Metadata-Version: 2.5
Name: groundgate
Version: 0.11.0
Summary: Deterministic admission for LLM-extracted facts: admit, flag for verification, or reject, with receipts.
Project-URL: Repository, https://github.com/mohanraj00/groundgate
Project-URL: Documentation, https://github.com/mohanraj00/groundgate/blob/main/docs/guide.md
Project-URL: Specification, https://github.com/mohanraj00/groundgate/blob/main/SPEC.md
Project-URL: Changelog, https://github.com/mohanraj00/groundgate/blob/main/CHANGELOG.md
Project-URL: Issues, https://github.com/mohanraj00/groundgate/issues
Author: Mohan Raj
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: extraction,grounding,langextract,llm,verification
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing
Classifier: Typing :: Typed
Requires-Python: >=3.10
Provides-Extra: langextract
Requires-Dist: langextract>=1.0; extra == 'langextract'
Provides-Extra: pdf
Requires-Dist: pdfminer-six>=20231228; extra == 'pdf'
Description-Content-Type: text/markdown

# groundgate

**LLMs propose facts. groundgate decides which ones you can trust.**

groundgate is a deterministic admission layer for LLM document extraction. You give it a
document, a schema, and the facts an extractor proposed. Every fact comes back with one of three
outcomes:

- **admitted**: every check passed;
- **needs_verification**: nothing failed, but a person should look, and the decision says where;
- **rejected**: a check failed, with a stable reason code.

Every run writes a receipt with hashes of every input. Anyone can re-derive it byte for byte.

The goal is to admit as many fields as possible with the right value, while wrong values almost
never get in. I judge every rule by two numbers: the facts admitted with a right value, and the
wrong extractions admitted (escapes). Reviews are the cost between them: each one is a value that
a person confirms by hand.

![The groundgate review page for IRS Publication 590-A. Left: a Roth IRA limit flagged QUALIFIED_VALUE because the model cited the spousal-deduction sentence ("more than $236,000"). Right: the source text, with that citation outlined in amber and the correct Roth sentence, admitted, highlighted in green below it.](https://raw.githubusercontent.com/mohanraj00/groundgate/main/docs/report.png)

## Why this exists

Current models get most extracted values right. In the benchmark below, 4,233 of 4,350
extractions were correct. The other 117, about 1 in 37, each cited a real place in the document,
so nothing on the page tells you which ones are wrong.

Grounded extraction tools check that the quoted **text** exists in the source. They don't check
the **value** you store. LangExtract is the clearest example, and a good tool. It aligns each
`extraction_text` to the source and reports `MATCH_EXACT`, `MATCH_FUZZY` and so on. It never
looks at the attributes that hold the typed value.

A real case from the benchmark: IRS Publication 560 states two limits a few lines apart.

```text
The limit on elective deferrals, other than catch-up contributions, is $23,500 for 2025 ...
The limit on salary reduction contributions, other than catch-up contributions, is $16,500 for 2025 ...
```

The first is the 401(k) limit. The second is the SIMPLE plan limit. Asked for the 2025 elective
deferral limit, 4 of 14 runs proposed both, and LangExtract marked both quotes `MATCH_EXACT`.
groundgate sent both to a person with `CONFLICTING_CANDIDATES`, because two proposals for one
field disagree. In Publication 15-B, one model stored "$1 million" as 1, also an exact match, and
groundgate flagged it `SCALE_WORD`.

The same gap shows up on the document I used while building the library. I ran Gemini 3.6 Flash and GPT-OSS 120B through
LangExtract on two pages of IRS Publication 590-A. LangExtract aligned all 48 extractions as
`MATCH_EXACT`. groundgate then:

- **rejected** Gemini's reading of a misprinted `$252,0000` as 2,520,000;
- **flagged** three GPT-OSS facts: two took a Roth IRA limit from the spousal-deduction
  sentence, where the numbers match but the text says "more than" where the field says "at
  least", and one is a right value next to an "or more" that the schema did not declare;
- **listed** a required field both models missed;
- **admitted** 44 facts, all with the right value.

