christian/helmdocs-proposal-system
1
0
Fork 0
Code Issues 8 Pull Requests Actions Packages Projects Releases Wiki Activity

Add three synthesized Friendship PCS responses with ground truth

Browse Source 
Covers all nine stress cases from #25, #15 and #16. The lowest bid is
disqualified on two missing health documents and the highest bid is
strongest on the SFA's own geographic-preference criterion, so a ranking
that cannot represent absence gets the field exactly backwards.

Deliberate traps: a planted $400 arithmetic error in a stated total, an
unverifiable total whose unit price lives only in the external Excel, an
unlabelled exception, a non-priceable exception that is really a conditional
withdrawal, and an answered-but-negative response.

Second schema finding, surfaced by the validator: R-B6C is a mandatory gate
that no response document can establish. Coverage over it is unknowable
rather than absent.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Christian
2026-08-03 18:39:08 -04:00
parent e81da40947
commit 19e7ffe92a
9 changed files with 1509 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
corpus/friendship-pcs/NOTES.md
View File

@@ -63,3 +63,62 @@ present, its content is not, and no amount of better PDF parsing recovers it.
149 × "shall", 64 × "must" across 52 pages. An earlier ad-hoc extraction reported 149 × "shall", 64 × "must" across 52 pages. An earlier ad-hoc extraction reported
zero of each; that was the extractor failing, not the document. zero of each; that was the extractor failing, not the document.
---
# Response set
Three synthesized responses in `responses/source/`, each paired with a truth
file. Designed so the field has a real outcome rather than three
interchangeable bids.
| Vendor | Binding | Price | Gates | Distinguishing feature |
|---|---|---|---|---|
| Potomac Provisions | tabbed compliance matrix | $589,970 | PASS | Complete; volume-banded pricing; 18% local |
| Chesapeake Food Service | free prose, no anchors | $541,280 | **FAIL** | Cheapest and disqualified; unlabelled exception |
| Anacostia Farm Collective | named sections + enumeration | $624,315 | PASS | 61% local; three labelled exceptions; seasonal pricing |
The lowest bid is disqualified and the highest bid is strongest on the
criterion the SFA wrote into its own rubric. That is deliberate: a ranking
that cannot represent absence puts Chesapeake first.
## Deliberate traps
**Planted arithmetic error (Potomac).** The stated base-year total is
$589,970; band price times scenario volume is $589,570. A $400 gap. #15
decision 2 puts all price arithmetic in code precisely so a stated total is
never trusted over a computed one — this is the case that catches an
extractor lifting the vendor's own figure.
**Unverifiable total (Chesapeake).** The case price exists only in the
external Excel sheet, so no computed total can be produced at all. Contrast
Potomac, where the arithmetic can be checked and fails.
**Unlabelled exception (Chesapeake).** A price-relief request phrased as
politeness inside the Pricing section, with no heading and no delta.
Anacostia's three exceptions are explicitly headed with deltas and act as
the control.
**Non-priceable exception (Anacostia, EX-3).** If declined, the vendor
cannot bid produce at all — a conditional withdrawal expressed as an
exception. A price-delta field cannot hold it.
**Answered-but-negative (Anacostia).** "We are not currently an approved
USDA Foods processor." Squarely answers the requirement; the substance is a
disclosure of inability. Coverage and quality are orthogonal, and a system
that scores this like Potomac's 340,000 lbs is broken.
**Three certifications in one sentence (Chesapeake).** Attachments B, C and
D are satisfied by a single clause naming all three. A per-requirement
extractor must split one span three ways.
## Finding: a gate that no response document can satisfy
`R-B6C` — "Two bid copies submitted" — is a physical submission fact.
Potomac happens to assert it; the other two do not, and no better extraction
would change that. Coverage over it is neither answered nor not_answered but
**unknowable from the artifact**.
Surfaced by `validate-responses.py`, not by design. Treating it as
not_answered would disqualify two of three bidders over a packaging detail.
Raised against #10.

102
corpus/friendship-pcs/responses/anacostia-farm-collective.truth.json Normal file
View File

@@ -0,0 +1,102 @@
{
"$comment": "Ground truth for source/anacostia-farm-collective.md. Mid-gradient binding, and the exceptions case.",
"vendor": { "id": "ANACOSTIA", "name": "Anacostia Farm Collective", "location": "Washington, DC (Ward 8)" },
"bindingMechanism": {
"level": "named_section_with_partial_enumeration",
"$comment": "#22's middle tier. Four required sections are correctly titled and an enclosures paragraph enumerates artifacts with RFP references inline — but there is no matrix, so gates bind by name while narrative requirements bind only by section."
},
"expectedOutcome": {
"gatesPassed": true,
"narrative": "All gates satisfied. Highest price at $624,315, or $652,465 if exceptions 1 and 2 are declined. Strongest on geographic preference by a wide margin (61% vs 18%), openly weakest on USDA Foods, and materially below the field on organizational scale. The right award depends entirely on how the SFA weights local content against price — which is the judgement the retailer is supposed to make and the system is not."
},
"answers": [
{ "requirementId": "R-A1", "coverage": "answered", "evidence": "Cover block present" },
{ "requirementId": "R-A2", "coverage": "indeterminate", "evidence": "Enclosures paragraph enumerates items in checklist order but is not the checklist form itself" },
{ "requirementId": "R-B2-LOCAL", "coverage": "answered", "evidence": "61% certified; audit right accepted; certification enclosed under B.2", "value": { "localPercent": 61 } },
{ "requirementId": "R-B6C", "coverage": "not_answered", "evidence": null },
{ "requirementId": "R-B6D", "coverage": "answered", "evidence": "DC Department of Health food establishment certificate, exp. 2022-06-30" },
{ "requirementId": "R-B7-FORMAT", "coverage": "answered", "evidence": "Four sections, titles exact" },
{ "requirementId": "R-B8-QUEST", "coverage": "answered", "evidence": "References provided in questionnaire" },
{ "requirementId": "R-B8-LICENSE", "coverage": "answered", "evidence": "DC BBL 410203000891" },
{ "requirementId": "R-B8-OCCUPANCY", "coverage": "answered", "evidence": "Enclosed" },
{ "requirementId": "R-B8-FINANCIALS", "coverage": "answered", "evidence": "FY2019 and FY2020, Mercer Group CPAs" },
{ "requirementId": "R-C1-VALUES", "coverage": "answered", "evidence": "Explicit 'Response to values statement (C.1)' subsection in Section Four" },
{ "requirementId": "R-C5-INSPECTIONS", "coverage": "answered", "evidence": "2020-09-22 and 2021-01-14, both passed" },
{ "requirementId": "R-D6-INSURANCE", "coverage": "answered", "evidence": "Certificate of insurance enclosed",
"$comment": "Enclosed but NO AMOUNTS STATED, unlike the other two bidders. The requirement is 'Insurance amounts.' A strict reading makes this indeterminate; a lenient one accepts the certificate. Deliberately left ambiguous — it is the kind of call that should reach a human." },
{ "requirementId": "R-SCHED-C", "coverage": "answered", "evidence": "Submitted on Schedule C in the Excel workbook" },
{ "requirementId": "R-ATT-A", "coverage": "answered", "evidence": "Supplies four DC charter SFAs under HSA; certification designed to support the local sourcing subsidy claim" },
{ "requirementId": "R-ATT-B", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-ATT-C", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-ATT-D", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-E1-EEO", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-E3-CLEANAIR", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-USDA-FOODS", "coverage": "answered",
"evidence": "'This is our weakest area and we will not overstate it. We are not currently an approved USDA Foods processor.'",
"$comment": "ANSWERED, and answered in the NEGATIVE. The requirement is squarely addressed; the substance is a disclosure of inability. A system that treats 'answered' as 'satisfied' scores this identically to Potomac's 340,000 lbs. It must not." },
{ "requirementId": "R-C8-FARM2SCHOOL", "coverage": "answered", "evidence": "34 member farms in the Chesapeake foodshed; two within the District" },
{ "requirementId": "R-C7-QA", "coverage": "answered", "evidence": "Farm-level GAP certification, annual audit, credit at receipt" },
{ "requirementId": "R-C5-FOODSAFETY", "coverage": "answered", "evidence": "DC DoH certified facility; inspections enclosed" },
{ "requirementId": "R-C6-PEST", "coverage": "answered", "evidence": "Licensed applicator monthly, semi-annual third-party audit" },
{ "requirementId": "R-CN-LABELS", "coverage": "answered",
"evidence": "'Whole produce does not carry CN labels; for those items we supply the crediting documentation the meal pattern requires.'",
"$comment": "A QUALIFIED answer — satisfies the requirement for processed items and explains why it cannot for whole produce. Neither fully answered nor a gap." },
{ "requirementId": "R-D1-DELIVERY", "coverage": "answered", "evidence": "Addressed, and subject to Exception 1 on delivery windows",
"hasException": "EX-1" },
{ "requirementId": "R-B5-PRICING-TERMS", "coverage": "answered", "evidence": "Firm within stated bands", "hasException": "EX-2" },
{ "requirementId": "R-D8-EPA", "coverage": "answered", "evidence": "Renegotiation of the out-of-region band, per Exception 2", "hasException": "EX-2" },
{ "requirementId": "R-C4-MENUS", "coverage": "not_answered", "evidence": null },
{ "requirementId": "R-D3-RECORDS", "coverage": "not_answered", "evidence": null }
],
"priceQuote": {
"rateStructure": {
"kind": "seasonal_piecewise",
"$comment": "The hardest of the three, and the one most likely to break a naive model. Cost depends on WHEN volume falls, not only how much — so derived_cost cannot be computed without the school calendar. #22 found exactly this shape in the wild (SLC rent varying by contract year and sales threshold).",
"unit": "case",
"baseProduceCasePrice": 31.20,
"appliesTo": "produce only; grocery, dairy and protein are flat on Schedule C",
"bands": [
{ "id": "peak_regional", "months": [6, 7, 8, 9, 10], "multiplier": 0.88 },
{ "id": "shoulder", "months": [4, 5, 11], "multiplier": 1.00 },
{ "id": "out_of_region", "months": [12, 1, 2, 3], "multiplier": 1.19 }
],
"requiresCalendar": true,
"$calendarNote": "The 180-day school calendar falls disproportionately outside the peak band — the vendor says so explicitly. Any cost comparison that ignores the calendar flatters this bid."
},
"statedBaseYearTotal": 624315,
"statedTotalIfExceptionsDeclined": 652465,
"$verify": "624315 + 18400 + 9750 = 652465. Internally consistent. Contrast Potomac's planted $400 error."
},
"exceptions": [
{
"id": "EX-1", "labelled": true, "requirementId": "R-D1-DELIVERY",
"text": "Delivery windows beginning no earlier than 6:30 AM at all sites; Schedule A specifies several beginning at 5:30 AM.",
"priceDeltaIfDeclined": 18400,
"$comment": "A hard operational conflict with Schedule A, not a preference."
},
{
"id": "EX-2", "labelled": true, "requirementId": "R-B5-PRICING-TERMS",
"text": "Out-of-region band subject to renegotiation if PPI for fresh vegetables moves more than 12% between award and 1 December.",
"priceDeltaIfDeclined": 9750
},
{
"id": "EX-3", "labelled": true, "requirementId": null,
"targetSection": "C.3",
"text": "Pack configuration agreed during onboarding rather than fixed at award, produce categories only.",
"priceDeltaIfDeclined": null,
"isBidWithdrawalCondition": true,
"$comment": "NOT PRICEABLE. If declined the vendor cannot bid produce at all — a conditional withdrawal expressed as an exception. A price-delta field cannot hold it, and a system that models exceptions purely as monetary adjustments loses the most consequential one of the three. It also targets a requirement the RFP truth file does not enumerate (C.3 Specifications), which is itself a finding."
}
],
"extractionDifficulty": {
"expectRecall": "medium",
"$comment": "Gates bind reliably via the enclosures paragraph. Narrative requirements bind by section only. The exceptions block is explicitly headed and should extract cleanly — it is the control against which Chesapeake's unlabelled exception is measured."
}
}

