+			"corpusRows": 212,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 27,
+			"emittedRows": 19,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-vi",
+			"corpusRows": 171,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 26,
+			"emittedRows": 16,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-bw",
+			"corpusRows": 172,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 25,
+			"emittedRows": 13,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-gg",
+			"corpusRows": 125,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 13,
+			"emittedRows": 13,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-mo",
+			"corpusRows": 100,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 15,
+			"emittedRows": 11,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm-lr",
+			"corpusRows": 55,
+			"license": "ODbL-1.0",
+			"weight": 1,
+			"drawnRows": 4,
+			"emittedRows": 2,
+			"augmentExcluded": false,
+			"excludedBecause": null
+		},
+		{
+			"source": "osm",
+			"corpusRows": 153965,
+			"license": "ODbL-1.0",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "usgov-imls-pls",
+			"corpusRows": 102451,
+			"license": "Public Domain",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "state-ia-contractors",
+			"corpusRows": 74682,
+			"license": "Public Domain",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "osm-cn",
+			"corpusRows": 51555,
+			"license": "ODbL-1.0",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "spliced-unit",
+			"corpusRows": 50000,
+			"license": "OpenAddresses and National Address Database US (non-VT) skeletons + injected USPS Pub-28 C2 unit designators",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "rendered-no-street-led",
+			"corpusRows": 12000,
+			"license": "Synthetic — no-street-led; (street, number, postcode, city) from OpenAddresses NO (per-source attribution in the model card)",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "fragment-fr-bare-street",
+			"corpusRows": 10803,
+			"license": "Synthetic — fr-bare-street; (street, number, city) from BAN (Base Adresse Nationale, Licence Ouverte)",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		},
+		{
+			"source": "rendered-cz-pcfirst-preposition",
+			"corpusRows": 8501,
+			"license": "Synthetic — cz-pcfirst-preposition; (street, number, postcode, city) from OpenAddresses CZ (per-source attribution in the model card)",
+			"weight": 0,
+			"drawnRows": 0,
+			"emittedRows": 0,
+			"augmentExcluded": false,
+			"excludedBecause": "zero-weight"
+		}
+	],
+	"trainingSources": [
+		"osm-ru",
+		"spliced-sub-venue",
+		"rendered-cz-pcfirst-preposition-v21",
+		"rendered-si-bare-village",
+		"fragment-fr-bare-street-v22",
+		"fragment-no",
+		"fragment-fr",
+		"invented-anchor-absorption",
+		"gleif-lei",
+		"gnaf",
+		"rendered-de",
+		"rendered-ch",
+		"rendered-nl-postcode",
+		"rendered-gb-os-open",
+		"rendered-hr",
+		"overture-latam",
+		"rendered-pt",
+		"rendered-sk",
+		"rendered-lu",
+		"rendered-fr-admin-split",
+		"tiger",
+		"fragment-assay",
+		"deepseek-kryptonite",
+		"rendered-sg-register",
+		"osm-in",
+		"osm-id",
+		"overture",
+		"rendered-pk-register",
+		"rendered-fr-order",
+		"osm-pk",
+		"ban",
+		"usgov-hrsa-fqhc",
+		"usgov-nppes",
+		"state-ny-notaries",
+		"spliced-country",
+		"spliced-affix",
+		"osm-vn",
+		"osm-eg",
+		"cordis",
+		"state-tx-notaries",
+		"invented-house-venue",
+		"spliced-suffix-boundary",
+		"spliced-trailing-region-ca-bare",
+		"spliced-unit-v30",
+		"osm-md",
+		"osm-rs",
+		"ads",
+		"lv-varis",
+		"wof-admin",
+		"invented-po-box-cedex",
+		"osm-ar",
+		"wof-postalcode",
+		"invented-po-box-military",
+		"spliced-trailing-region-es-v28",
+		"usgov-nad",
+		"rendered-bd-register",
+		"invented-intersection",
+		"ro-retea-scolara",
+		"osm-cl",
+		"ban-re",
+		"osm-by",
+		"ban-gp",
+		"osm-ae",
+		"osm-ng",
+		"osm-tt",
+		"spliced-trailing-region-us",
+		"osm-bd",
+		"ide-uy",
+		"ban-mq",
+		"ban-gf",
+		"ban-nc",
+		"codex-bare-postcode",
+		"ban-yt",
+		"osm-kz",
+		"fr-annuaire-education-overseas",
+		"osm-ua",
+		"osm-th",
+		"fr-finess-overseas",
+		"ban-mf",
+		"osm-ph",
+		"osm-pe",
+		"osm-dz",
+		"osm-my",
+		"osm-kw",
+		"osm-am",
+		"osm-co",
+		"ban-bl",
+		"ban-pm",
+		"osm-ba",
+		"ban-pf",
+		"osm-bn",
+		"osm-uz",
+		"osm-ir",
+		"landregistry-im",
+		"adressur-fo",
+		"osm-ge",
+		"osm-cu",
+		"osm-kg",
+		"ryhti-ax",
+		"osm-lk",
+		"bsp-gu",
+		"osm-hk",
+		"osm-ma",
+		"osm-ec",
+		"osm-pr",
+		"osm-gt",
+		"opendata-az",
+		"osm-az",
+		"osm-iq",
+		"osm-mk",
+		"osm-tj",
+		"osm-bb",
+		"osm-tn",
+		"llv-li",
+		"osm-do",
+		"osm-ci",
+		"osm-np",
+		"osm-sv",
+		"osm-sa",
+		"osm-mn",
+		"osm-sm",
+		"osm-tm",
+		"osm-gh",
+		"osm-al",
+		"osm-gl",
+		"osm-mm",
+		"osm-tz",
+		"osm-cd",
+		"osm-bz",
+		"osm-py",
+		"osm-mt",
+		"osm-ve",
+		"osm-jm",
+		"osm-me",
+		"osm-bm",
+		"osm-pa",
+		"osm-cr",
+		"osm-cw",
+		"osm-ke",
+		"osm-ug",
+		"osm-zw",
+		"osm-na",
+		"osm-ht",
+		"osm-kh",
+		"osm-lb",
+		"osm-mz",
+		"osm-bt",
+		"osm-aw",
+		"osm-sn",
+		"osm-sr",
+		"osm-qa",
+		"osm-mg",
+		"osm-mv",
+		"osm-ao",
+		"osm-jo",
+		"gbpa-bs",
+		"osm-bh",
+		"osm-pf",
+		"osm-bs",
+		"osm-zm",
+		"osm-je",
+		"osm-rw",
+		"osm-om",
+		"osm-vi",
+		"osm-bw",
+		"osm-gg",
+		"osm-mo",
+		"osm-lr"
+	],
+	"excludedSources": {
+		"osm": "zero-weight",
+		"usgov-imls-pls": "zero-weight",
+		"state-ia-contractors": "zero-weight",
+		"osm-cn": "zero-weight",
+		"spliced-unit": "zero-weight",
+		"rendered-no-street-led": "zero-weight",
+		"fragment-fr-bare-street": "zero-weight",
+		"rendered-cz-pcfirst-preposition": "zero-weight"
+	},
+	"emittedButUnrecorded": {},
+	"unrecordedSourceStages": {},
+	"totalEmittedRows": 1000000,
+	"contentDigest": "22e6f7e4643031069eef76a915c328857d0a5549da35220c5008aa8d3506c915"
+}