One admitted fact still cites the wrong rule. Its number is correct, its comparator matches, and
no span check can tell. I checked every decision by hand; the details are in
[examples/irs-590a](https://github.com/mohanraj00/groundgate/blob/main/examples/irs-590a), which is also the page in the screenshot.

I measured the gap on purpose before writing the library. On 51 facts from two public-domain
government documents, LangExtract's strictest setting (`MATCH_EXACT` only) accepted **100%** of
planted value and unit errors whose quote was correct. groundgate caught **all** of them and
rejected **none** of the correct facts. The method and full tables are in
[spikes/m0_5](https://github.com/mohanraj00/groundgate/blob/main/spikes/m0_5/README.md).

LangExtract locates the text. groundgate checks the number in it.

## Benchmark

Seven models (Gemini, GPT and Claude, each through its own CLI) ran through LangExtract on 30
public-domain FDA drug labels, NTSB accident reports and IRS publications, at two chunk sizes. A
person checked every gold fact. These are spec 0.1's numbers on the first set, as published. Of 4,350 extractions, 117 were wrong: the wrong value, a value
for a field the document doesn't state, the wrong unit, or not a number.

![Pooled over all 14 runs: MATCH_EXACT accepted 98% of wrong extractions without review, groundgate 6.8%. Of correct extractions citing the right place, MATCH_EXACT rejected 4.6%, groundgate 0.3%. groundgate sent 12% of extractions to a person.](https://raw.githubusercontent.com/mohanraj00/groundgate/main/bench/charts/summary.svg)

| | LangExtract, `MATCH_EXACT` | groundgate |
|---|---:|---:|
| wrong extractions accepted without review | 98.3% (115/117) | 6.8% (8/117) |
| correct extractions citing the right place, rejected | 4.6% (194/4,233) | 0.3% (14/4,233) |
| extractions sent to a person | 0% | 12.1% (526/4,350) |
| gold facts admitted with a right value | 92.5% (3,588/3,878) | 87.1% (3,379/3,878) |

A gold fact is one value that a document states for a field, so a field with 12 strengths counts
12 times, and each fact counts once in each run. groundgate admits fewer right facts than
`MATCH_EXACT`, and lets in 8 wrong values instead of 115. With the reviews, 96.5% (3,742/3,878)
of gold facts get a right value.

Of the 526 extractions groundgate sent to a person, 92 were wrong; a random sample that size
would have held about 14. groundgate also rejected 71 correct values that LangExtract had aligned
to a place that doesn't state them: the value was right, the evidence wasn't.

Most catches (84 of 109) were `CONFLICTING_CANDIDATES`: a model proposed two values for a
single-valued field, and groundgate sent both to review instead of picking one.

Six of the 8 that got through are the case groundgate says it cannot catch (see
[What it does not do](#what-it-does-not-do)). Five models took metoprolol's heart failure maximum
(200 mg) as the hypertension maximum, and one took lisinopril's renal impairment dose as the usual
starting dose. Each number is real and cited correctly; it belongs to another condition. The
other two read levothyroxine's 1.6 mcg/kg/day as a flat 1.6 mcg, which the unit check allows.
Putting all seven models through one gate caught one more, because when they were wrong they
mostly agreed. Spec 0.2 goes after both: keyed fields check the condition, and a dose per
kilogram no longer passes as a flat dose.

The benchmark also found a bug. When LangExtract's chunker cut "29.97" after "29.", groundgate
read the span as 29, which its own spec forbids. It's fixed, and three wrong altimeter settings no
longer get through.

Tables and planted-error results: [bench/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/RESULTS.md). Method and caveats:
[bench/README.md](https://github.com/mohanraj00/groundgate/blob/main/bench/README.md). The write-up, with what got through and why:
[Grounding is a contract, not a citation](https://mohanraj00.github.io/tech/grounding-is-a-contract/).

