Generated 2026-09-27 20:20 UTC by scripts/dataset_stats.py. Everything below is derived data; the underlying QuickBooks and mailbox exports are not in the repo.
Gaps: the archive covers Jul 2026 -> now; the labelled mailbox goes back to Aug 2020 · 7 of 73 companies surveyed (one template for accounts; classes per company) · campus classifier under-attributes forwarded / reply / reminder messages (see edge cases)
By signal: docnum+vendor (6), filename+docnum+vendor+amount (4), filename+docnum+vendor (3), hash+vendor (2), docnum (1), hash+filename (1), hash+filename+docnum+vendor+amount (1), docnum+vendor+amount (1)
Campus label the classifier had given the matched messages: not_campus_specific (9), alpha_school_33155_llc (4), alpha_school_78746_llc_austin_k_8 (3), alpha_school_75010_llc_alpha_carrolton (2), alpha_school_78701_llc_alpha_high_school (1)
Cases a classifier trained on clean vendor invoices would get wrong. Counts are pairs.
62300 Facilities/Support:Repairs and Maintenance / Alpha Orange County — classifier said not_campus_specific; QuickBooks class is Alpha Orange County62304 Facilities/Support:Security Services / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami64100 Program:Apps / Alpha High School — classifier said not_campus_specific; QuickBooks class is Alpha High School62304 Facilities/Support:Security Services / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami62304 Facilities/Support:Security Services / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami63220 Program:Workshops / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami — classifier said not_campus_specific; QuickBooks class is Alpha Miami62300 Facilities/Support:Repairs and maintenance / Texas Sports Academy — classifier said not_campus_specific; QuickBooks class is Texas Sports Academy62300 Facilities/Support:Repairs and Maintenance / Alpha Orange County62304 Facilities/Support:Security Services / Alpha Miami62300 Facilities/Support:Repairs and maintenance / Alpha Miami62304 Facilities/Support:Security Services / Alpha Miami64100 Program:Apps / Alpha High School62304 Facilities/Support:Security Services / Alpha Miami63220 Program:Workshops / Alpha Miami62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami62300 Facilities/Support:Repairs and Maintenance / Alpha Orange County62304 Facilities/Support:Security Services / Alpha Miami64100 Program:Apps / Alpha High School62304 Facilities/Support:Security Services / Alpha Miami63220 Program:Workshops / Alpha Miami62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami62300 Facilities/Support:Repairs and maintenance / Carrolton Sports Academy62304 Facilities/Support:Security Services / Alpha High School62304 Facilities/Support:Security Services / Texas Sports Academy62304 Facilities/Support:Security Services / Alpha High School64100 Program:Apps / Alpha High School62304 Facilities/Support:Security Services / Alpha Miami62304 Facilities/Support:Security Services / Alpha Miami63220 Program:Workshops / Alpha Miami62304 Facilities/Support:Security Services / Alpha Miami — 2 messages about one bill64100 Program:Apps / Alpha High School — 2 messages about one bill62304 Facilities/Support:Security Services / Alpha Miami — 2 messages about one bill63220 Program:Workshops / Alpha Miami — 2 messages about one bill62303 Facilities/Support:Janitorial/Toiletry / Alpha Miami — 2 messages about one bill| mail uid | date | from | subject | campus label | bill | vendor | doc# | amount | account | class | signals |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 71411 | Wed, 23 Sep 2026 | Shawn Adli <shawn@skylinevis | Fwd: Open Invoices (Skyline Vision Secur | not_campus_specific | 1486 | Good Guard Security, Inc | 13308 | 5831.1 | 62304 Facilities/Support:Security | Alpha Miami | docnum |
