{
  "slug": "table-and-form-validation-for-document-extraction",
  "title": "Table and Form Validation for Document Extraction: Row Counts, Totals and Required Fields",
  "description": "Validating table and form extraction from documents: rows split across pages, subtotal rows, exact money reconciliation, column sums, required-field maps per form type, cross-field checks and a failed-check-to-route table.",
  "kind": "sub",
  "order": 3,
  "target_query": "validating table and form extraction from documents",
  "secondary_queries": [],
  "tags": [
    "document-extraction",
    "validation",
    "tables",
    "forms",
    "reconciliation",
    "production"
  ],
  "published": "2026-10-26",
  "updated": "2026-10-26",
  "words": 1572,
  "estimated_tokens": 2091,
  "premium": false,
  "rights": {
    "access": "free",
    "note": "Editorial guides are always free and never part of the licensed corpus.",
    "license": "https://changegamer.ai/license.xml",
    "pricing": "https://changegamer.ai/api/pricing.json",
    "payment": "https://changegamer.ai/api/payment.json"
  },
  "license": "https://changegamer.ai/license.xml",
  "citation": "ChangeGamer (2026-10-26). Table and Form Validation for Document Extraction: Row Counts, Totals and Required Fields. ChangeGamer. https://changegamer.ai/articles/table-and-form-validation-for-document-extraction (updated 2026-10-26).",
  "bibtex": "@misc{changegamer_table_and_form_validation_for_document_extraction, title = {Table and Form Validation for Document Extraction: Row Counts, Totals and Required Fields}, publisher = {ChangeGamer}, year = {2026}, url = {https://changegamer.ai/articles/table-and-form-validation-for-document-extraction}, note = {Updated 2026-10-26}}",
  "canonical": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction",
  "markdown": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction.md",
  "takeaways": [
    "Validating a table extracted from a document starts with classifying every row as item, subtotal, tax, total or repeated header before counting, because only item rows belong in the row count (author design choice).",
    "Money reconciliation should compare exact decimal or integer minor-unit values, and a rounding tolerance is justified only when the document itself rounds per line, in which case the tolerance should be a stated number of minor units per row (author inference).",
    "A required-field map per form type, with conditional-required fields such as a credit note needing the original invoice reference, turns \"field presence\" into a testable rule instead of a general instruction (author design choice).",
    "The structured outputs reference lists no numeric or string constraints such as minimum or maxLength for Anthropic structured outputs, so amount reconciliation belongs in your own code (author inference).",
    "As of October 2026 ChangeGamer parses no documents and has no extraction accuracy numbers, so the rules here are design inference to test on your own labelled sample."
  ],
  "outline": [
    {
      "depth": 2,
      "text": "Why do table checks belong in your code and not in the schema?",
      "anchor": "why-do-table-checks-belong-in-your-code-and-not-in-the-schema",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#why-do-table-checks-belong-in-your-code-and-not-in-the-schema"
    },
    {
      "depth": 2,
      "text": "How do you validate a table that continues across pages?",
      "anchor": "how-do-you-validate-a-table-that-continues-across-pages",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#how-do-you-validate-a-table-that-continues-across-pages"
    },
    {
      "depth": 2,
      "text": "Which rows count as item rows?",
      "anchor": "which-rows-count-as-item-rows",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#which-rows-count-as-item-rows"
    },
    {
      "depth": 2,
      "text": "How should money be reconciled: exact or with a tolerance?",
      "anchor": "how-should-money-be-reconciled-exact-or-with-a-tolerance",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#how-should-money-be-reconciled-exact-or-with-a-tolerance"
    },
    {
      "depth": 3,
      "text": "What if the document states no total?",
      "anchor": "what-if-the-document-states-no-total",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#what-if-the-document-states-no-total"
    },
    {
      "depth": 2,
      "text": "What does a required-field map look like per form type?",
      "anchor": "what-does-a-required-field-map-look-like-per-form-type",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#what-does-a-required-field-map-look-like-per-form-type"
    },
    {
      "depth": 2,
      "text": "Which cross-field checks catch the errors that totals miss?",
      "anchor": "which-cross-field-checks-catch-the-errors-that-totals-miss",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#which-cross-field-checks-catch-the-errors-that-totals-miss"
    },
    {
      "depth": 2,
      "text": "What route should each failed check take?",
      "anchor": "what-route-should-each-failed-check-take",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#what-route-should-each-failed-check-take"
    },
    {
      "depth": 2,
      "text": "What does ChangeGamer know first-hand about failing loudly?",
      "anchor": "what-does-changegamer-know-first-hand-about-failing-loudly",
      "url": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction#what-does-changegamer-know-first-hand-about-failing-loudly"
    }
  ],
  "faq": [
    {
      "question": "How do you validate a table that continues across several pages of a PDF?",
      "answer": "Merge the page fragments into one logical table before checking anything, dropping repeated header rows and carrying a row that is split at a page break into a single record. Then run row counts and totals on the merged table, never per page (author design choice)."