### Spec 0.2 on a second set

Spec 0.2's rules were written from the escapes above, so they can't be measured on the same
documents. I picked 101 new ones by rules frozen before anyone read them: FDA labels with doses
per indication or per kilogram, IRS publications and Federal Register rules with "increased from",
"must not be more than" and "$1.2 million". The same seven models ran at both chunk sizes. Every
candidate was decided twice, by spec 0.1 (the released 0.1.0 wheel) and by spec 0.2. Pooled over
14 runs on the 74 documents checked in full:

| | LangExtract, `MATCH_EXACT` | groundgate, spec 0.1 | groundgate, spec 0.2 |
|---|---:|---:|---:|
| wrong extractions accepted without review | 85.7% (705/823) | 30.7% (253/823) | 8.8% (72/823) |
| correct extractions citing the right place, rejected | 3.8% (230/6,080) | 11.3% (690/6,080) | 0.5% (28/6,080) |
| extractions sent to a person | 0% | 28.2% (1,950/6,903) | 39.6% (2,730/6,903) |
| gold facts admitted with a right value | 84.6% (4,751/5,614) | 51.0% (2,862/5,614) | 53.2% (2,985/5,614) |

642 of 0.1's 690 false rejects are in the 19 documents picked for amounts like "$1.2 million",
which 0.1 could not match. 82 of its 253 escapes were a right value under the wrong indication;
0.2 lets 10 of those through. It pays in review load. The 72 that still got through are listed
one by one in [bench/set2/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/set2/RESULTS.md), and two rules that need work are
open for the next version (#51, #52).

This set shows the gap that matters most. Spec 0.2 admits a right value for 53.2% of gold facts,
and the reviews bring it to 86.8% (4,873/5,614). Closing that gap without new escapes is the work
of the versions since: the 0.4 key clear and the 0.5 evidence list aim at it, and the next section
measures 0.5.

### Spec 0.5 on new 10-K filings

Spec 0.5 lets the extractor cite each part of a value: the sign, the scale, the unit, the field
and the key. I measured it on 20 10-K filings that the rules did not come from, and on the IRS
filing-status set. One extractor (Claude Haiku 4.5) ran once per set, and every candidate was
decided by spec 0.4 (the released 0.4.0 wheel) and by spec 0.5. A person labeled every admitted
value blind.

| Set | Decision | Right values admitted | Escapes |
|---|---|---:|---:|
| new 10-K set | spec 0.4 | 23 | 1 |
| new 10-K set | spec 0.5 | 26 | 0 |
| IRS filing status | spec 0.4 | 28 | 0 |
| IRS filing status | spec 0.5 | 28 | 0 |

Two rules still cost right values, and neither adds an escape: a unit item fails when the unit is
already next to the number, and a scale quote must match the case of the text. Without the unit
check, spec 0.5 admits 33 right values on the 10-K set. Spec 0.6 changes the unit rule (below).
[bench/evidence/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/evidence/RESULTS.md) has every number.

### Spec 0.6 on a held-out 10-K set

The 0.6 rules came from that 10-K set and the status set, so I measured them on 20 other 10-K
filings (`bench/sec3`). Two extractors ran once each, with `gg.extractor_schema(schema)` as their
structured output and the guide's instructions. Each rule was decided alone, and a person labeled
every admitted value, and every value whose outcome changed, blind.

| Decision | claude-haiku-5-5 | gpt-6-luna | Escapes |
|---|---:|---:|---:|
| spec 0.5 | 15 | 17 | 0 |
| a unit item that repeats the unit passes (#145) | 15 | 27 | 0 |
| a scale quote in any case (#145, not shipped) | 15 | 17 | 0 |
| `between` with words before an `and` range (#159) | 15 | 17 | 0 |
| a heading scale over a table (#162) | 15 | 17 | 0 |

The numbers are right values admitted. The unit rule admits 10 more right values on one run. The
scale rule admits none more, so it did not ship. #159 and #162 only add flags, and they cost no
right value. [bench/sec3/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/sec3/RESULTS.md) has every number.

