Apparel Agentic-Commerce Attribute Readiness Index Methodology
StoreSteady crawled 72 deterministically ranked candidate stores from 131 valid candidates and retained 30 apparel-evaluable stores with exactly two classified public PDPs each. This page documents selection, denominator, exclusion, redaction, source, and version rules.
Corpus And Window
Selection rule: Normalize and deduplicate discovery candidates, rank the frozen store pool by stable hash, crawl HTTP-only, recover public Shopify catalog PDP observations through the shared crawl engine, rank eligible human-apparel PDPs by stable hash, and retain the first two evaluable PDPs per store. Stop when 30 stores clear the denominator contract.
Freeze timestamp: 2026-07-11T00:09:19.670Z
Evaluation window: 2026-07-11T00:09:19.670Z to 2026-07-11T00:24:51.234Z
Fields collected: redacted candidate rank, selection phase, store hash, and denominator state, HTTP-only crawl status, inferred category, public Shopify evidence, and exclusion reasons, two stable-hash-selected human-apparel PDPs per evaluable store, nine attribute states per PDP with one-layer subtype applicability, public evidence surface labels and non-identifying evidence hashes, parser, applicability-contract, report, and run versions.
Denominator Rules
Every published rate has its own evaluable N and Wilson 95% confidence interval.
Access friction, detector non-evaluability, deterministic conflicts, tentative findings, and confirmed findings are kept separate.
No blended denominator is used in this report.
Metric Quality Table
| Metric | Tier | N | Count | CI | Caveat |
|---|---|---|---|---|---|
| apparel_store_any_applicable_attribute_missing_public_evidence | Headline | 30 | 30 | 88.6% - 100% | Public PDP evidence only. A missing-public-evidence state does not establish that private Shopify data, Merchant Center data, OpenAI/ACP feeds, or other connected systems lack the attribute. |
| apparel_store_category_evaluable | Supporting | 72 | 30 | 31.0% - 53.2% | A store is evaluable only when public Shopify and human-apparel evidence is confirmed, crawling completes, and two deterministic PDPs are classified. |
| apparel_attribute_missing_public_evidence_color | Supporting | 60 | 12 | 11.8% - 31.8% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_size | Supporting | 55 | 18 | 21.8% - 45.9% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_age_group_or_audience | Supporting | 60 | 45 | 62.8% - 84.2% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_gender_or_unisex | Supporting | 60 | 29 | 36.2% - 60.7% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_size_system_or_size_guidance | Supporting | 52 | 42 | 68.1% - 89.2% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_fit_or_size_type | Supporting | 52 | 40 | 63.9% - 86.3% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_material_composition | Supporting | 60 | 20 | 22.7% - 45.9% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_variant_group_clarity | Supporting | 60 | 19 | 21.3% - 44.2% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_attribute_missing_public_evidence_return_exchange_path | Supporting | 60 | 12 | 11.8% - 31.8% | PDP-attribute denominator. Not-applicable rows are excluded, and public absence is not evidence about private or connected feed state. |
| apparel_excluded_empty_or_blocked | Limitation | 72 | 6 | 3.88% - 17.0% | Access friction is counted separately and is never converted into missing apparel-attribute evidence. |
| apparel_excluded_zero_pdp_discovered | Limitation | 72 | 6 | 3.88% - 17.0% | Completed public crawls with no eligible human-apparel PDP discovery remain outside the headline denominator. |
| apparel_excluded_eligible_pdp_n_lt_2 | Limitation | 72 | 5 | 3% - 15.3% | Stores exposing only one eligible human-apparel PDP do not enter the two-PDP evaluable denominator. |
| apparel_excluded_evaluable_pdp_n_lt_2 | Limitation | 72 | 3 | 1.43% - 11.6% | Eligible PDPs that remain blocked or otherwise unevaluable do not satisfy the two-PDP evidence floor. |
| apparel_not_human_apparel_public_evidence | Limitation | 72 | 22 | 21.1% - 41.9% | Historical source labels are treated as discovery signals and are re-qualified from current public PDP evidence. |
| apparel_subtype_distribution | Not rate-published | not published | not published | not published | Raw diagnostic counts only: footwear: 8 PDPs across 6 stores; tops: 20 PDPs across 12 stores; bottoms: 7 PDPs across 6 stores; outerwear: 3 PDPs across 2 stores; swim_intimates: 1 PDPs across 1 stores; accessories: 17 PDPs across 12 stores; general_apparel: 4 PDPs across 3 stores. No subtype clears its own N >= 30 floor. |
Apparel Rubric
The corpus parser applies the STO-463 public-evidence rubric and subtype applicability contract to two deterministic PDPs per evaluable store. Every row remains independently recomputable from its state and redacted evidence metadata.