    },
    {
      "question": "Should extracted invoice amounts be compared with a tolerance?",
      "answer": "Compare exactly by default, using decimals or integer minor units. Allow a tolerance only when the document is known to round each line separately, and then express it as a fixed number of minor units per line rather than as a percentage (author inference)."
    },
    {
      "question": "What should a pipeline do when a table has no stated total to check against?",
      "answer": "Treat the column sum as a consistency signal, not proof. A sum that matches nothing on the page cannot be verified, so record \"total not stated\" as a reason code and apply the stricter review route for that document type (author inference)."
    },
    {
      "question": "Can a JSON schema enforce required fields that depend on other fields?",
      "answer": "Not reliably across providers. The structured outputs reference lists schema limits for Anthropic, including no numeric or string constraints, so conditional-required rules such as \"credit notes need an original invoice reference\" are safer as code that runs after parsing."
    }
  ],
  "body": "Table and form extraction is valid only when you can prove four things after the model has answered: the right rows were counted, the money reconciles, the required fields for that form type are present, and the fields agree with each other. This article is the value-checking step that follows [schema-constrained extraction](/articles/schema-constrained-field-extraction-from-documents) and a parser chosen as in [OCR vs vision model for document parsing](/articles/ocr-vs-vision-model-vs-hybrid-document-parsing). The [AI document extraction pipeline](/articles/ai-document-extraction-pipeline-in-production) pillar owns the validation layers; here is the table- and form-specific detail. Facts cite the [Document Extraction and Parsing for Agents](/resources/document-extraction-for-agents) reference (updated 2026-09-28) and the [Structured Outputs and JSON Mode](/resources/structured-outputs-and-json-mode) reference (updated 2026-09-26). Everything else is author inference or a design choice, and says so.\n\n## Why do table checks belong in your code and not in the schema?\n\nTable checks belong in your code because schema keywords are unlikely to express them. The structured outputs reference lists no numeric or string constraints such as `minimum` and `maxLength` for Anthropic's structured outputs, which rules out an amount-sum rule in the schema; that a schema also cannot say \"this field is required when that one is set\" is the author's inference. The extraction reference lists merged table cells among the hard cases to test, places complex table spans in its OCR-and-layout tier, and advises cross-validating high-stakes values. The rules below are the author's design for doing that.\n\n## How do you validate a table that continues across pages?\n\nMerge the page fragments into one logical table first, then validate the merged result. A multi-page table repeats its header on each page, may split one row across a page break, and may restart row numbers or carry a \"continued\" marker (author inference, from how such documents are commonly laid out).\n\nSuppose a purchase order table runs over three pages. A workable merge order, all design choice:\n\n1. **Drop repeated headers.** A row whose cells equal the first page's header cells is a header, not data.\n2. **Join split rows.** A page ends with a partial row (a description but no amount) and the next page starts with the remainder; join them when the first fragment lacks a required cell and the second lacks the first cell.\n3. **Keep the page of origin** on every row so a reviewer can find it.\n4. **Compare counts.** If the document numbers its lines, the highest line number should equal the item-row count; a gap or duplicate is a failure.\n\nIf the schema was filled per page, the merge belongs in code after extraction. If the whole table was extracted in one call, the same checks still apply to the output.\n\n## Which rows count as item rows?\n\nOnly rows that describe a billed thing count as item rows; subtotal, discount, shipping, tax and total rows are separate classes. Counting them together makes the row count wrong whenever a document prints a subtotal, and a total row summed with the items doubles the amount (author inference).\n\n| Row class | Counts toward row count | Counts toward item sum |\n|---|---|---|\n| Item | Yes | Yes |\n| Subtotal | No | No (use as a check target) |\n| Discount or shipping | No | Only if your rule says so |\n| Tax | No | No (check separately) |\n| Total / balance due | No | No (check target) |\n| Repeated header | No | No |\n\nMake the class an explicit field in the extraction schema (an enum with an escape value, as sub 2 recommends) so the model labels the row and your code can disagree with it. A subtotal in the middle of a long table is also a checkpoint: validate each segment's sum against its own subtotal and you learn which page the error is on.