237
corpus/friendship-pcs/responses/chesapeake-food-service.truth.json Normal file
View File

@@ -0,0 +1,237 @@
{
"$comment": "Ground truth for source/chesapeake-food-service.md. The hard end of the binding gradient.",
"vendor": {
"id": "CHESAPEAKE",
"name": "Chesapeake Food Service, Inc.",
"location": "Baltimore, MD"
},
"bindingMechanism": {
"level": "free_prose",
"$comment": "#22's least reliable tier. Four sections exist but carry no requirement-level anchors, no RFP references and no matrix. Recovering which sentence answers which requirement is text classification, not structural lookup. This is the document that will expose extraction weakness."
},
"expectedOutcome": {
"gatesPassed": false,
"failedGates": [
"R-B6D",
"R-C5-INSPECTIONS"
],
"atRiskGates": [
"R-B2-LOCAL",
"R-C1-VALUES",
"R-A2"
],
"narrative": "Lowest price in the field at $541,280 and DISQUALIFIED regardless, on two missing mandatory health documents. This is the case that proves absence must be representable — a ranking that scores it on price alone puts a disqualified bid at the top."
},
"answers": [
{
"requirementId": "R-A1",
"coverage": "answered",
"evidence": "Cover block present"
},
{
"requirementId": "R-A2",
"coverage": "not_answered",
"evidence": null,
"$comment": "No checklist is reproduced anywhere."
},
{
"requirementId": "R-B6D",
"coverage": "not_answered",
"evidence": null,
"isGateFailure": true,
"$comment": "THE PRIMARY OMISSION. A current state or local health certificate is never mentioned. Not refused, not deferred — simply absent. The response lists many enclosures, which makes the absence easy for a human to miss and is exactly why coverage must be computed per requirement rather than eyeballed."
},
{
"requirementId": "R-C5-INSPECTIONS",
"coverage": "not_answered",
"evidence": null,
"isGateFailure": true,
"$comment": "Two most recent health inspections never mentioned. The response DOES discuss pest management at the same facility, which is topically adjacent and will tempt a weak extractor into a false positive."
},
{
"requirementId": "R-B2-LOCAL",
"coverage": "indeterminate",
"evidence": "'Chesapeake buys from the Maryland and Delmarva growing region in season... We would expect a meaningful proportion of produce delivered between June and October to originate within the region.'",
"$comment": "Addresses the TOPIC warmly and satisfies none of the OBLIGATION — no percentage, no certification, no acceptance of the audit right. This is KM-2's requirement meeting a response that gestures at it. The hardest coverage call in the corpus."
},
{
"requirementId": "R-C1-VALUES",
"coverage": "indeterminate",
"evidence": "'We are committed to student nutrition and to the communities we serve' — one clause in the Executive Summary, under no heading.",
"$comment": "Exercises KM-3 from the response side. Whether this constitutes a 'response to values statement' is a judgement, not a lookup."
},
{
"requirementId": "R-B6C",
"coverage": "not_answered",
"evidence": null
},
{
"requirementId": "R-B7-FORMAT",
"coverage": "answered",
"evidence": "Four sections present",
"$comment": "Section three is titled 'Method of Approach and Implementation', dropping 'Plan'. Near-miss on a required section title — a strict matcher fails, a fuzzy one passes."
},
{
"requirementId": "R-B8-QUEST",
"coverage": "answered",
"evidence": "'Three references are provided in the questionnaire' — implies completion, never states it"
},
{
"requirementId": "R-B8-LICENSE",
"coverage": "answered",
"evidence": "'Our business license and certificate of occupancy are enclosed'"
},
{
"requirementId": "R-B8-OCCUPANCY",
"coverage": "answered",
"evidence": "Same sentence as the business license"
},
{
"requirementId": "R-B8-FINANCIALS",
"coverage": "answered",
"evidence": "Two years audited, Hanlon & Reeve LLP"
},
{
"requirementId": "R-D6-INSURANCE",
"coverage": "answered",
"evidence": "$2M per occurrence / $4M aggregate, FPCS as additional insured"
},
{
"requirementId": "R-ATT-B",
"coverage": "answered",
"evidence": "'debarment, price determination and lobbying certifications are signed and enclosed'"
},
{
"requirementId": "R-ATT-C",
"coverage": "answered",
"evidence": "Same sentence"
},
{
"requirementId": "R-ATT-D",
"coverage": "answered",
"evidence": "Same sentence",
"$comment": "THREE separate certification requirements satisfied by ONE sentence naming all three. A per-requirement extractor must split one span three ways."
},
{
"requirementId": "R-E1-EEO",
"coverage": "answered",
"evidence": "'as are the equal opportunity and clean air and water certifications'"
},
{
"requirementId": "R-E3-CLEANAIR",
"coverage": "answered",
"evidence": "Same sentence"
},
{
"requirementId": "R-SCHED-C",
"coverage": "answered",
"evidence": "'submitted separately on the Excel schedule provided'"
},
{
"requirementId": "R-USDA-FOODS",
"coverage": "answered",
"evidence": "'We participate in the USDA Foods programme in Maryland... our processing relationships are stronger in the protein categories than in fruit and vegetable.'",
"$comment": "ANSWERED but WEAK. Coverage and quality are orthogonal — a correct extraction marks this answered and a correct score marks it low. Conflating them is a defect."
},
{
"requirementId": "R-CN-LABELS",
"coverage": "answered",
"evidence": "'category managers hold CN labels and formulation statements... typically within two business days of a request'"
},
{
"requirementId": "R-C6-PEST",
"coverage": "answered",
"evidence": "'licensed applicator, serviced monthly'"
},
{
"requirementId": "R-D1-DELIVERY",
"coverage": "answered",
"evidence": "Site survey of all eight locations; delivery window confirmed with authorised designee"
},
{
"requirementId": "R-B5-PRICING-TERMS",
"coverage": "answered",
"evidence": "'Prices are held firm through the base year'"
},
{
"requirementId": "R-D8-EPA",
"coverage": "answered",
"evidence": "'relief... in the event of a commodity movement exceeding eight percent'"
},
{
"requirementId": "R-C5-FOODSAFETY",
"coverage": "indeterminate",
"evidence": "Pest management is described; no GFSI, SQF or equivalent certification is claimed.",
"$comment": "Partial. The requirement asks for a food safety programme and the response supplies one component of one."
},
{
"requirementId": "R-ATT-A",
"coverage": "indeterminate",
"evidence": "'the District's Healthy Schools Act obligations' named in passing, no compliance detail"
},
{
"requirementId": "R-C7-QA",
"coverage": "not_answered",
"evidence": null
},
{
"requirementId": "R-C8-FARM2SCHOOL",
"coverage": "not_answered",
"evidence": null
},
{
"requirementId": "R-C4-MENUS",
"coverage": "not_answered",
"evidence": null
},
{
"requirementId": "R-D3-RECORDS",
"coverage": "not_answered",
"evidence": null
}
],
"priceQuote": {
"rateStructure": {
"kind": "flat_unit_plus_frequency_surcharge",
"$comment": "Exercises #29 differently from Potomac. Cost depends on a variable the SFA controls per site and may change mid-term with two weeks' notice — so derived_cost is only defined against a declared frequency assumption, and the response states one.",
"unit": "case",
"flatUnitPrice": null,
"$note": "Unit case price lives only in the external Excel sheet — the KM-1 shape again, this time making the vendor's own stated total unverifiable from the document alone.",
"perStopCharge": [
{
"deliveriesPerWeek": 2,
"chargePerStop": 34.0
},
{
"deliveriesPerWeek": 3,
"chargePerStop": 28.5
},
{
"deliveriesPerWeek": 4,
"chargePerStop": 24.0
}
],
"frequencyChangeableWithNotice": "2 weeks"
},
"statedBaseYearTotal": 541280,
"statedAssumptions": {
"deliveriesPerWeek": 3,
"sites": 8,
"calendarDays": 180
},
"$verify": "UNVERIFIABLE from this document. The case price is absent, so no computed total can be produced — only the vendor's stated figure exists. Contrast Potomac, where the arithmetic can be checked and fails."
},
"exceptions": [
{
"id": "IMPLICIT-1",
"labelled": false,
"requirementId": "R-B5-PRICING-TERMS",
"text": "We would ask only for relief under the economic price adjustment provision in the event of a commodity movement exceeding eight percent",
"$comment": "AN UNLABELLED EXCEPTION. It is phrased as a polite request inside the Pricing section, carries no heading, no price delta and no 'exception' wording. Compare Anacostia, which labels three exceptions explicitly with deltas. #22 called exceptions the thing evaluators care most about and the thing an invented corpus always forgets — this is the version that is present but hidden."
}
],
"extractionDifficulty": {
"expectRecall": "low",
"$comment": "No anchors of any kind. Expect false positives on R-C5-INSPECTIONS from adjacent pest-management prose, and expect the three-certifications-in-one-sentence span to be split incorrectly or attributed to only one requirement."
}
}