| 71442 | Thu, 24 Sep 2026 | Jake Petersen <jake.petersen | Re: Fwd: Open Invoices (Skyline Vision S | not_campus_specific | 1486 | Good Guard Security, Inc | 13308 | 5831.1 | 62304 Facilities/Support:Security | Alpha Miami | docnum+vendor |
| 71526 | Thu, 24 Sep 2026 | United Site Services <receip | Your United Site Services receipt [#1214 | not_campus_specific | 2228 | United Site Services of Te | INV-6259533 | 1473.74 | 62300 Facilities/Support:Repairs a | Texas Sports Academy | docnum+vendor |
| 71439 | Wed, 23 Sep 2026 | KW Handyman Miami <kwhandyma | Re: Alpha School – Billing Reconciliatio | alpha_school_33155_llc | 4079 | KW HANDYMAN MIAMI | 42728 | 3005.0 | 62300 Facilities/Support:Repairs a | Alpha Miami | docnum+vendor+amount |
| 71413 | Wed, 23 Sep 2026 | "Watchmen Protective Service | Reminder: Invoice 12714 from Watchmen Pr | alpha_school_78746_llc_austin_k_8 | 340 | Watchmen Protective Servic | 12714 | 11471.79 | 62304 Facilities/Support:Security | Alpha High School | filename+docnum+vendor+amount |
| 71441 | Thu, 24 Sep 2026 | Mason Security Protective Se | Automated Payment Reminder – Invoice #10 | alpha_school_33155_llc | 6570 | Mason Security Protective | 1029 | 24377.28 | 62304 Facilities/Support:Security | Alpha Miami | docnum+vendor |
| 71479 | Thu, 24 Sep 2026 | Jake Petersen <jake.petersen | Re: Automated Payment Reminder – Invoice | not_campus_specific | 6570 | Mason Security Protective | 1029 | 24377.28 | 62304 Facilities/Support:Security | Alpha Miami | docnum+vendor |
| 71409 | Wed, 23 Sep 2026 | "Watchmen Protective Service | Reminder: Invoice 12745 from Watchmen Pr | alpha_school_78746_llc_austin_k_8 | 369 | Watchmen Protective Servic | 12745 | 9580.13 | 62304 Facilities/Support:Security | Alpha High School | filename+docnum+vendor+amount |
| 71410 | Wed, 23 Sep 2026 | "Watchmen Protective Service | Reminder: Invoice 12746 from Watchmen Pr | alpha_school_78746_llc_austin_k_8 | 2286 | Watchmen Protective Servic | 12746 | 6365.1 | 62304 Facilities/Support:Security | Texas Sports Academy | filename+docnum+vendor |
| 71418 | Wed, 23 Sep 2026 | "LanguageBird, Inc." <quickb | Invoice - Reminder: Your payment to Lang | not_campus_specific | 376 | LANGUAGEBIRD, INC | 1834 | 40684.0 | 64100 Program:Apps | Alpha High School | filename+docnum+vendor+amount |
| 71484 | Thu, 24 Sep 2026 | Chris Locke <chris.locke@alp | Fwd: Invoice - Reminder: Your payment to | alpha_school_78701_llc_alpha_high_school | 376 | LANGUAGEBIRD, INC | 1834 | 40684.0 | 64100 Program:Apps | Alpha High School | filename+docnum+vendor+amount |
| 71495 | Thu, 24 Sep 2026 | Accounting Department <accou | FW: PAST DUE INVOICES | not_campus_specific | 8067 | Nicolas Management Group, | 66196 | 194.43 | 62303 Facilities/Support:Janitoria | Alpha Miami | hash+vendor |