\n\n## How should money be reconciled: exact or with a tolerance?\n\nCompare exactly, using decimals or integer minor units, unless the document is known to round each line separately. Converting amounts to minor units (cents for two-decimal currencies) before comparing removes float noise, and the pillar already shows decimal arithmetic. A currency with a different number of decimal places (general knowledge, not from the corpus) needs its own scale, so derive it from the currency code rather than assuming two.\n\nA tolerance is justified only when line-level rounding exists in the document itself: tax computed and rounded per line, then summed, can differ from tax computed once on the subtotal. In that case allow a stated number of minor units per rounded row, and write the number down as a decision with an owner (design choice). Do not use a percentage: a percentage tolerance grows with the total and can hide a transposed digit on a large invoice. This site has no data on which tolerance suits which tax regime, so none is given.\n\n### What if the document states no total?\n\nIf no total is printed, the column sum becomes a consistency signal that cannot be verified, so say so in the record. Compute it, store it as `computed_total`, set `total_stated` to false, and route by the stricter rule for that document type. Never copy the computed sum into the stated-total field; a derived number presented as an extracted one is the error this check exists to prevent (design choice).\n\n## What does a required-field map look like per form type?\n\nA required-field map lists, for each document type, the fields that must be present, the fields that must be present only when a condition holds, and the fields that may be null. The map is data, not prompt text, so it can be reviewed and versioned. This one is illustrative (design choice); your obligations differ by jurisdiction and customer.\n\n| Field | Invoice | Credit note | Purchase order |\n|---|---|---|---|\n| Document number | Required | Required | Required |\n| Issue date | Required | Required | Required |\n| Currency | Required | Required | Required |\n| Original invoice reference | Not applicable | Required | Not applicable |\n| Tax identifier | Required if tax amount is above zero | Required if tax amount is above zero | Optional |\n| Delivery date | Optional | Not applicable | Required if lines exist |\n| Total | Required | Required | Optional |\n\nThe conditional entries are where schemas fail: an optional field that becomes required depends on another value. Express each as a small function over the whole record and return a reason code naming the unmet condition. Sub 2's nullable-field rule still holds, since \"absent\" must stay a valid answer; the map decides when absent is acceptable.\n\n## Which cross-field checks catch the errors that totals miss?\n\nCross-field checks catch errors that internal sums cannot, because a record can reconcile and still be wrong. Three are cheap (all design choice; the currency-decimals, shared-symbol and locale-separator facts are general knowledge, not from the corpus):\n\n- **Date ordering beyond the pillar's check.** The pillar's layer 3 already covers a due date before the issue date; add a check that a delivery or service date is not years away from the issue date, which usually means a day/month swap or a misread digit.\n- **Currency symbol versus code.** A document showing \"$\" with a code of EUR is ambiguous, since \"$\" is shared by several currencies; compare the symbol seen in the Stage A text with the extracted code and flag a mismatch instead of picking one.\n- **Number format versus locale.** \"1.250,00\" and \"1,250.00\" are the same amount in different locales; check that the separators match the document's currency or language hint.\n\n## What route should each failed check take?\n\nEach failed check should map to a named route in advance, chosen by what the failure means. The table classifies and names the route only; thresholds and queue design live in the review article of this cluster. Routes are the author's design.\n\n| Failed check | Likely cause | Route |\n|---|---|---|\n| Item-row count differs from the highest line number | Dropped or duplicated row at a page break | Re-extract with a changed scope, else review |\n| Item sum differs from the stated subtotal | Misread amount or a misclassified row | Review, showing the page of the failing segment |\n| Required field missing | Absent on the document, or unread | Review if the map requires it, otherwise accept null |\n| Conditional-required unmet | Missing dependent value | Review with the reason code |\n| Date check violated | Date misread or swapped | Review |\n| Symbol and currency code disagree | Ambiguous symbol | Review |\n| Total not stated | Document design | Stricter review route for the type |\n\nRe-extraction follows sub 2's one-retry cap; this table does not add a second retry.