90
corpus/friendship-pcs/responses/potomac-provisions.truth.json Normal file
View File

@@ -0,0 +1,90 @@
{
"$comment": "Ground truth for source/potomac-provisions.md. Answers key to rfp.truth.json requirement ids.",
"vendor": { "id": "POTOMAC", "name": "Potomac Provisions LLC", "location": "Landover, MD" },
"bindingMechanism": {
"level": "tabbed_restatement",
"$comment": "#22's most reliable tier. A compliance matrix restates each RFP reference explicitly, giving a near-guaranteed 1:1 join key. This is the easy end of the gradient and should extract almost perfectly."
},
"expectedOutcome": {
"gatesPassed": true,
"narrative": "Complete and responsive. Strongest on USDA Foods and dependability, weakest on geographic preference at 18%. Should win on completeness rather than on any single criterion."
},
"answers": [
{ "requirementId": "R-A1", "coverage": "answered", "evidence": "Compliance matrix row A.1 — Complete, signed" },
{ "requirementId": "R-A2", "coverage": "answered", "evidence": "Compliance matrix row A.2" },
{ "requirementId": "R-B2-LOCAL", "coverage": "answered", "evidence": "18% certified; audit right accepted", "value": { "localPercent": 18 } },
{ "requirementId": "R-B6C", "coverage": "answered", "evidence": "Two bid copies provided" },
{ "requirementId": "R-B6D", "coverage": "answered", "evidence": "Prince George's County health certificate, exp. 2022-03-31" },
{ "requirementId": "R-B7-FORMAT", "coverage": "answered", "evidence": "Four titled sections present" },
{ "requirementId": "R-B8-QUEST", "coverage": "answered", "evidence": "Pre-Qualification Questionnaire complete" },
{ "requirementId": "R-B8-LICENSE", "coverage": "answered", "evidence": "MD SDAT D14882910" },
{ "requirementId": "R-B8-OCCUPANCY", "coverage": "answered", "evidence": "Attached" },
{ "requirementId": "R-B8-FINANCIALS", "coverage": "answered", "evidence": "FY2019 and FY2020 audited" },
{ "requirementId": "R-C1-VALUES", "coverage": "answered", "evidence": "Section Four, 'Response to values statement' — explicit heading" },
{ "requirementId": "R-C5-INSPECTIONS", "coverage": "answered", "evidence": "2020-11-04 and 2021-02-17, both passed" },
{ "requirementId": "R-D6-INSURANCE", "coverage": "answered", "evidence": "$2M per occurrence / $4M aggregate" },
{ "requirementId": "R-SCHED-C", "coverage": "answered", "evidence": "Submitted in Excel as instructed; structure summarised in Section Two",
"$comment": "The RESPONSE references pricing correctly, but the actual price sheet is outside this document — the same KM-1 shape on the response side." },
{ "requirementId": "R-ATT-A", "coverage": "answered", "evidence": "HSA acknowledged, Section Three" },
{ "requirementId": "R-ATT-B", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-ATT-C", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-ATT-D", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-E1-EEO", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-E3-CLEANAIR", "coverage": "answered", "evidence": "Signed" },
{ "requirementId": "R-C5-FOODSAFETY", "coverage": "answered", "evidence": "GFSI-certified under SQF Level 2" },
{ "requirementId": "R-C6-PEST", "coverage": "answered", "evidence": "Licensed applicator, monthly service, quarterly third-party audit" },
{ "requirementId": "R-C7-QA", "coverage": "answered", "evidence": "USDA No. 1 or better; driver authorised to credit at receipt" },
{ "requirementId": "R-C8-FARM2SCHOOL", "coverage": "indeterminate", "evidence": "Local sourcing addressed at 18%, but Farm to School participation as such is never mentioned",
"$comment": "The topic is adjacent and the requirement is not squarely answered. This is the coverage state that most needs a human." },
{ "requirementId": "R-USDA-FOODS", "coverage": "answered", "evidence": "Approved processor-distributor MD and DC; 340,000 lbs processed SY2020-21" },
{ "requirementId": "R-CN-LABELS", "coverage": "answered", "evidence": "Portal per-item document library; bulk PDF per menu cycle" },
{ "requirementId": "R-D1-DELIVERY", "coverage": "answered", "evidence": "Freight to all eight sites within Schedule A windows" },
{ "requirementId": "R-D8-EPA", "coverage": "answered", "evidence": "PPI-based, at contract anniversary only" },
{ "requirementId": "R-B5-PRICING-TERMS", "coverage": "answered", "evidence": "Prices firm for base year" },
{ "requirementId": "R-D3-RECORDS", "coverage": "not_answered", "evidence": null,
"$comment": "Narrative requirement, not a gate — no disqualification, but it is a real gap in an otherwise complete response." },
{ "requirementId": "R-C4-MENUS", "coverage": "not_answered", "evidence": null }
],
"priceQuote": {
"rateStructure": {
"kind": "volume_banded",
"$comment": "Exercises #29. Retroactive year-end rebate — the applicable band is not knowable at order time, only at year end, which means derived_cost must be computed against the DECLARED scenario volume rather than observed.",
"unit": "case",
"listPrice": 28.40,
"bands": [
{ "minCases": 0, "maxCases": 11999, "discountPercent": 0.0, "effectiveUnitPrice": 28.40 },
{ "minCases": 12000, "maxCases": 23999, "discountPercent": 3.0, "effectiveUnitPrice": 27.55 },
{ "minCases": 24000, "maxCases": 35999, "discountPercent": 5.5, "effectiveUnitPrice": 26.84 },
{ "minCases": 36000, "maxCases": null, "discountPercent": 7.5, "effectiveUnitPrice": 26.27 }
],
"freightIncluded": true,
"fuelSurcharge": false,
"minimumOrderCharge": false
},
"statedBaseYearTotal": 589970,
"statedAtScenarioVolume": 21400,
"$verify": "21400 cases falls in band 2 (12000-23999) at 27.55 -> 21400 * 27.55 = 589,570. The document states 589,970. DELIBERATE 400 DISCREPANCY — see arithmeticTraps."
},
"exceptions": [],
"arithmeticTraps": [
{
"id": "AT-1",
"where": "Section Two, base year total",
"$comment": "The stated total ($589,970) does not equal band price x scenario volume ($589,570). A $400 gap. Planted deliberately: #15 decision 2 puts all price arithmetic in code precisely so a stated total is never trusted over a computed one. An extractor that lifts the vendor's stated figure reports the wrong number and nothing catches it.",
"statedTotal": 589970,
"computedTotal": 589570,
"delta": 400
}
],
"extractionDifficulty": {
"expectRecall": "very high",
"$comment": "The compliance matrix gives explicit RFP references. Failure here indicates a table-parsing defect rather than a binding problem."
}
}

184
corpus/friendship-pcs/responses/source/anacostia-farm-collective.md Normal file
View File