| 71497 | Thu, 24 Sep 2026 | Randall Grant <randall.grant | Fwd: PAST DUE INVOICES | not_campus_specific | 8067 | Nicolas Management Group, | 66196 | 194.43 | 62303 Facilities/Support:Janitoria | Alpha Miami | hash+vendor |
| 71443 | Thu, 24 Sep 2026 | Mason Security Protective Se | Automated Payment Reminder – Invoice #10 | alpha_school_33155_llc | 8109 | Mason Security Protective | 1035 | 11941.2 | 62304 Facilities/Support:Security | Alpha Miami | filename+docnum+vendor |
| 71444 | Thu, 24 Sep 2026 | Mason Security Protective Se | Automated Payment Reminder – Invoice #10 | alpha_school_33155_llc | 8110 | Mason Security Protective | 1036 | 3424.0 | 63220 Program:Workshops | Alpha Miami | filename+docnum+vendor |
| 71480 | Thu, 24 Sep 2026 | Jake Petersen <jake.petersen | Re: Automated Payment Reminder – Invoice | not_campus_specific | 8110 | Mason Security Protective | 1036 | 3424.0 | 63220 Program:Workshops | Alpha Miami | docnum+vendor |
| 71401 | 23 Sep 2026 14:5 | "Amanda McClary" <amanda@tec | Invoice #82121 for Sports Academy 75010 | alpha_school_75010_llc_alpha_carrolton | 808 | Tech-Scape Inc. | #82121 | 2992.64 | 62302 Facilities/Support:Landscapi | Carrolton Sports Academy | hash+filename |
| 71391 | Wed, 23 Sep 2026 | White Rock Air Conditioning | New payment request from White Rock Air | alpha_school_75010_llc_alpha_carrolton | 806 | White Rock Air Conditionin | 9668 | 746.93 | 62300 Facilities/Support:Repairs a | Carrolton Sports Academy | hash+filename+docnum+vendor+amount |
| 71396 | Wed, 23 Sep 2026 | Steve Dorfman <steve.dorfman | Re: Invoice #2177494 | not_campus_specific | 764 | Sonitrol Orange County, LL | 2177494 | 233.29 | 62300 Facilities/Support:Repairs a | Alpha Orange County | docnum+vendor |
Per month (messages, of which linked to a bill):
| month | messages | linked to a bill | share |
|---|---|---|---|
| 2026-06 | 29 | 3 | 10% |
| 2026-07 | 3665 | 375 | 10% |
| 2026-08 | 4445 | 367 | 8% |
| 2026-09 | 5108 | 454 | 9% |
Origin, all messages: employee forward (3821), employee thread (2789), vendor direct (2772), vendor platform (1873), vendor reply (1233), system (759)
Origin, messages that became bills: employee forward (509), vendor platform (266), vendor direct (216), employee thread (120), vendor reply (80), system (8)
billing@ was: neither (3107), to (8826), cc (1314)
Human labels: 2551 messages carry an AP workflow-state label, 9636 a Vendor/ label, 77 a not-AP label. Top labels: Approved (1692), Posted (546), Vendor Onboarded (405), Onboarded (242), Pending from BU (196), Awaiting Approval (160), Alpha Team (93), **Syft (89), Tuition and other Fees Queries (77), Pending from AP Team (65)
Top Vendor/ labels: Intuit (515), Worksmith, Inc. (299), XTIUM, Inc. (259), Scoot Education Inc. (219), CTTS, Inc. (184), Good Guard Security, Inc. (177), Skyline Vision Security Alliance (169), SCHOOL EATERY (166), Hubspot (165), Nicolas Management Group, Inc. (134), WATCHMEN PROTECTIVE SDERVICES LLC (128), Mason Security (128), AMAZON BUSINESS (125), Cintas Corporation (125), FPL (112)
Linked messages by company: Alpha School 33155, LLC (449), Sports Academy 75010, LLC (CSA) (235), Alpha School 78701, LLC (Alpha High School) (177), Sports Academy 78734, LLC (TSA) (129), Alpha School 78521, LLC (Brownsville) (111), Alpha School 92610, LLC (Orange County) (98); 99 messages touch more than one company.