\n\n## What does ChangeGamer know first-hand about failing loudly?\n\nAs of October 2026 ChangeGamer parses no documents and has no extraction accuracy numbers, so none of the rules above is measured on its own data. One verifiable adjacent fact is how its build treats a broken reference: the cluster checks in `src/lib/articles.ts` throw when an article body links an `/articles/` URL that does not exist, and the build stops. A failed reference check is a hard stop there, not a warning. That is the stance behind the routes above: a failed check should produce a named outcome, not a quiet pass.",
  "cluster": {
    "id": "document-pipelines",
    "title": "Document extraction pipelines in production",
    "description": "How to run AI document extraction as a production pipeline — OCR vs vision-model vs hybrid parsing, schema-constrained field extraction, table and form validation, human-review fallback, schema versioning, cost per page, open-source vs managed tooling and feeding a system of record — not chunking and retrieval (chunking-documents-for-rag, rag-ingestion-pipeline), not generic structured-output and tool-call mechanics (structured-outputs-vs-tool-calling, tool-calling-contracts-for-ai-agents) and not injection defense in depth (prompt-injection-defense-in-depth-for-agents).",
    "status": "complete",
    "pillar": {
      "slug": "ai-document-extraction-pipeline-in-production",
      "title": "AI Document Extraction in Production: Parse, Extract, Validate, Review",
      "description": "How to run AI document extraction as a production pipeline: separate parsing from schema-constrained field extraction, choose OCR, a vision model or a hybrid, validate values, route doubtful ones to a human, version the schema, and work out cost per page.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/ai-document-extraction-pipeline-in-production",
      "markdown": "https://changegamer.ai/articles/ai-document-extraction-pipeline-in-production.md",
      "json": "https://changegamer.ai/api/articles/ai-document-extraction-pipeline-in-production.json"
    },
    "articles": [
      {
        "slug": "ocr-vs-vision-model-vs-hybrid-document-parsing",
        "title": "OCR vs Vision Language Model for Document Parsing: How to Choose Stage A",
        "description": "OCR vs vision language model for document parsing: a decision order keyed on residency, layout variance, volume and known schema, how a hybrid arbitrates disagreements, a per-field bake-off, failure-mode mapping, page batching and privacy.",
        "kind": "sub",
        "order": 1,
        "html": "https://changegamer.ai/articles/ocr-vs-vision-model-vs-hybrid-document-parsing",
        "markdown": "https://changegamer.ai/articles/ocr-vs-vision-model-vs-hybrid-document-parsing.md",
        "json": "https://changegamer.ai/api/articles/ocr-vs-vision-model-vs-hybrid-document-parsing.json"
      },
      {
        "slug": "schema-constrained-field-extraction-from-documents",
        "title": "Schema-Constrained Field Extraction From Documents: Settings and Failure Branches",
        "description": "Schema constrained field extraction from documents: nullable fields, enums with an escape value, evidence fields, a branch table for refusal, truncation, parse failure and empty output, a one-retry policy, and field confidence as inference.",
        "kind": "sub",
        "order": 2,
        "html": "https://changegamer.ai/articles/schema-constrained-field-extraction-from-documents",
        "markdown": "https://changegamer.ai/articles/schema-constrained-field-extraction-from-documents.md",
        "json": "https://changegamer.ai/api/articles/schema-constrained-field-extraction-from-documents.json"
      },
      {
        "slug": "table-and-form-validation-for-document-extraction",
        "title": "Table and Form Validation for Document Extraction: Row Counts, Totals and Required Fields",
        "description": "Validating table and form extraction from documents: rows split across pages, subtotal rows, exact money reconciliation, column sums, required-field maps per form type, cross-field checks and a failed-check-to-route table.",
        "kind": "sub",
        "order": 3,
        "html": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction",
        "markdown": "https://changegamer.ai/articles/table-and-form-validation-for-document-extraction.md",
        "json": "https://changegamer.ai/api/articles/table-and-form-validation-for-document-extraction.json"
      },
      {