@@ -0,0 +1,184 @@
# ANACOSTIA FARM COLLECTIVE
## Response to RFP — Supply and Delivery of Food Items
### Friendship Public Charter School, SY 2021–2022
2214 Martin Luther King Jr Ave SE, Washington, DC 20020
Yolanda Reyes, Managing Director — (202) 555-0173
---
## Section One — Executive Summary
Anacostia Farm Collective is a District-based food hub aggregating from
thirty-four farms within the Chesapeake foodshed. We were formed in 2014
specifically to make regionally grown food available to institutions that
want it and cannot reach it through conventional broadline distribution.
We currently supply eleven institutional accounts including four DC public
charter schools.
We are the smallest bidder Friendship is likely to consider, and we want to
be direct about what that means. We will not be the cheapest bid. What we
offer is the highest local content available in this market and a supply
relationship that is legible all the way back to the farm.
**Enclosures.** Business license (DC BBL 410203000891); Certificate of
Occupancy; audited financial statements FY2019 and FY2020, prepared by
Mercer Group CPAs; current DC Department of Health food establishment
certificate, expiring 2022-06-30; our two most recent health inspections,
dated 2020-09-22 and 2021-01-14, both passed; certificate of insurance;
Attachments B, C and D signed; equal opportunity and clean air and water
certifications signed; certification of local percentage under B.2.
**Exceptions.** We take three exceptions to the solicitation as issued.
They are set out in full at the end of this response with the price effect
of each. We would rather state them plainly now than discover them at
contract execution.
---
## Section Two — Pricing
Submitted on Schedule C in the Excel workbook provided.
**Rate structure: seasonal piecewise unit pricing.** Because our supply is
regional and genuinely seasonal, a single annual unit price would require
us to carry the winter cost of out-of-region sourcing across the whole
year. Instead we price produce in three seasonal bands. Non-produce
categories — grocery, dairy, protein — are priced flat.
| Band | Months | Produce index | Basis |
|---|---|---|---|
| Peak regional | June – October | 0.88 × base | in-region supply at volume |
| Shoulder | April – May, November | 1.00 × base | mixed regional and contracted |
| Out-of-region | December – March | 1.19 × base | sourced outside foodshed |
Base delivered produce case price, mixed: $31.20. Grocery, dairy and
protein are quoted flat on Schedule C.
Applying the band weighting across the 180-day school calendar — which
falls disproportionately in the shoulder and out-of-region bands — our
**base year total bid cost is $624,315.**
We recognise this is materially above the likely low bid, and roughly six
percent above what we would guess the middle of this field looks like. We
believe the local content justifies it against the Geographic Preference
criterion and against the Healthy Schools Act local provisions, and we
would rather present an honest seasonal structure than a flat price that
conceals the same economics.
Prices firm for the base year within the stated bands.
---
## Section Three — Method of Approach and Implementation Plan
### Food and packaging
Produce is packed to USDA No. 1. Because we aggregate from multiple farms,
pack configuration varies more than a broadline distributor's would, and we
would agree standard configurations with the SFA during onboarding rather
than assume them. Every case is labelled with the originating farm.
Quality assurance is farm-level: each member farm carries GAP certification
and we audit annually. Any item rejected at receipt is credited on the
delivery ticket.
CN labels and formulation statements are held for all processed and grocery
items and are provided through our shared drive per account. Whole produce
does not carry CN labels; for those items we supply the crediting
documentation the meal pattern requires.
### Utilization of USDA Foods
This is our weakest area and we will not overstate it. We are not currently
an approved USDA Foods processor. We would work alongside a processor
designated by the SFA, or support the SFA in managing entitlement directly,
but we cannot manage drawdown and diversion in-house today.
### Geographic preference
**Sixty-one percent (61%)** of the product value we propose to supply will
be locally grown or raised within 250 miles of Washington, DC, measured
across the full contract year. In the peak regional band that figure
exceeds eighty percent. Certification of the percentage is enclosed under
B.2 and we accept the SFA's audit right.
All thirty-four member farms are within the Chesapeake foodshed; nineteen
are in Maryland, nine in Virginia, four in Delaware and two within the
District itself.
### Healthy Schools Act
We supply four DC charter SFAs under HSA requirements today and our
certification of local percentage is designed to support the SFA's local
sourcing subsidy claim directly.
---
## Section Four — Bidder's Experience, Expertise and Reliability
**Knowledge of USDA and District requirements.** Our operations lead spent
six years in DC OSSE child nutrition administration. We are fluent in the
HSA and in the meal pattern; we are less fluent in USDA Foods entitlement
mechanics, as stated above.
**Dependability.** On-time delivery for SY2020–21 was 96.1% against
contracted windows, and order fill accuracy 97.4% by line. Both are below
what a broadline distributor will quote. The gap is almost entirely
weather-driven crop shortfall in the peak band, where we substitute within
category rather than fail the line.
**Warehouse and facilities.** Our aggregation facility on Martin Luther
King Jr Avenue is DC Department of Health certified. Two most recent
inspections enclosed, both passed. Pest management is contracted monthly
with a licensed applicator and audited semi-annually.
**Customer service.** Named account lead, orders by phone, email or shared
order sheet until 3:00 PM for next-day. The managing director is reachable
directly and is on the escalation path for every account.
**Proven organizational capacity.** Seven years in operation, eleven
institutional accounts, thirty-four member farms. Our largest current
account is three sites. **Friendship's eight sites would be the largest
network we have served**, and we would staff a dedicated route and a
second driver for it, funded within the pricing above.
**Response to values statement (C.1).** Friendship's values statement
speaks to educational outcomes and to the community the school sits in. We
are based in Ward 8, we employ from Ward 8, and two of our member farms are
inside the District. When Friendship spends with us, a measurable share of
that spend stays within the same community the students come from. That is
the whole reason the Collective exists, and it is why we are bidding
despite being the highest price on the table.
**References.** Three DC institutional accounts, provided in the
questionnaire.
---
## Exceptions and Qualifications
We take the following three exceptions to the solicitation as issued.
**Exception 1 — D.1 Delivery Requirements, delivery windows.**
Schedule A specifies delivery windows at several sites beginning at 5:30
AM. Our aggregation model consolidates farm deliveries overnight and we
cannot reliably load before 5:00 AM. We request windows beginning no
earlier than 6:30 AM at all sites.
*Price effect if not granted: +$18,400 (second overnight shift).*
**Exception 2 — B.5, price firmness across the full term.**
We request that the out-of-region band (December–March) be subject to
renegotiation if the published PPI for fresh vegetables moves more than
twelve percent between award and 1 December. Our regional supply cannot
absorb that movement the way a national distributor's can.
*Price effect if not granted: +$9,750 (risk premium carried in base).*
**Exception 3 — C.3 Specifications, pack configuration.**
We request that pack configuration be agreed jointly during onboarding
rather than fixed at award, for produce categories only. Aggregated supply
cannot guarantee a single fixed pack across thirty-four farms.
*Price effect if not granted: we would be unable to bid produce categories.*
Total price effect of exceptions 1 and 2 if declined: **+$28,150**, giving
an adjusted base year total bid cost of **$652,465**.

118
corpus/friendship-pcs/responses/source/chesapeake-food-service.md Normal file
View File

@@ -0,0 +1,118 @@
# Chesapeake Food Service, Inc.
## Proposal to Friendship Public Charter School — Food Items, 2021–2022
1120 Ridgely Street, Baltimore, MD 21230
Marcus Bell, Vice President — (410) 555-0188
---
### Executive Summary
Chesapeake Food Service is a family-owned broadline distributor operating
out of Baltimore since 1978. We serve roughly two hundred accounts across
Maryland and the District, of which about thirty are schools, and we are
pleased to offer Friendship Public Charter School the most competitive
delivered pricing in this market.
Our proposition is straightforward. We buy well, we run lean, and we pass
that through. Where other distributors in this bid will layer on portal
technology and account management structures that ultimately appear in the
case price, we have chosen to compete on the number that matters. Over an
eight-site network across a full school year, the difference is
substantial, and it is money that returns directly to the meal programme.
Our business license and certificate of occupancy are enclosed, along with
two years of audited financial statements prepared by Hanlon & Reeve LLP.
The debarment, price determination and lobbying certifications are signed
and enclosed, as are the equal opportunity and clean air and water
certifications. Insurance is carried at two million per occurrence and four
million aggregate and a certificate naming Friendship Public Charter School
as additional insured is enclosed.
We are committed to student nutrition and to the communities we serve, and
we believe strongly that a school food programme succeeds or fails on
consistency of supply rather than on marketing. That is the value we bring.
### Pricing
Our pricing is submitted separately on the Excel schedule provided.
We price at a flat delivered unit cost per case with no volume tiers and no
rebate mechanism, because we have found that banded pricing chiefly serves
to make comparison difficult and to defer benefit to year end. Our number
is our number from day one.
Delivered case pricing is applied as quoted plus a per-stop delivery charge
which varies with the frequency requested. At two deliveries per week per
site, the charge is $34.00 per stop. At three per week it falls to $28.50
per stop, and at four or more it falls to $24.00 per stop. Sites may elect
different frequencies and may change frequency with two weeks' notice.
At the estimated volume stated in the solicitation and assuming three
deliveries weekly to each of the eight sites across a one hundred and
eighty day calendar, our base year total bid cost is five hundred and
forty-one thousand, two hundred and eighty dollars ($541,280).
Prices are held firm through the base year. We would ask only for relief
under the economic price adjustment provision in the event of a commodity
movement exceeding eight percent, on the same published index basis
contemplated in the solicitation.
### Method of Approach and Implementation
We would begin with a site survey of all eight locations in the two weeks
following award, walking each receiving area with the site's authorised
designee to confirm the delivery window, the receiving point and the
storage capacity. Our experience is that most transition problems are
receiving problems rather than supply problems, and they are best solved
before the first delivery rather than after.
Product is packed to USDA standards throughout. We have not historically
found that schools require pack size changes from our standard
configurations, but we would accommodate reasonable requests where our
suppliers can support them.
On nutritional documentation, our category managers hold CN labels and
formulation statements for the school product range and provide these on
request. We can supply these for any item in the proposed catalogue,
typically within two business days of a request.
We participate in the USDA Foods programme in Maryland and would work with
the SFA to make appropriate use of entitlement, though we would note that
our processing relationships are stronger in the protein categories than
in fruit and vegetable. We think it right to be plain about that rather
than to overstate it.
As to local sourcing, Chesapeake buys from the Maryland and Delmarva
growing region in season and has done so throughout its history. We are
proud of those relationships. We would expect a meaningful proportion of
produce delivered between June and October to originate within the region.
We maintain a pest management programme at our Baltimore facility under
contract with a licensed applicator, serviced monthly.
### Bidder's Experience, Expertise and Reliability
Forty-three years in continuous operation under the same family ownership
is, we would suggest, its own evidence of dependability. We have never
failed to complete work awarded to us and we have never been terminated for
cause.
We deliver on time. Our internal measurement for the last school year was
in the high nineties by percentage, and we are comfortable being held to
that standard contractually.
Our staff know the USDA meal pattern requirements and the District's
Healthy Schools Act obligations, and several of our account team have
worked with DC schools for more than a decade.
We would provide a single point of contact for the network with escalation
directly to the undersigned. We do not operate an ordering portal; orders
are placed by telephone or email to a named person, which our customers
tell us they prefer.
Three references are provided in the questionnaire, all Maryland school
accounts.
We appreciate the opportunity and would welcome the chance to discuss any
element of this proposal with the committee.