Mail ↔ bill join over the archive: 2102 strong pairs, 451 bills matched; bill already in QuickBooks at arrival: {'True': 1375, 'False': 727}. By signal: vendor+amount (584), docnum+vendor+amount (325), docnum+vendor (312), hash+filename+vendor (294), docnum (172), hash+filename+docnum+vendor+amount (119), hash+filename+docnum+vendor (72), hash+filename (58), filename+vendor (44), filename+docnum+vendor+amount (40), filename+docnum+vendor (19), hash+filename+vendor+amount (17)
Bills matched by company: Alpha School 33155, LLC (132), Sports Academy 75010, LLC (CSA) (106), Alpha School 78701, LLC (Alpha High School) (71), Alpha School 78521, LLC (Brownsville) (64), Sports Academy 78734, LLC (TSA) (52), Alpha School 92610, LLC (Orange County) (26)
Top sender domains (all / linked): alpha.school (3785), trilogy.com (2706), notification.intuit.com (761), intuit.com (344), appcenter.intuit.com (327), gmail.com (305), worksmith.com (231), cttsonline.com (188) / alpha.school (423), notification.intuit.com (244), trilogy.com (205), worksmith.com (49), nmanagementgroup.com (29), gmail.com (19), stripe.com (16), yahoo.com (14)
Alpha School 33155, LLC realm 9341452781248173
991 bills, 1175 lines, ['2024-07-01', '2026-10-01']; 90 active accounts, 11 classes, 133 vendors, 6 POs. Dominant class Alpha Miami on 99.5% of lines; 15 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 1175}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 11510 Tangible Assets | 237 |
| 62300 Facilities/Support:Repairs and maintenance | 210 |
| 62303 Facilities/Support:Janitorial/Toiletry | 114 |
| 62304 Facilities/Support:Security Services | 100 |
| 63220 Program:Workshops | 98 |
| 62400 Facilities/Support:Utilities | 95 |
| 62302 Facilities/Support:Landscaping | 60 |
| 61300 Administration:Marketing | 51 |
| 62600 Food Services:Lunch Program | 50 |
| 62301 Facilities/Support:IT Maintenance | 32 |
Bills per month (last 6): 2026-05 52, 2026-06 35, 2026-07 28, 2026-08 38, 2026-09 28, 2026-10 1
Sports Academy 78734, LLC (TSA) realm 9341452844510916
405 bills, 580 lines, ['2024-07-09', '2026-09-21']; 85 active accounts, 8 classes, 87 vendors, 2 POs. Dominant class Texas Sports Academy on 100.0% of lines; 15 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 580}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 62300 Facilities/Support:Repairs and maintenance | 132 |
| 62303 Facilities/Support:Janitorial/Toiletry | 97 |
| 11510 Tangible Assets | 88 |
| 62400 Facilities/Support:Utilities | 54 |
| 62302 Facilities/Support:Landscaping | 50 |
| 62304 Facilities/Support:Security Services | 31 |
| 62301 Facilities/Support:IT Maintenance | 28 |
| 61300 Administration:Marketing | 19 |
| 21100 Prepaid expenses | 15 |
| 63220 Program:Workshops | 13 |
Bills per month (last 6): 2026-04 56, 2026-05 15, 2026-06 9, 2026-07 10, 2026-08 11, 2026-09 20
Sports Academy 75010, LLC (CSA) realm 9341452845377673
298 bills, 308 lines, ['2024-07-19', '2026-09-25']; 77 active accounts, 6 classes, 55 vendors, 0 POs. Dominant class Carrolton Sports Academy on 99.4% of lines; 13 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 308}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 62300 Facilities/Support:Repairs and maintenance | 90 |
| 62303 Facilities/Support:Janitorial/Toiletry | 67 |