### Spec 0.7 on held-out agency reports

The 0.7 unit rule (#164) came from the 10-K sets and the status set, so I measured it on the
principal statements of 20 FY2025 agency financial reports (`bench/afr`). The same two
extractors ran once each, and a person labeled every admitted value blind.

| Decision | claude-haiku-5-5 | gpt-6-luna |
|---|---|---|
| spec 0.6 | 3 right, 1 escape | 6 right, 0 escapes |
| spec 0.7 | 3 right, 1 escape | 6 right, 0 escapes |

The numbers count admitted values. Each run made 100 proposals, and the rule changes the
outcome of none of them. Most proposals fail on the field or the key citation before the unit
matters. [bench/afr/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/afr/RESULTS.md) has every number.

### Spec 0.8 on held-out state and agency reports

0.8 is about yield. I measured each change on documents that it did not come from: the 20 agency
reports of `bench/afr` for the PDF table rows of #230, 10 FY2025 state ACFRs (`bench/acfr`) for
#242, 10 more (`bench/acfr2`) for #249, #250 and #256, and 10 drug labels (`bench/strings`) for
#140. A person labeled every admitted value blind. #242, #250 and #140 change no decision on their
sets, so the table leaves them out.

| Change | Set | claude-haiku-5-5 | gpt-6-luna |
|---|---|---|---|
| PDF table rows as lines with tabs (#230) | `bench/afr` | 3 to 73 right, 1 to 0 escapes | 6 to 74 right, 0 escapes |
| The value where the field item passes, a column unit (#249) | `bench/acfr2` | 5 to 7 right, 0 escapes | 2 to 2 right, 0 escapes |
| No role `key` on a field with no keys (#256) | `bench/acfr2` | 10 to 23 right, 0 escapes | 0 to 9 right, 0 escapes |

The numbers count admitted values. The #230 rows compare the 0.7 text under spec 0.7 with new
runs on the new text under 0.8. #249 and #250 came from `bench/afr`, so the #230 rows include
their effect on that set (#263). The #256 rows ask a schema with no keys on its fields, so they do not compare with
the #249 row. [bench/afr/tabs/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/afr/tabs/RESULTS.md),
[bench/acfr/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/acfr/RESULTS.md), [bench/acfr2/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/acfr2/RESULTS.md),
[bench/strings/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/strings/RESULTS.md) and
[bench/acfr/keyrole/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/acfr/keyrole/RESULTS.md) have every number.

### Spec 0.9 on requested fields

0.9 is about misses on the fields that an app asks for. `bench/requested` has 61 held-out documents
in three kinds that no rule came from: 20 component datasheets, 20 health plan SBCs and 21 annual
reports. Each kind has one fixed field list, and a person labeled each field blind before any model
output. The documents state 196 of the labeled values. Both arms use `gpt-6.1-sol` at medium effort.

| Arm | Right values admitted | Right absences | Escapes | Reviews | Silent misses | Miss rate |
|---|---:|---:|---:|---:|---:|---:|
| One-pass extraction with feedback (baseline) | 9 | 0 | 1 | 69 | 118 | 95.41% |
| `groundgate.extract` | 16 | 6 | 0 | 119 | 61 | 91.84% |

The loop halves the silent misses and admits no wrong value, but both arms still miss more than 90%
of the stated values. The loop did not complete 18 of the 21 annual reports: each stopped at a
harness limit. [bench/requested/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/requested/RESULTS.md) has every number.

### Spec 0.10 on requested fields

0.10 is about fewer reviews of right values. `bench/requested3` has 111 held-out documents in
four kinds that no rule came from: 18 component datasheets, 23 health plan SBCs, 20 annual
reports and 50 safety data sheets, a new kind. Each kind has one fixed field list. Two blind passes
labeled each field from the original PDFs before any model output. The documents state 305 of
the labeled values. The baseline and `groundgate.extract` use `gpt-6.1-sol` at medium effort. The
`drop_rounded` arm makes no model call: it replays the calls of `groundgate.extract`.

| Arm | Right values admitted | Right absences | Escapes | Reviews | Silent misses | Miss rate |
|---|---:|---:|---:|---:|---:|---:|
| One-pass extraction with feedback (baseline) | 115 | 0 | 2 | 142 | 48 | 62.30% |
| `groundgate.extract` | 97 | 118 | 0 | 160 | 48 | 68.20% |
| `groundgate.extract` with `drop_rounded` | 99 | 118 | 0 | 158 | 48 | 67.54% |