| Attribute | OpenAI/ACP | Shopify | |
|---|---|---|---|
| color | color, variant_option, item_group_id | color, variant_dict.color, group_id, listing_has_variations | color, category metafield color entries, variant option connection |
| size | size, variant_option, item_group_id | size, variant_dict.size, group_id, listing_has_variations | size, clothing size, variant option connection |
| age_group_or_audience | age_group | age_group | age-group |
| gender_or_unisex | gender | gender | target-gender |
| size_system_or_size_guidance | size_system, size | size_system, size, variant_dict.size | size, clothing size, footwear size system |
| fit_or_size_type | size_type, size | variant_dict.size_type, Custom_variant1_category: Size_Type | fit, cycling-apparel-fit, clothing-features |
| material_composition | material | material | fabric, fabric composition |
| variant_group_clarity | item_group_id, item_group_title, variant_option | group_id, listing_has_variations, variant_dict, item_group_title | variant option connection, category metafield entries |
| return_exchange_path | return policy settings, MerchantReturnPolicy structured data | accepts_returns, accepts_exchanges, return_deadline_in_days, return_policy | category return reasons, store return policy surface |
Judgment Policy
No LLM judgments were used for this report section; StoreSteady used deterministic parsers only.
Parser version: apparel-attribute-public-evidence-parser.v2
Redaction Policy
- No store names, raw domains, raw URLs, raw crawl text, or raw AI responses are published.
- No exact promo codes, private feed/admin evidence, or merchant-identifying product examples are published.
- Public examples fail closed unless Caleb explicitly approves the specific exposure.
Related Public Benchmarks
This report is not a placement dashboard, market forecast, AEO forecast, or financial impact estimate. It measures evidence quality and evaluability under the StoreSteady public research protocol.
Sources
- Google Merchant Center product data specification - Source map for apparel attributes including color, size, age_group, gender, size_system, size_type, material, item_group_id, and variant_option.
- OpenAI product feed specification - Source map for product-feed item, variant, material, audience, seller, and return-policy fields.
- Agentic Commerce Protocol product feed specification - Source map for ACP/OpenAI apparel variant fields used as external rubric evidence.
- Shopify category metafields - Source map for category metafields, product attributes, and variant option connections.
- Shopify Standard Product Taxonomy - Source map for apparel category attributes such as color, age group, target gender, fabric, size, and fit.
- Google MerchantReturnPolicy structured data - Public structured-data context for return-policy surfaces. The report does not audit private policy settings.
- Schema.org ProductGroup - Public structured-data context for variant grouping. The corpus parser keeps schema-only and visible surfaces separate.
Version History
- 2026-summer.apparel-attribute-readiness-public-v2 (2026-07-13): Replaced the one-store smoke framing with the STO-511 30-store, 60-PDP report-grade corpus; added store-, PDP-, and attribute-level denominators, Wilson intervals, subtype diagnostics, redacted corpus rows, and final owner validation approval.
- 2026-summer.apparel-attribute-readiness-v1 (2026-05-26): Initial apparel-specific public-evidence attribute readiness smoke with source-mapped rubric, redacted row artifact, and baseline/diff artifact.