170
corpus/friendship-pcs/responses/source/potomac-provisions.md Normal file
View File

@@ -0,0 +1,170 @@
# POTOMAC PROVISIONS LLC
### Response to Friendship Public Charter School
### RFP for the Supply and Delivery of Food Items, SY 2021–2022
8600 Ardwick-Ardmore Road, Landover, MD 20785 · (301) 555-0142
Contact: Denise Whitaker, Director of Education Accounts
---
## SECTION ONE — EXECUTIVE SUMMARY
Potomac Provisions has distributed to School Food Authorities in the
Washington metropolitan area since 1994. We currently serve 41 SFAs across
DC, Maryland and Northern Virginia, including 11 public charter networks,
and deliver approximately 2.3 million cases annually from a single
GFSI-certified warehouse in Landover.
### Compliance Matrix
Per Section A.2, every required item is enumerated below with the page of
this response on which it appears.
| RFP Ref | Requirement | Status | Page |
|---|---|---|---|
| A.1 | Cover Page | Complete, signed | 1 |
| A.2 | Bidder Checklist | Complete | 2 |
| B.2 | Certification of percentage of local foods | Complete — 18% certified | 3 |
| B.6(c) | Two bid copies | Provided | — |
| B.6(d) | Current state or local health certificate | Attached, Prince George's County, exp. 2022-03-31 | A-1 |
| B.7 | Four-section format | This document | — |
| B.8 | Distributor Pre-Qualification Questionnaire | Complete | 4 |
| B.8 | Business license | Attached, MD SDAT D14882910 | A-2 |
| B.8 | Certificate of Occupancy | Attached | A-3 |
| B.8 | Two years audited financial statements | Attached, FY2019 & FY2020 | A-4 |
| C.1 | Response to values statement | Section Four | 7 |
| C.5 | Two most recent health inspections | Attached, 2020-11-04 and 2021-02-17, both passed | A-5 |
| D.6 | Insurance amounts | Certificate attached, $2M/$4M | A-6 |
| Schedule C | Pricing Sheet | Submitted in Excel as instructed | — |
| Att. A | Healthy Schools Act requirements | Acknowledged, Section Three | 5 |
| Att. B | Debarment & Suspension | Signed | A-7 |
| Att. C | Independent Price Determination | Signed | A-8 |
| Att. D | Certification Regarding Lobbying | Signed | A-9 |
| E.1 | Equal Opportunity | Signed | A-10 |
| E.3 | Clean Air and Water Certification | Signed | A-11 |
No exceptions are taken to any term or condition of this solicitation.
---
## SECTION TWO — PRICING
Pricing is submitted on Schedule C in the Excel workbook provided, as
instructed. The structure is summarised here for the evaluation committee.
**Rate structure: volume-banded unit pricing.** Unit price per case falls as
aggregate annual volume across all eight sites rises. Bands are measured on
total cases invoiced in the contract year and applied retroactively at
year end as a rebate.
| Annual case volume | Discount from list | Illustrative delivered case price, mixed produce |
|---|---|---|
| 0 – 11,999 cases | list | $28.40 |
| 12,000 – 23,999 cases | 3.0% | $27.55 |
| 24,000 – 35,999 cases | 5.5% | $26.84 |
| 36,000+ cases | 7.5% | $26.27 |
Delivered price includes freight to all eight sites within the delivery
windows in Schedule A. There is no separate fuel surcharge and no minimum
order charge.
**Base year total bid cost, at FPCS's stated estimated volume of 21,400
cases: $589,970.**
Prices are firm for the base year. Economic price adjustment is requested
only as permitted under D.8, on the published PPI for the relevant
commodity group, and only at contract anniversary.
---
## SECTION THREE — METHOD OF APPROACH AND IMPLEMENTATION PLAN
### Food and packaging
All produce is packed to USDA No. 1 or better. Case configurations follow
the SFA's existing pack sizes so that no menu re-costing is required at
transition. Product acceptance issues are credited on the delivery ticket
at the point of receipt; the driver is authorised to credit without a
return authorisation.
CN labels and product formulation statements are supplied through our
online portal, which exposes a per-item document library. Every catalogue
item carries its CN label, nutrient analysis and allergen statement, and
these are downloadable in bulk as a single PDF per menu cycle. This is how
we make nutritional information available to the SFA as required in B.7.
### Utilization of USDA Foods
We are an approved processor-distributor for USDA Foods in both Maryland
and the District. We manage entitlement drawdown, diversion and pass-through
value directly, and provide a monthly entitlement position statement.
For SY2020–21 we processed 340,000 lbs of USDA-donated commodity on behalf
of DC-area SFAs.
### Geographic preference
Eighteen percent (18%) of the product value we propose to supply to FPCS
will be locally grown or raised, defined as originating within 250 miles
of Washington, DC. Certification of this percentage is provided under B.2.
We accept the SFA's right to audit the actual percentage once awarded.
We are candid that 18% is a function of our scale and our year-round
service commitment: we will not substitute a local item where continuity
of supply cannot be guaranteed across the full school year.
### Healthy Schools Act
We have supplied DC SFAs under HSA requirements since 2010 and are familiar
with the local meal reimbursement conditions in Attachment A, including the
whole-grain-rich and local-sourcing provisions.
---
## SECTION FOUR — BIDDER'S EXPERIENCE, EXPERTISE AND RELIABILITY
### Knowledge of USDA and District requirements
Our education accounts team includes two staff who previously worked in
SFA operations. We complete DC OSSE reporting alongside our SFA customers
each year.
### Dependability
Our on-time delivery rate across all SFA accounts for SY2020–21 was 98.6%,
measured against contracted delivery windows. Order fill accuracy was
99.2% by line. Both figures are drawn from our WMS and can be audited.
### Warehouse and facilities
Our Landover facility is GFSI-certified under SQF Level 2. The two most
recent health inspections, both passed with no critical violations, are
attached under C.5. Our stored products pest management programme is
operated under contract by a licensed applicator with monthly service and
quarterly third-party audit, per C.6.
### Customer service
Each SFA has a named account manager and a named backup. Orders may be
placed through the portal or by phone until 2:00 PM for next-day delivery.
Credits are issued within one business day.
### Proven organizational capacity
Twenty-seven years in operation. 2.3 million cases annually. We have run
eight-site or larger charter networks continuously since 2011, and our
audited financials for FY2019 and FY2020 are attached.
### Response to values statement (C.1)
FPCS's stated commitment to student nutrition as a driver of educational
outcomes matches how we run our education accounts. We staff them
separately from our commercial business precisely because the buying
calendar, the compliance burden and the tolerance for substitution are
different. We are interested in this business because eight sites under one
authority is the scale at which menu consistency actually becomes
achievable.
### References
Three SFA references are provided in the Pre-Qualification Questionnaire,
all DC or Prince George's County charter networks of comparable size.