`groundgate.extract` admits no wrong value. The baseline admits 2 wrong values of 117. But
`groundgate.extract` misses more right values than the baseline: 208 of 305 (68.20%) against 190
of 305 (62.30%). The silent misses are the same (48), so the difference is right values that
it sends to review and the baseline admits. It did not complete 15 of the 20 annual reports and
4 of the 18 datasheets: each stopped at a harness limit. Its annual miss rate is 97.06%, against
73.53% for the baseline. Every arm misses more than 60% of the stated values, so 0.10 does
not meet the goal on this set. [bench/requested3/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/requested3/RESULTS.md) has
every number.

### Spec 0.11 on requested fields

`bench/requested4` has 91 documents in the four kinds and field lists of `bench/requested3`. It
is the first set with a development split and a held-out split: a hash of the source family puts
32 documents in development and 59 in held-out. Two blind passes labeled each field from the
original PDFs before any model output. The learning loop ran only on the development split, and
the code froze before the first held-out model call. The 59 held-out documents state 204 of the
labeled values. The arms are the arms of 0.10, with `gpt-6.1-sol` at medium effort.

| Arm | Right values admitted | Right absences | Escapes | Reviews | Silent misses | Miss rate |
|---|---:|---:|---:|---:|---:|---:|
| One-pass extraction with feedback (baseline) | 76 | 0 | 1 | 103 | 25 | 62.75% |
| `groundgate.extract` | 79 | 0 | 1 | 97 | 28 | 61.27% |
| `groundgate.extract` with `drop_rounded` | 81 | 0 | 1 | 95 | 28 | 60.29% |

`groundgate.extract` misses 125 of 204 (61.27%) and the baseline misses 128 of 204 (62.75%).
Each arm admits 1 wrong value. The gap of 3 misses is inside the run noise of the development
split, so I do not claim a difference between the arms. No document stopped at a harness limit.
`groundgate.extract` reports no absence on this set: 0 right absences and 76 unreported
absences. The cause: #382 cuts a region longer than 6,000 characters, a cut marks the search
truncated, and the bench writes an absence only for a search that is not truncated. The queries
of each field include words such as "the" and "and", so the regions cover most of the document.
So its miss rate is not comparable with the 0.10 `groundgate.extract` on `bench/requested3`. Both
problems are open for 0.12 (#464, #466).
Every arm misses more than 60% of the stated values, so 0.11 does not meet the goal on this set.
[bench/requested4/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/requested4/RESULTS.md) has every number.

A judge can clear part of the reviews. A Codex judge (`gpt-6.1-sol`, frozen at threshold 0.9)
answered each of the 104 held-out fields that `groundgate.extract` sent to review with a
candidate, two times. It clears 91 right values in run 1 and 94 in run 2, with no escape. With
these clears, the miss rate would be 16.67% and 15.20%. The judge is a recorded input, not part of
a decision, and these numbers hold for documents that do not attack the model.
[bench/requested4/judge/heldout/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/requested4/judge/heldout/RESULTS.md) has every
number. The review answers of a person did not pass the bar for use as labels: 10 of 132 scored
answers are wrong, with a 95% upper bound of 0.1251 against a bar of 0.05
([bench/requested4/review/RESULTS.md](https://github.com/mohanraj00/groundgate/blob/main/bench/requested4/review/RESULTS.md)).

## Quickstart

```bash
pip install groundgate
```

```python
import groundgate as gg

text = "The IRA contribution limit is $7,000. The deduction phases out above $79,000."
schema = {
    "fields": {
        "ira_limit": {"type": "integer", "unit": "USD"},
        "phaseout_start": {"type": "integer", "unit": "USD"},
    }
}


def cite(field, value, quote):
    """A candidate whose evidence is a quote: groundgate finds it in the text."""
    return {"field": field, "value": value, "unit": "USD", "evidence": [{"text": quote}]}


candidates = [
    cite("ira_limit", "7000", "$7,000"),
    cite("ira_limit", "70000", "$7,000"),  # a digit too many
    cite("phaseout_start", "79000", "$79,000"),  # "above" is not "at"
]
receipt = gg.admit(text, schema, candidates)
for d in receipt.decisions:
    print(f"{d.outcome:<19} {d.field:<15} {d.value:<6} {' '.join(d.codes)}".rstrip())

print(gg.verify(receipt.to_dict(), text, schema, candidates).ok)
```

```text
admitted            ira_limit       7000
needs_verification  phaseout_start  79000  QUALIFIED_VALUE
rejected            ira_limit       70000  VALUE_NOT_IN_EVIDENCE
True
```