| 62302 Facilities/Support:Landscaping | 39 |
| 11510 Tangible Assets | 38 |
| 62304 Facilities/Support:Security Services | 30 |
| 62400 Facilities/Support:Utilities | 21 |
| 62100 Other Expenses:Renovations/Furnishings | 7 |
| 61210 Administration:Professional Fees | 4 |
| 61600 Administration:Office supplies | 3 |
| 62301 Facilities/Support:IT Maintenance | 3 |
Bills per month (last 6): 2026-04 30, 2026-05 21, 2026-06 22, 2026-07 18, 2026-08 23, 2026-09 21
Alpha School 92610, LLC (Orange County) realm 9341455755640825
62 bills, 74 lines, ['2025-12-13', '2026-10-01']; 86 active accounts, 6 classes, 30 vendors, 0 POs. Dominant class Alpha Orange County on 100.0% of lines; 9 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 74}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 11510 Tangible Assets | 17 |
| 63220 Program:Workshops | 13 |
| 60220 Administration:Contracted Labor - Campus Administration | 10 |
| 62303 Facilities/Support:Janitorial/Toiletry | 9 |
| 62300 Facilities/Support:Repairs and Maintenance | 7 |
| 62600 Food Services:Lunch Program | 7 |
| 61400 Administration:Meals and Entertainment | 5 |
| 62400 Facilities/Support:Utilities | 3 |
| 62304 Facilities/Support:Security Services | 3 |
Bills per month (last 6): 2026-05 5, 2026-06 2, 2026-07 4, 2026-08 6, 2026-09 14, 2026-10 1
Alpha School 78701, LLC (Alpha High School) realm 9341456032003663
144 bills, 215 lines, ['2026-01-01', '2026-09-25']; 84 active accounts, 6 classes, 34 vendors, 0 POs. Dominant class Alpha High School on 99.5% of lines; 15 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 215}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 62300 Facilities/Support:Repairs and Maintenance | 69 |
| 62304 Facilities/Support:Security Services | 32 |
| 62303 Facilities/Support:Janitorial/Toiletry | 28 |
| 62600 Food Services:Lunch Program | 12 |
| 11510 Tangible Assets | 11 |
| 61600 Administration:Office Supplies | 10 |
| 21100 Prepaid expenses | 10 |
| 63220 Program:Workshops | 9 |
| 62200 Facilities/Support:Rent | 8 |
| 64100 Program:Apps | 7 |
Bills per month (last 6): 2026-04 16, 2026-05 17, 2026-06 13, 2026-07 10, 2026-08 17, 2026-09 21
Alpha School 78521, LLC (Brownsville) realm 9341456032410115
230 bills, 254 lines, ['2026-01-01', '2026-09-26']; 84 active accounts, 6 classes, 38 vendors, 0 POs. Dominant class Brownsville K-8 on 100.0% of lines; 15 distinct accounts used on bills; line types {'AccountBasedExpenseLineDetail': 254}.
Top accounts on bill lines:
| account | lines |
|---|---|
| 62300 Facilities/Support:Repairs and Maintenance | 48 |
| 63220 Program:Workshops | 48 |
| 62303 Facilities/Support:Janitorial/Toiletry | 40 |
| 62600 Food Services:Lunch Program | 27 |
| 61400 Administration:Meals and Entertainment | 21 |
| 62304 Facilities/Support:Security Services | 18 |
| 61600 Administration:Office Supplies | 16 |
| 62302 Facilities/Support:Landscaping | 13 |
| 60214 Program:Contracted Labor - Coaches - Asst. Guide | 8 |
| 11510 Tangible Assets | 6 |
Bills per month (last 6): 2026-04 34, 2026-05 24, 2026-06 22, 2026-07 7, 2026-08 21, 2026-09 25
Alpha School 75010, LLC (Alpha Carrolton) realm 9341457865184016
0 bills, 0 lines, None; 73 active accounts, 4 classes, 5 vendors, 0 POs. Dominant class None on 0.0% of lines; 0 distinct accounts used on bills; line types {}.