526
corpus/friendship-pcs/rfp.truth.json
View File

@@ -6,7 +6,6 @@
"", "",
"Requirement ids are stable and are what response truth files answer against." "Requirement ids are stable and are what response truth files answer against."
], ],
"solicitation": { "solicitation": {
"title": "Request for Proposal for the Supply and Delivery of Food Items", "title": "Request for Proposal for the Supply and Delivery of Food Items",
"issuer": "Friendship Public Charter School", "issuer": "Friendship Public Charter School",
@@ -14,10 +13,16 @@
"issueDate": "2021-03-15", "issueDate": "2021-03-15",
"closingDate": "2021-04-16", "closingDate": "2021-04-16",
"pages": 52, "pages": 52,
"programContext": ["NSLP", "SBP", "ASSP", "FFVP", "CACFP", "SFSP"], "programContext": [
"NSLP",
"SBP",
"ASSP",
"FFVP",
"CACFP",
"SFSP"
],
"siteCount": 8 "siteCount": 8
}, },
"bindingMechanism": { "bindingMechanism": {
"level": "named_section", "level": "named_section",
"$comment": [ "$comment": [
@@ -27,42 +32,151 @@
"This is the single most important fact about scoring this document." "This is the single most important fact about scoring this document."
], ],
"requiredSections": [ "requiredSections": [
{ "ordinal": 1, "title": "Executive Summary", "mapsToCriterion": null }, {
{ "ordinal": 2, "title": "Pricing", "mapsToCriterion": "PRICING" }, "ordinal": 1,
{ "ordinal": 3, "title": "Method of Approach and Implementation Plan", "mapsToCriterion": "METHOD" }, "title": "Executive Summary",
{ "ordinal": 4, "title": "Bidder's Experience, Expertise and Reliability", "mapsToCriterion": "EXPERIENCE" } "mapsToCriterion": null
},
{
"ordinal": 2,
"title": "Pricing",
"mapsToCriterion": "PRICING"
},
{
"ordinal": 3,
"title": "Method of Approach and Implementation Plan",
"mapsToCriterion": "METHOD"
},
{
"ordinal": 4,
"title": "Bidder's Experience, Expertise and Reliability",
"mapsToCriterion": "EXPERIENCE"
}
] ]
}, },
"ratingScale": { "ratingScale": {
"$comment": "Per-document, never normalised (#10, #22). The prose anchor is load-bearing, not the integer.", "$comment": "Per-document, never normalised (#10, #22). The prose anchor is load-bearing, not the integer.",
"min": 0, "min": 0,
"max": 5, "max": 5,
"anchors": [ "anchors": [
{ "points": 0, "label": "Completely Deficient", "anchor": "Elements is missing or is completely nonresponsive to the request" }, {
{ "points": 1, "label": "Unsatisfactory", "anchor": "Fails to meet minimum requirements; major deficiencies which are not correctable" }, "points": 0,
{ "points": 2, "label": "Below Average", "anchor": "Marginally meets minimum requirements; significant deficiencies which may be correctable" }, "label": "Completely Deficient",
{ "points": 3, "label": "Average", "anchor": "Meets requirements; only minor deficiencies which are correctable" }, "anchor": "Elements is missing or is completely nonresponsive to the request"
{ "points": 4, "label": "Very Good", "anchor": "Meets requirements; no deficiencies" }, },
{ "points": 5, "label": "Exceptional", "anchor": "Exceeds most, if not all requirements; no deficiencies" } {
"points": 1,
"label": "Unsatisfactory",
"anchor": "Fails to meet minimum requirements; major deficiencies which are not correctable"
},
{
"points": 2,
"label": "Below Average",
"anchor": "Marginally meets minimum requirements; significant deficiencies which may be correctable"
},
{
"points": 3,
"label": "Average",
"anchor": "Meets requirements; only minor deficiencies which are correctable"
},
{
"points": 4,
"label": "Very Good",
"anchor": "Meets requirements; no deficiencies"
},
{
"points": 5,
"label": "Exceptional",
"anchor": "Exceeds most, if not all requirements; no deficiencies"
}
] ]
}, },
"criteria": [ "criteria": [
{ "id": "PRICING", "parentId": null, "label": "Pricing", "maxPoints": 40, "page": 37 }, {
{ "id": "METHOD", "parentId": null, "label": "Method of Approach and Implementation", "maxPoints": 30, "page": 37 }, "id": "PRICING",
{ "id": "FOOD_PACKAGING", "parentId": "METHOD", "label": "Food and Packaging (Appearance, Quality, Taste and Acceptance)", "maxPoints": 15, "page": 37 }, "parentId": null,
{ "id": "USDA_FOODS", "parentId": "METHOD", "label": "Utilization of USDA Foods", "maxPoints": 10, "page": 37 }, "label": "Pricing",
{ "id": "GEO_PREF", "parentId": "METHOD", "label": "Geographic preference — locally grown or raised foods", "maxPoints": 5, "page": 37 }, "maxPoints": 40,
{ "id": "EXPERIENCE", "parentId": null, "label": "Bidder's Experience, Expertise, & Reliability", "maxPoints": 20, "page": 37 }, "page": 37
{ "id": "EXP_KNOWLEDGE", "parentId": "EXPERIENCE", "label": "Knowledge of USDA, District requirements", "maxPoints": 5, "page": 37 }, },
{ "id": "EXP_DEPENDABILITY", "parentId": "EXPERIENCE", "label": "Dependability (on-time deliveries, accuracy filling orders)", "maxPoints": 5, "page": 37 }, {
{ "id": "EXP_WAREHOUSE", "parentId": "EXPERIENCE", "label": "Inspection of warehouse and other facilities", "maxPoints": 5, "page": 37 }, "id": "METHOD",
{ "id": "EXP_SERVICE", "parentId": "EXPERIENCE", "label": "Customer Service", "maxPoints": 5, "page": 37 }, "parentId": null,
{ "id": "ORG_CAPACITY", "parentId": null, "label": "Proven Organizational Capacity", "maxPoints": 5, "page": 38 }, "label": "Method of Approach and Implementation",
{ "id": "COMMUNITY", "parentId": null, "label": "Community Connection, Values Alignment", "maxPoints": 5, "page": 38 } "maxPoints": 30,
"page": 37
},
{
"id": "FOOD_PACKAGING",
"parentId": "METHOD",
"label": "Food and Packaging (Appearance, Quality, Taste and Acceptance)",
"maxPoints": 15,
"page": 37
},
{
"id": "USDA_FOODS",
"parentId": "METHOD",
"label": "Utilization of USDA Foods",
"maxPoints": 10,
"page": 37
},
{
"id": "GEO_PREF",
"parentId": "METHOD",
"label": "Geographic preference — locally grown or raised foods",
"maxPoints": 5,
"page": 37
},
{
"id": "EXPERIENCE",
"parentId": null,
"label": "Bidder's Experience, Expertise, & Reliability",
"maxPoints": 20,
"page": 37
},
{
"id": "EXP_KNOWLEDGE",
"parentId": "EXPERIENCE",
"label": "Knowledge of USDA, District requirements",
"maxPoints": 5,
"page": 37
},
{
"id": "EXP_DEPENDABILITY",
"parentId": "EXPERIENCE",
"label": "Dependability (on-time deliveries, accuracy filling orders)",
"maxPoints": 5,
"page": 37
},
{
"id": "EXP_WAREHOUSE",
"parentId": "EXPERIENCE",
"label": "Inspection of warehouse and other facilities",
"maxPoints": 5,
"page": 37
},
{
"id": "EXP_SERVICE",
"parentId": "EXPERIENCE",
"label": "Customer Service",
"maxPoints": 5,
"page": 37
},
{
"id": "ORG_CAPACITY",
"parentId": null,
"label": "Proven Organizational Capacity",
"maxPoints": 5,
"page": 38
},
{
"id": "COMMUNITY",
"parentId": null,
"label": "Community Connection, Values Alignment",
"maxPoints": 5,
"page": 38
}
], ],
"criteriaNotes": { "criteriaNotes": {
"totalPoints": 100, "totalPoints": 100,
"nestingIsInconsistent": { "nestingIsInconsistent": {
@@ -73,8 +187,14 @@
"they are requirements mapped to the criterion, not sub-criteria. Identical visual", "they are requirements mapped to the criterion, not sub-criteria. Identical visual",
"nesting, two different meanings, in one document." "nesting, two different meanings, in one document."
], ],
"weightedParents": ["METHOD", "EXPERIENCE"], "weightedParents": [
"guidanceOnlyParents": ["ORG_CAPACITY", "COMMUNITY"] "METHOD",
"EXPERIENCE"
],
"guidanceOnlyParents": [
"ORG_CAPACITY",
"COMMUNITY"
]
}, },
"scoringLevelIsAmbiguous": { "scoringLevelIsAmbiguous": {
"$comment": [ "$comment": [
@@ -86,48 +206,307 @@
] ]
} }
}, },
"requirements": [ "requirements": [
{ "id": "R-A1", "kind": "mandatory_gate", "section": "A.1", "page": 4, "text": "Cover Page completed and signed.", "criterionIds": [] }, {
{ "id": "R-A2", "kind": "mandatory_gate", "section": "A.2", "page": 5, "text": "Bidder Checklist completed.", "criterionIds": [] }, "id": "R-A1",
"kind": "mandatory_gate",
{ "id": "R-B2-LOCAL", "kind": "mandatory_gate", "section": "B.2", "page": 5, "text": "Certification of percentage of local foods to be provided.", "criterionIds": ["GEO_PREF"], "knownMissId": "KM-2" }, "section": "A.1",
{ "id": "R-B6C", "kind": "mandatory_gate", "section": "B.6(c)", "page": 5, "text": "Two bid copies submitted.", "criterionIds": [] }, "page": 4,
{ "id": "R-B6D", "kind": "mandatory_gate", "section": "B.6(d)", "page": 5, "text": "A copy of a current state or local health certificate assuring that all regulations for the preparation of food and the facilities are being met.", "criterionIds": ["EXP_WAREHOUSE"] }, "text": "Cover Page completed and signed.",
{ "id": "R-B8-QUEST", "kind": "mandatory_gate", "section": "B.8", "page": 5, "text": "Distributor Pre-Qualification Questionnaire completed.", "criterionIds": ["EXP_KNOWLEDGE"] }, "criterionIds": []
{ "id": "R-B8-LICENSE", "kind": "mandatory_gate", "section": "B.8", "page": 5, "text": "Business license.", "criterionIds": [] }, },
{ "id": "R-B8-OCCUPANCY", "kind": "mandatory_gate", "section": "B.8", "page": 5, "text": "Certificate of Occupancy.", "criterionIds": [] }, {
{ "id": "R-B8-FINANCIALS", "kind": "mandatory_gate", "section": "B.8", "page": 5, "text": "Two years of audited financial statements.", "criterionIds": ["ORG_CAPACITY"] }, "id": "R-A2",
"kind": "mandatory_gate",
{ "id": "R-C1-VALUES", "kind": "mandatory_gate", "section": "C.1", "page": 5, "text": "Response to values statement.", "criterionIds": ["COMMUNITY"], "knownMissId": "KM-3" }, "section": "A.2",
{ "id": "R-C5-INSPECTIONS", "kind": "mandatory_gate", "section": "C.5", "page": 5, "text": "Two most recent health inspections.", "criterionIds": ["EXP_WAREHOUSE"] }, "page": 5,
{ "id": "R-D6-INSURANCE", "kind": "mandatory_gate", "section": "D.6", "page": 5, "text": "Insurance amounts.", "criterionIds": [] }, "text": "Bidder Checklist completed.",
"criterionIds": []
{ "id": "R-SCHED-C", "kind": "pricing", "section": "Schedule C", "page": 41, "text": "Pricing Sheet — separate attachment to be completed in Excel.", "criterionIds": ["PRICING"], "knownMissId": "KM-1" }, },
{
{ "id": "R-ATT-B", "kind": "certification_form", "section": "Attachment B", "page": 44, "text": "Certificate Regarding Debarment, Suspension, Ineligibility and Voluntary Exclusion.", "criterionIds": [], "externalFormSchema": true }, "id": "R-B2-LOCAL",
{ "id": "R-ATT-C", "kind": "certification_form", "section": "Attachment C", "page": 46, "text": "Certificate of Independent Price Determination.", "criterionIds": [], "externalFormSchema": true }, "kind": "mandatory_gate",