The core has no dependencies. `groundgate[pdf]` adds pdfminer.six for PDF text, and
`groundgate[langextract]` installs LangExtract. [docs/](https://github.com/mohanraj00/groundgate/blob/main/docs/README.md) has a guide to writing a
schema, a how-to guide for each task, and [the reference](https://github.com/mohanraj00/groundgate/blob/main/docs/guide.md). An evidence item can also give UTF-8 byte offsets
(`start`, `end`), and it can cite the sign, scale, unit, field or key of the value (spec 0.5).

### With your own model

`gg.extractor_schema(schema)` turns your schema into a JSON Schema for the model's structured
output, so the model sends only your fields, units and keys, and quotes its evidence.
[docs/howto/own-model.md](https://github.com/mohanraj00/groundgate/blob/main/docs/howto/own-model.md) goes from a document to a receipt, and
[docs/howto/feedback.md](https://github.com/mohanraj00/groundgate/blob/main/docs/howto/feedback.md) sends the reasons back to the model.

### With LangExtract

```python
import langextract as lx
from groundgate.adapters.langextract import admit_document

result = lx.extract(text_or_documents=text, prompt_description=prompt, examples=examples)
receipt = admit_document(result, schema)
```

Each extraction's `value` and `unit` attributes are checked at the place LangExtract aligned its
`extraction_text`. The attributes `sign_text`, `scale_text`, `unit_text`, `field_text` and
`key_text` become role items. `field_text` can be a list, such as a row label and a column
header, for up to 8 field items. `source_url` (with `source_quote` and `source_retrieved`) or
`knowledge` becomes outside evidence. An extraction that LangExtract could not align, with no
outside evidence, is rejected `NO_EVIDENCE`.

### From the command line

```bash
groundgate read p590a.pdf --pages 1-2 -o doc.txt --layout layout.json
groundgate admit   doc.txt schema.json candidates.json -o receipt.json
groundgate admit   --docs docs --candidates candidates --schema schema.json --out receipts
groundgate verify  receipt.json doc.txt schema.json candidates.json
groundgate report  receipt.json doc.txt schema.json candidates.json --layout layout.json -o report.html
groundgate schema  schema.json -o extractor.schema.json
groundgate schema check schema.json
```

`read` turns a PDF, HTML, XML or text file into the NFC text everything else reads, and
records the page and box of every word. Text a reader can't see (proof marks drawn off the page,
hidden HTML) is dropped, and superscripts are marked so that 10⁹ reads `10^9`, never `109`.
`admit`, `verify` and `report` read the document from a pipe when DOC is `-`, and also take
`--references`, `--document-source` and `--pack`. `report` refuses to render a receipt that doesn't
re-derive from its inputs. `schema` writes the extractor schema, and `schema check` prints the
settings that make a check fail every time, or pass for the wrong key or field
([Check a schema](https://github.com/mohanraj00/groundgate/blob/main/docs/schema.md#check-a-schema)).
[examples/irs-590a](https://github.com/mohanraj00/groundgate/blob/main/examples/irs-590a) runs the whole pipeline on an IRS publication with cached model output, so it reproduces without an API key.

For a batch, `--docs` holds `<doc>.txt` files and `--candidates` holds matching `<doc>.json`
candidate arrays. `--out` receives one receipt per document and `summary.json` with outcome and
code counts per document and in total, and the CLI prints the totals. The
[guide](https://github.com/mohanraj00/groundgate/blob/main/docs/guide.md#command-line) describes missing and empty candidate files, shared policy
and references, per-document judgments, and the batch options and summary format.