Top accounts on bill lines:
| account | lines |
|---|
Bills per month (last 6):
Workflow-state labels: Awaiting Onboarding (45), Onboarded (246), Vendor Onboarded (409), Awaiting Approval (160), Approved (1695), *Bill verification (15), Pending from BU (202), Pending from AP Team (69), *For Payment (249), *Pending NS Posting (162), Posted (592), **Pending for approval (5)
Largest folders:
| folder | messages | oldest | newest |
|---|---|---|---|
| [Gmail]/All Mail | 79223 | 2020-08-25 | 2026-09-27 |
| [Gmail]/Important | 46894 | 2020-08-25 | 2026-09-27 |
| [Gmail]/Sent Mail | 20141 | 2020-08-26 | 2026-09-27 |
| Tuition and other Fees Queries | 2904 | 2021-12-20 | 2026-09-22 |
| Vendor/Worksmith, Inc. | 1874 | 2022-12-08 | 2026-09-22 |
| Alpha Team | 1769 | 2021-07-28 | 2026-09-23 |
| Approved | 1695 | 2026-08-31 | 2026-09-01 |
| Vendor/CTTS, Inc. | 1617 | 2025-04-22 | 2026-09-17 |
| Trilogy Query | 1305 | 2022-02-28 | 2026-02-11 |
| Vendor/Cintas Corporation | 1069 | 2022-04-13 | 2026-09-25 |
| Vendor/Intuit | 1018 | 2024-07-24 | 2026-09-27 |
| INBOX | 1010 | 2025-12-16 | 2026-09-27 |
| Vendor/City of Austin Utilities | 887 | 2021-12-08 | 2026-09-26 |
| Vendor/Good Guard Security, Inc. | 817 | 2025-09-16 | 2026-09-27 |
| Vendor/Slack | 745 | 2022-12-19 | 2026-09-27 |
| Vendor/Hubspot | 649 | 2024-07-26 | 2026-09-26 |
| **Syft | 646 | 2024-11-14 | 2026-09-26 |
| [Gmail]/Trash | 622 | 2026-08-28 | 2026-09-22 |
| Vendor/Nellie's Cakes &- Snack Bar | 598 | 2023-09-07 | 2026-09-20 |
| Posted | 592 | 2026-09-14 | 2026-09-25 |
Largest Vendor/ folders: Worksmith, Inc. (1874), CTTS, Inc. (1617), Cintas Corporation (1069), Intuit (1018), City of Austin Utilities (887), Good Guard Security, Inc. (817), Slack (745), Hubspot (649), Nellie's Cakes &- Snack Bar (598), Neftali Tavares (580), CONVERGINT TECHNOLOGIES LLC (548), Spectrum Business (528), Husch Blackwell LLP (521), Nicolas Management Group, Inc. (510), *1-One Time Vendor (509)
Attachment types: pdf (87), png (78), jpg (8), xlsx (2)
Message kinds: reply/forward (59), from internal address (36), original (41), sent via QuickBooks (13)
Origin (did the vendor send it, or did an employee forward it?): vendor direct (19), vendor reply (19), employee forward (18), employee thread (18), vendor platform (17), system (9)
billing@ was: to (74), cc (25), neither (1)
Original senders behind employee forwards: xtium.com (4), central-vendor-management.kayako.com (3), eliotsantos.com (2), trilogy.com (2), samlp.com (1), bencharchitecture.com (1), valleyalarm.com (1), skylinevisionsecurity.com (1), notification.intuit.com (1), gmail.com (1)
Top sender domains: trilogy.com (29), notification.intuit.com (13), alpha.school (7), accounts.google.com (5), valleyalarm.com (4), gmail.com (4), alpha-school-support.kayako.com (3), stripe.com (3), xtium.com (3), fastsigns.com (3)
Confidence buckets: ≥0.9 (55), 0.7–0.9 (24), 0.5–0.7 (16), <0.5 (5)
Labels: not_campus_specific (52), alpha_school_78521_llc_brownsville (7), alpha_school_78746_llc_austin_k_8 (6), alpha_school_92610_llc_orange_county (6), other_alpha_campus (5), alpha_school_33155_llc (4), alpha_school_75010_llc_alpha_carrolton (3), alpha_school_00692_llc_dorado (3), alpha_school_90265_llc_alpha_malibu (2), alpha_early_center_10038_llc_alpha_early_center_fin_district (2), nova_academy_78723_llc_nova_austin (2), alpha_school_78701_llc_alpha_high_school (2)