{ "id": "R-ATT-D", "kind": "certification_form", "section": "Attachment D", "page": 47, "text": "Permanent Certification Regarding Lobbying.", "criterionIds": [], "externalFormSchema": true }, "section": "B.2",
{ "id": "R-ATT-A", "kind": "compliance_schedule", "section": "Attachment A", "page": 42, "text": "Healthy Schools Act requirements compliance.", "criterionIds": ["EXP_KNOWLEDGE"] }, "page": 5,
"text": "Certification of percentage of local foods to be provided.",
{ "id": "R-B7-FORMAT", "kind": "mandatory_gate", "section": "B.7", "page": 15, "text": "The submitted proposal must have four sections, titled: Executive Summary; Pricing; Method of Approach and Implementation Plan; Bidder's Experience, Expertise and Reliability.", "criterionIds": [] }, "criterionIds": [
"GEO_PREF"
{ "id": "R-C5-FOODSAFETY", "kind": "narrative", "section": "C.5", "page": 23, "text": "Warehouse and distribution food safety programme.", "criterionIds": ["EXP_WAREHOUSE", "FOOD_PACKAGING"] }, ],
{ "id": "R-C6-PEST", "kind": "narrative", "section": "C.6", "page": 24, "text": "Stored products pest management programme.", "criterionIds": ["EXP_WAREHOUSE"] }, "knownMissId": "KM-2"
{ "id": "R-C7-QA", "kind": "narrative", "section": "C.7", "page": 24, "text": "Distributor's responsibility to provide quality assurance.", "criterionIds": ["FOOD_PACKAGING"] }, },
{ "id": "R-C8-FARM2SCHOOL", "kind": "narrative", "section": "C.8", "page": 25, "text": "Farm to School participation.", "criterionIds": ["GEO_PREF", "COMMUNITY"] }, {
{ "id": "R-C4-MENUS", "kind": "narrative", "section": "C.4", "page": 23, "text": "Use of advisory group and menus.", "criterionIds": ["EXP_SERVICE"] }, "id": "R-B6C",
{ "id": "R-D1-DELIVERY", "kind": "narrative", "section": "D.1", "page": 26, "text": "Delivery requirements, including delivery windows per school site.", "criterionIds": ["EXP_DEPENDABILITY"] }, "kind": "mandatory_gate",
{ "id": "R-D3-RECORDS", "kind": "narrative", "section": "D.3", "page": 27, "text": "Record-keeping obligations.", "criterionIds": ["EXP_KNOWLEDGE"] }, "section": "B.6(c)",
{ "id": "R-USDA-FOODS", "kind": "narrative", "section": "B.2/C.3", "page": 7, "text": "Utilization of USDA Foods in the product offering, including processing and diversion.", "criterionIds": ["USDA_FOODS"] }, "page": 5,
{ "id": "R-CN-LABELS", "kind": "narrative", "section": "B.7", "page": 15, "text": "How the Distributor will make nutritional information such as CN labels available to the SFA.", "criterionIds": ["FOOD_PACKAGING", "EXP_KNOWLEDGE"] }, "text": "Two bid copies submitted.",
"criterionIds": [],
{ "id": "R-D8-EPA", "kind": "narrative", "section": "D.8", "page": 30, "text": "Economic price adjustment and price renegotiation terms.", "criterionIds": ["PRICING"] }, "determinableFromResponseDocument": false,
{ "id": "R-B5-PRICING-TERMS", "kind": "narrative", "section": "B.5", "page": 12, "text": "Requirements regarding pricing, bidding and ordering. Prices from the awarded bidder shall remain in effect for the term of the contract.", "criterionIds": ["PRICING"] }, "$comment": "A physical submission fact, not a document-content fact. No extraction of any response can establish it, and no better parsing would help. Kept as a mandatory gate because the SFA does enforce it — but it must be satisfied out of band. The schema has no concept for this today; see the note raised on #10."
{ "id": "R-E1-EEO", "kind": "certification_form", "section": "E.1", "page": 32, "text": "Equal Opportunity provisions.", "criterionIds": [], "externalFormSchema": true }, },
{ "id": "R-E3-CLEANAIR", "kind": "certification_form", "section": "E.3", "page": 33, "text": "Clean Air and Water Certification.", "criterionIds": [], "externalFormSchema": true } {
"id": "R-B6D",
"kind": "mandatory_gate",
"section": "B.6(d)",
"page": 5,
"text": "A copy of a current state or local health certificate assuring that all regulations for the preparation of food and the facilities are being met.",
"criterionIds": [
"EXP_WAREHOUSE"
]
},
{
"id": "R-B8-QUEST",
"kind": "mandatory_gate",
"section": "B.8",
"page": 5,
"text": "Distributor Pre-Qualification Questionnaire completed.",
"criterionIds": [
"EXP_KNOWLEDGE"
]
},
{
"id": "R-B8-LICENSE",
"kind": "mandatory_gate",
"section": "B.8",
"page": 5,
"text": "Business license.",
"criterionIds": []
},
{
"id": "R-B8-OCCUPANCY",
"kind": "mandatory_gate",
"section": "B.8",
"page": 5,
"text": "Certificate of Occupancy.",
"criterionIds": []
},
{
"id": "R-B8-FINANCIALS",
"kind": "mandatory_gate",
"section": "B.8",
"page": 5,
"text": "Two years of audited financial statements.",
"criterionIds": [
"ORG_CAPACITY"
]
},
{
"id": "R-C1-VALUES",
"kind": "mandatory_gate",
"section": "C.1",
"page": 5,
"text": "Response to values statement.",
"criterionIds": [
"COMMUNITY"
],
"knownMissId": "KM-3"
},
{
"id": "R-C5-INSPECTIONS",
"kind": "mandatory_gate",
"section": "C.5",
"page": 5,
"text": "Two most recent health inspections.",
"criterionIds": [
"EXP_WAREHOUSE"
]
},
{
"id": "R-D6-INSURANCE",
"kind": "mandatory_gate",
"section": "D.6",
"page": 5,
"text": "Insurance amounts.",
"criterionIds": []
},
{
"id": "R-SCHED-C",
"kind": "pricing",
"section": "Schedule C",
"page": 41,
"text": "Pricing Sheet — separate attachment to be completed in Excel.",
"criterionIds": [
"PRICING"
],
"knownMissId": "KM-1"
},
{
"id": "R-ATT-B",
"kind": "certification_form",
"section": "Attachment B",
"page": 44,
"text": "Certificate Regarding Debarment, Suspension, Ineligibility and Voluntary Exclusion.",
"criterionIds": [],
"externalFormSchema": true
},
{
"id": "R-ATT-C",
"kind": "certification_form",
"section": "Attachment C",
"page": 46,
"text": "Certificate of Independent Price Determination.",
"criterionIds": [],
"externalFormSchema": true
},
{
"id": "R-ATT-D",
"kind": "certification_form",
"section": "Attachment D",
"page": 47,
"text": "Permanent Certification Regarding Lobbying.",
"criterionIds": [],
"externalFormSchema": true
},
{
"id": "R-ATT-A",
"kind": "compliance_schedule",
"section": "Attachment A",
"page": 42,
"text": "Healthy Schools Act requirements compliance.",
"criterionIds": [
"EXP_KNOWLEDGE"
]
},
{
"id": "R-B7-FORMAT",
"kind": "mandatory_gate",
"section": "B.7",
"page": 15,
"text": "The submitted proposal must have four sections, titled: Executive Summary; Pricing; Method of Approach and Implementation Plan; Bidder's Experience, Expertise and Reliability.",
"criterionIds": []
},
{
"id": "R-C5-FOODSAFETY",
"kind": "narrative",
"section": "C.5",
"page": 23,
"text": "Warehouse and distribution food safety programme.",
"criterionIds": [
"EXP_WAREHOUSE",
"FOOD_PACKAGING"
]
},
{
"id": "R-C6-PEST",
"kind": "narrative",
"section": "C.6",
"page": 24,
"text": "Stored products pest management programme.",
"criterionIds": [
"EXP_WAREHOUSE"
]
},
{
"id": "R-C7-QA",
"kind": "narrative",
"section": "C.7",
"page": 24,
"text": "Distributor's responsibility to provide quality assurance.",
"criterionIds": [
"FOOD_PACKAGING"
]
},
{
"id": "R-C8-FARM2SCHOOL",
"kind": "narrative",
"section": "C.8",
"page": 25,
"text": "Farm to School participation.",
"criterionIds": [
"GEO_PREF",
"COMMUNITY"
]
},
{
"id": "R-C4-MENUS",
"kind": "narrative",
"section": "C.4",
"page": 23,
"text": "Use of advisory group and menus.",
"criterionIds": [
"EXP_SERVICE"
]
},
{
"id": "R-D1-DELIVERY",
"kind": "narrative",
"section": "D.1",
"page": 26,
"text": "Delivery requirements, including delivery windows per school site.",
"criterionIds": [
"EXP_DEPENDABILITY"
]
},
{
"id": "R-D3-RECORDS",
"kind": "narrative",
"section": "D.3",
"page": 27,
"text": "Record-keeping obligations.",
"criterionIds": [
"EXP_KNOWLEDGE"
]
},
{
"id": "R-USDA-FOODS",
"kind": "narrative",
"section": "B.2/C.3",
"page": 7,
"text": "Utilization of USDA Foods in the product offering, including processing and diversion.",
"criterionIds": [
"USDA_FOODS"
]
},
{
"id": "R-CN-LABELS",
"kind": "narrative",
"section": "B.7",
"page": 15,
"text": "How the Distributor will make nutritional information such as CN labels available to the SFA.",
"criterionIds": [
"FOOD_PACKAGING",
"EXP_KNOWLEDGE"
]
},
{
"id": "R-D8-EPA",
"kind": "narrative",
"section": "D.8",
"page": 30,
"text": "Economic price adjustment and price renegotiation terms.",
"criterionIds": [
"PRICING"
]
},
{
"id": "R-B5-PRICING-TERMS",
"kind": "narrative",
"section": "B.5",
"page": 12,
"text": "Requirements regarding pricing, bidding and ordering. Prices from the awarded bidder shall remain in effect for the term of the contract.",
"criterionIds": [
"PRICING"
]
},
{
"id": "R-E1-EEO",
"kind": "certification_form",
"section": "E.1",
"page": 32,
"text": "Equal Opportunity provisions.",
"criterionIds": [],
"externalFormSchema": true
},
{
"id": "R-E3-CLEANAIR",
"kind": "certification_form",
"section": "E.3",
"page": 33,
"text": "Clean Air and Water Certification.",
"criterionIds": [],
"externalFormSchema": true
}
], ],
"knownMisses": [ "knownMisses": [
{ {
"id": "KM-1", "id": "KM-1",
@@ -165,7 +544,6 @@
"exercisesSweepBehaviour": "the sweep's second job — running over spans covered ONLY by informational requirements" "exercisesSweepBehaviour": "the sweep's second job — running over spans covered ONLY by informational requirements"
} }
], ],
"expectedExtractionDifficulty": { "expectedExtractionDifficulty": {
"rubricHasNoCriteriaHeading": { "rubricHasNoCriteriaHeading": {
"$comment": "The rubric lives under 'SECTION K: Evaluation Factors' → 'K.2 Technical Rating Scale'. Searching for 'evaluation criteria' or 'scoring' returns nothing. Weights are bullet suffixes ('– 40 points'), not a table.", "$comment": "The rubric lives under 'SECTION K: Evaluation Factors' → 'K.2 Technical Rating Scale'. Searching for 'evaluation criteria' or 'scoring' returns nothing. Weights are bullet suffixes ('– 40 points'), not a table.",
@@ -178,5 +556,11 @@
"textLayerIsClean": { "textLayerIsClean": {
"$comment": "No page required OCR. This document does not exercise the OCR ladder — use SLC Airport for that." "$comment": "No page required OCR. This document does not exercise the OCR ladder — use SLC Airport for that."
} }
},
"requirementNotes": {
"gatesNotDeterminableFromResponse": [
"R-B6C"
],
"$comment": "Surfaced by validate-responses.py rather than by design. A mandatory gate whose satisfaction is invisible to the response document is a real category: coverage over it is neither answered nor not_answered, it is unknowable from the artifact. Treating it as not_answered would disqualify two of three bidders for a packaging detail."
} }
} }