        "slug": "human-review-fallback-for-document-extraction",
        "title": "Human Review Fallback for Document Extraction: Triggers, Capacity and the Correction Loop",
        "description": "Designing the human review fallback for document extraction: a routing-trigger table, cross-checking high-stakes fields, review capacity and backlog policy, the review item record and a correction loop that feeds regression sets.",
        "kind": "sub",
        "order": 4,
        "html": "https://changegamer.ai/articles/human-review-fallback-for-document-extraction",
        "markdown": "https://changegamer.ai/articles/human-review-fallback-for-document-extraction.md",
        "json": "https://changegamer.ai/api/articles/human-review-fallback-for-document-extraction.json"
      },
      {
        "slug": "extraction-schema-versioning-for-document-pipelines",
        "title": "Versioning a Document Extraction Schema: Migrations, Manifests and Rollback",
        "description": "How to version a document extraction schema: which edits break stored records, absent versus null fields, lazy upcast versus backfill, reprocessing from stored parse output, a version manifest, dual-read cutover, correction migration and rollback.",
        "kind": "sub",
        "order": 5,
        "html": "https://changegamer.ai/articles/extraction-schema-versioning-for-document-pipelines",
        "markdown": "https://changegamer.ai/articles/extraction-schema-versioning-for-document-pipelines.md",
        "json": "https://changegamer.ai/api/articles/extraction-schema-versioning-for-document-pipelines.json"
      },
      {
        "slug": "cost-per-page-for-document-extraction",
        "title": "Document Extraction Cost per Page: Tokens, Retries, Review and Budget Alarms",
        "description": "How to model document extraction cost per page beyond the parse fee: page-count mix versus per-page pricing, image tokens versus per-call overhead, retries by failure class, review share, batch versus sync, and a budget kill switch on cost per accepted document.",
        "kind": "sub",
        "order": 6,
        "html": "https://changegamer.ai/articles/cost-per-page-for-document-extraction",
        "markdown": "https://changegamer.ai/articles/cost-per-page-for-document-extraction.md",
        "json": "https://changegamer.ai/api/articles/cost-per-page-for-document-extraction.json"
      },
      {
        "slug": "open-source-vs-managed-document-parsing",
        "title": "Open Source vs Managed Document Parsing: A Decision Order, Operating Burden and Exit Plan",
        "description": "How to decide between self-hosted open-source parsers and a managed parsing service: residency and licence first, volume and operations capacity second, reversibility third, plus the cost of operating models, lock-in, a single-interface fallback design and a trial protocol on your own documents.",
        "kind": "sub",
        "order": 7,
        "html": "https://changegamer.ai/articles/open-source-vs-managed-document-parsing",
        "markdown": "https://changegamer.ai/articles/open-source-vs-managed-document-parsing.md",
        "json": "https://changegamer.ai/api/articles/open-source-vs-managed-document-parsing.json"
      },
      {
        "slug": "feeding-extraction-output-into-a-system-of-record",
        "title": "Writing Extracted Document Data to a System of Record: Matching, Keys, States and Replay",
        "description": "How to write extracted document data to a system of record: matching an extracted record to an existing one, retry keys versus business keys, a staged-to-committed state machine, per-record versus per-document atomicity, dead-letter queues, replay from the saved parse artifact and the write-boundary log.",
        "kind": "sub",
        "order": 8,
        "html": "https://changegamer.ai/articles/feeding-extraction-output-into-a-system-of-record",
        "markdown": "https://changegamer.ai/articles/feeding-extraction-output-into-a-system-of-record.md",
        "json": "https://changegamer.ai/api/articles/feeding-extraction-output-into-a-system-of-record.json"
      },
      {
        "slug": "multimodal-document-understanding-for-extraction-pipelines",
        "title": "Multimodal Document Understanding for Extraction: Charts, Diagrams, Photos, Stamps and Video Frames",
        "description": "How to handle non-text visuals in a document extraction pipeline: when OCR is not enough, extracting a value versus a description versus a class, region-level routing, figure-aware page packing, poor scans, video frames, image-borne injection and per-visual evaluation.",
        "kind": "sub",
        "order": 9,
        "html": "https://changegamer.ai/articles/multimodal-document-understanding-for-extraction-pipelines",
        "markdown": "https://changegamer.ai/articles/multimodal-document-understanding-for-extraction-pipelines.md",