## What it checks

Checks run in a fixed order. The first failure rejects the fact.

| Code | Rejects when |
|---|---|
| `CANDIDATE_INVALID` | the candidate is malformed |
| `FIELD_UNKNOWN` | the field is not in the schema |
| `NULL_STRING_LITERAL` | the value is `"null"`, `"none"`, `"nil"` or `"n/a"`, in any case |
| `TYPE_INVALID` | the value does not parse as the field's type |
| `RANGE_INVALID` | the value is outside the field's bounds |
| `UNIT_INVALID` | the unit is not the field's unit |
| `KEY_INVALID` | the field is keyed by condition, and the key is missing or not one of its keys |
| `NO_EVIDENCE` | the evidence has no value item and no outside item |
| `SPAN_INVALID` | the span is outside the document or splits a character |
| `QUOTE_NOT_FOUND` | the quoted value text is not in the document, or in the reference it cites |
| `VALUE_NOT_IN_EVIDENCE` | no number in the span equals the value, with the sign and scale the evidence gives |
| `UNIT_NOT_IN_EVIDENCE` | the value is there, but with another unit |
| `SOURCE_REJECTED` | only outside evidence supports the value, and the policy rejects it |

A fact that passes every check can still be flagged for a person:

| Code | Flags when |
|---|---|
| `NON_VERBATIM_EVIDENCE` | the quote differs from the text at the span |
| `QUALIFIED_VALUE` | "up to", "approximately", "or more" changes the value, and the schema didn't declare it |
| `SCALE_WORD` | "million", "lakh" and similar follow the value, and the value was given unscaled |
| `PART_MISSING` | the value needs a sign, a scale or a unit that no evidence item supports |
| `SIGN_CITATION_INVALID`, `SCALE_CITATION_INVALID`, `UNIT_CITATION_INVALID`, `FIELD_CITATION_INVALID` | a cited part fails its check |
| `KEY_NOT_AT_VALUE` | the text puts no key, or another key, at the value, such as another indication's heading |
| `KEY_CITATION_INVALID` | the cited key item does not name the key |
| `EVIDENCE_QUOTED`, `EVIDENCE_STATED` | only an external quote, or the extractor's own knowledge, supports the value |
| `LOW_CONFIDENCE` | the extractor's confidence is below the policy minimum |
| `CONFLICTING_CANDIDATES` | another proposal for the same field and key has a different value |
| `RELATION_FAILED` | a relation of the schema, such as a total and its parts, does not add up |
| `MODEL_DOUBT` | a recorded judgment of the policy's judge doubts the value |

Number matching is collision-safe. The span `500 mg` inside `1,500 mg` never reads as 500, a span
that stops at `29.` inside `29.97` never reads as 29, and a malformed number like the `$252,0000`
printed in IRS Publication 590-A never equals 252,000 or 2,520,000. When a span misses the value
but its quote occurs exactly once elsewhere with the right value and unit, groundgate moves the
evidence there and records `EVIDENCE_REANCHORED`. Other info codes say how a fact passed:
`VALUE_DERIVED` (the evidence gave the sign or scale), `KEY_CITED` (a key item put the key at the
value in a table), `ADMITTED_BY_POLICY` (the policy admits its outside evidence) and
`MODEL_CLEARED` (a recorded judgment cleared `KEY_NOT_AT_VALUE`).

The rules are in [SPEC.md](https://github.com/mohanraj00/groundgate/blob/main/SPEC.md). [conformance/](https://github.com/mohanraj00/groundgate/blob/main/conformance) holds 57 language-neutral
vectors that pin every code, and 38 invalid packets that an implementation must refuse, so another
implementation can prove it agrees.