94
corpus/validate-responses.py Normal file
View File

@@ -0,0 +1,94 @@
#!/usr/bin/env python3
"""Cross-check response truth files against their RFP truth file.
Run: python3 corpus/validate-responses.py corpus/friendship-pcs
Hand-authored ground truth — nothing else checks these.
"""
import json, sys, glob, os
root = sys.argv[1] if len(sys.argv) > 1 else 'friendship-pcs'
rfp = json.load(open(os.path.join(root, 'rfp.truth.json')))
reqs = {r['id']: r for r in rfp['requirements']}
gates = {r['id'] for r in rfp['requirements'] if r['kind'] == 'mandatory_gate'}
# A gate whose satisfaction is invisible to the response document cannot be scored
# from it. Excluded from the silent-gate check; see requirementNotes in the RFP truth.
undeterminable = {r['id'] for r in rfp['requirements']
if r.get('determinableFromResponseDocument') is False}
COVERAGE = {'answered', 'not_answered', 'indeterminate'}
errs, warns = [], []
print(f"RFP: {len(reqs)} requirements, {len(gates)} gates\n")
for path in sorted(glob.glob(os.path.join(root, 'responses', '*.truth.json'))):
t = json.load(open(path))
v = t['vendor']['id']
answered = {}
for a in t['answers']:
rid = a['requirementId']
if rid not in reqs:
errs.append(f"{v}: answer -> unknown requirement {rid}")
continue
if a['coverage'] not in COVERAGE:
errs.append(f"{v}: {rid} bad coverage '{a['coverage']}'")
if rid in answered:
errs.append(f"{v}: duplicate answer for {rid}")
answered[rid] = a
missing = sorted(set(reqs) - set(answered))
if missing:
warns.append(f"{v}: {len(missing)} requirements have no answer entry: {', '.join(missing[:4])}{'...' if len(missing) > 4 else ''}")
# gate failures must agree with the declared outcome
declared = set(t['expectedOutcome'].get('failedGates', []))
actual = {r for r, a in answered.items()
if r in gates and (a.get('isGateFailure') or a['coverage'] == 'not_answered')}
flagged = {r for r, a in answered.items() if a.get('isGateFailure')}
if not declared <= flagged:
errs.append(f"{v}: declared failedGates {sorted(declared - flagged)} not marked isGateFailure on the answer")
if t['expectedOutcome']['gatesPassed'] and declared:
errs.append(f"{v}: gatesPassed=true but failedGates is non-empty")
if not t['expectedOutcome']['gatesPassed'] and not declared:
errs.append(f"{v}: gatesPassed=false but no failedGates declared")
# unflagged gate misses are a real signal, not necessarily an error
silent = actual - declared - set(t['expectedOutcome'].get('atRiskGates', [])) - undeterminable
if silent:
warns.append(f"{v}: gate(s) not_answered but not declared failed or at-risk: {sorted(silent)}")
for e in t.get('exceptions', []):
rid = e.get('requirementId')
if rid is not None and rid not in reqs:
errs.append(f"{v}: exception {e['id']} -> unknown requirement {rid}")
counts = {}
for a in answered.values():
counts[a['coverage']] = counts.get(a['coverage'], 0) + 1
exc = len(t.get('exceptions', []))
labelled = sum(1 for e in t.get('exceptions', []) if e.get('labelled'))
print(f" {v:11} binding={t['bindingMechanism']['level']:34} "
f"answered={counts.get('answered',0):2} indet={counts.get('indeterminate',0)} "
f"absent={counts.get('not_answered',0)} exceptions={exc} ({labelled} labelled) "
f"gates={'PASS' if t['expectedOutcome']['gatesPassed'] else 'FAIL'}")
# corpus-level coverage of the stress-case checklist
files = [json.load(open(p)) for p in glob.glob(os.path.join(root, 'responses', '*.truth.json'))]
checks = {
'tabbed compliance matrix': any(f['bindingMechanism']['level'] == 'tabbed_restatement' for f in files),
'free prose, no anchors': any(f['bindingMechanism']['level'] == 'free_prose' for f in files),
'rate function, not scalar': len({f['priceQuote']['rateStructure']['kind'] for f in files}) >= 3,
'partially non-responsive': any(not f['expectedOutcome']['gatesPassed'] for f in files),
'exceptions with price deltas': any(e.get('priceDeltaIfDeclined') for f in files for e in f.get('exceptions', [])),
'unlabelled exception': any(e.get('labelled') is False for f in files for e in f.get('exceptions', [])),
'labelled known-misses in RFP': len(rfp.get('knownMisses', [])) >= 3,
'miskinded-as-informational': any(k['type'] == 'miskinded_as_informational' for k in rfp['knownMisses']),
'answered-but-negative': any('negative' in str(a.get('$comment','')).lower() for f in files for a in f['answers']),
}
print("\n stress-case checklist")
for k, ok in checks.items():
print(f" {'x' if ok else ' '} {k}")
if not ok: warns.append(f"stress case not covered: {k}")
for w in warns: print(f"\n WARN {w}")
for e in errs: print(f"\n ERR {e}")
print("\nVALID" if not errs else "\nINVALID")
sys.exit(1 if errs else 0)