        "json": "https://changegamer.ai/api/articles/multimodal-document-understanding-for-extraction-pipelines.json"
      },
      {
        "slug": "monitoring-document-extraction-accuracy-in-production",
        "title": "Monitoring Document Extraction Accuracy in Production: Audit Samples, Field Metrics and Drift",
        "description": "How to monitor document extraction accuracy in production: a stratified audit sample with independent labels, per-field metrics with intervals, extraction-specific drift triggers, thresholds from your own variance, and regression intake.",
        "kind": "sub",
        "order": 10,
        "html": "https://changegamer.ai/articles/monitoring-document-extraction-accuracy-in-production",
        "markdown": "https://changegamer.ai/articles/monitoring-document-extraction-accuracy-in-production.md",
        "json": "https://changegamer.ai/api/articles/monitoring-document-extraction-accuracy-in-production.json"
      },
      {
        "slug": "splitting-long-documents-for-document-extraction",
        "title": "How to Split Long Documents for Extraction: Batches, Overlap and Reassembly",
        "description": "How to split long documents for extraction: size batches from measured tokens per page, choose section or page windows, overlap pages, carry table headers, reconcile conflicts across batches and reassemble with provenance.",
        "kind": "sub",
        "order": 11,
        "html": "https://changegamer.ai/articles/splitting-long-documents-for-document-extraction",
        "markdown": "https://changegamer.ai/articles/splitting-long-documents-for-document-extraction.md",
        "json": "https://changegamer.ai/api/articles/splitting-long-documents-for-document-extraction.json"
      }
    ]
  },
  "navigation": {
    "pillar": {
      "slug": "ai-document-extraction-pipeline-in-production",
      "title": "AI Document Extraction in Production: Parse, Extract, Validate, Review",
      "description": "How to run AI document extraction as a production pipeline: separate parsing from schema-constrained field extraction, choose OCR, a vision model or a hybrid, validate values, route doubtful ones to a human, version the schema, and work out cost per page.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/ai-document-extraction-pipeline-in-production",
      "markdown": "https://changegamer.ai/articles/ai-document-extraction-pipeline-in-production.md",
      "json": "https://changegamer.ai/api/articles/ai-document-extraction-pipeline-in-production.json"
    },
    "previous": {
      "slug": "schema-constrained-field-extraction-from-documents",
      "title": "Schema-Constrained Field Extraction From Documents: Settings and Failure Branches",
      "description": "Schema constrained field extraction from documents: nullable fields, enums with an escape value, evidence fields, a branch table for refusal, truncation, parse failure and empty output, a one-retry policy, and field confidence as inference.",
      "kind": "sub",
      "order": 2,
      "html": "https://changegamer.ai/articles/schema-constrained-field-extraction-from-documents",
      "markdown": "https://changegamer.ai/articles/schema-constrained-field-extraction-from-documents.md",
      "json": "https://changegamer.ai/api/articles/schema-constrained-field-extraction-from-documents.json"
    },
    "next": {
      "slug": "human-review-fallback-for-document-extraction",
      "title": "Human Review Fallback for Document Extraction: Triggers, Capacity and the Correction Loop",
      "description": "Designing the human review fallback for document extraction: a routing-trigger table, cross-checking high-stakes fields, review capacity and backlog policy, the review item record and a correction loop that feeds regression sets.",
      "kind": "sub",
      "order": 4,
      "html": "https://changegamer.ai/articles/human-review-fallback-for-document-extraction",
      "markdown": "https://changegamer.ai/articles/human-review-fallback-for-document-extraction.md",
      "json": "https://changegamer.ai/api/articles/human-review-fallback-for-document-extraction.json"
    }
  },
  "resources": [
    {
      "slug": "document-extraction-for-agents",
      "html": "https://changegamer.ai/resources/document-extraction-for-agents",
      "markdown": "https://changegamer.ai/resources/document-extraction-for-agents.md",
      "json": "https://changegamer.ai/api/resources/document-extraction-for-agents.json"
    },
    {
      "slug": "structured-outputs-and-json-mode",
      "html": "https://changegamer.ai/resources/structured-outputs-and-json-mode",
      "markdown": "https://changegamer.ai/resources/structured-outputs-and-json-mode.md",
      "json": "https://changegamer.ai/api/resources/structured-outputs-and-json-mode.json"
    }
  ]
}