## Receipts

```json
{"groundgate": "0.11",
 "document": {"id": "irs-p590a-2025-pages-1-2", "sha256": "sha256:93e71e53d954...", "source": null},
 "references": [],
 "packs": [],
 "schema_sha256": "sha256:...", "policy_sha256": "sha256:...",
 "decisions": [{"candidate_id": "Gemini_3.6_Flash_Medium/0", "field": "ira_limit_2025", "key": null,
                "outcome": "admitted", "codes": [], "value": "7000", "unit": "USD",
                "source": "document", "ref": null, "url": null,
                "evidence": {"start": 2317, "end": 2323}, "parts": [], "missing": [], "packs": [],
                "candidate_sha256": "sha256:2246982c..."},
               "..."],
 "coverage": [{"field": "roth_phaseout_single_2025_end", "code": "REQUIRED_FIELD_MISSING"}],
 "judgments": [],
 "summary": {"admitted": 44, "needs_verification": 3, "rejected": 1},
 "receipt_sha256": "sha256:..."}
```

Hashes are SHA-256 over RFC 8785 canonical JSON, so a receipt means the same thing in any
language. `groundgate verify` re-runs every decision from the inputs and fails on any difference:
a changed document, schema, policy, candidate or outcome.

## What it does not do

- **It does not judge meaning.** If the model reports a number that really is in the sentence but
  belongs to another field, every span check passes: a model that reads an age-50 limit of $8,000
  as the IRA limit cites a real "$8,000" with the right unit. A second proposer plus
  `CONFLICTING_CANDIDATES` catches it only when the models disagree, and in the benchmark they
  mostly agreed: six of the eight escapes were this case. When the field depends on a condition
  the schema can name, such as a drug's indications, a keyed field checks it (spec 0.2).
- **No dates, arrays of records, or cross-document checks** in spec 0.11.
- **English number formats only.** A decimal comma (`1.234,56`), space groups (`1 234`) and
  number words (`five`) have no value, so a fact that cites them is rejected. The
  [guide](https://github.com/mohanraj00/groundgate/blob/main/docs/guide.md#how-values-are-read) lists what is read. Locale packs for other formats
  are a design ([docs/design/locale-packs.md](https://github.com/mohanraj00/groundgate/blob/main/docs/design/locale-packs.md), #60).
- **No OCR.** Scanned PDFs need a text layer first (for example `ocrmypdf`).
- **No model calls in the decision.** groundgate never asks an LLM whether an LLM was right.
  Since spec 0.4, it reads a judge's answers only as recorded inputs, so a receipt still re-derives
  byte for byte. This judge block is experimental: its one measure on real extractor output is the key
  clear on 10-K filings (#120). `groundgate calibrate` (#112, experimental) measures the
  thresholds on your own documents.
  [How to measure a judge's thresholds](https://github.com/mohanraj00/groundgate/blob/main/docs/howto/calibrate.md) runs it from start to end.

## Status

Alpha. groundgate 0.11.0 implements spec v0.11. [CHANGELOG.md](https://github.com/mohanraj00/groundgate/blob/main/CHANGELOG.md) lists what each version
changes, with its measure. 0.11 adds the store (#288, #402 to #405), the review step and its local
page (#287, #408 to #412), and `groundgate calibrate` inside groundgate (#385). It reads currency
headings and currency names (#367, #368, #423), refuses a bad field name (#359), and cuts large
search regions in the extraction loop (#382). 0.10 adds vocabulary and kind packs (#333 to #339),
relations across fields (#321), currency scales and heading units (#301, #313, #315, #365), up to 8
field items for one value (#300), label cells (#316), dash variants in aliases (#317), and the
runner rules of #318 and #319. 0.9 moves the reader to `groundgate.read` (#289), adds the extraction
loop `groundgate.extract` (#281), keeps an empty table cell in its column and refuses ambiguous
column keys (#280), and keeps PDF running heads out of tables and blank cells in their column
(#279). 0.8 writes PDF table rows as lines with tabs (#230), scales a value by its scale item
(#242), takes the value's occurrence where the field item passes (#249), lets a title key reach a
table with one number column (#250), puts a string value at its first occurrence in its span (#140),
and offers the role `key` only on a field with keys (#256). 0.7 passes a unit item that is away from
the number only at a unit place of the value (#164). 0.6 passes a unit item that repeats the unit
(#145), reads `between` with words before an `and` range (#159) and a scale heading over a table
(#162), and adds a `description` to each field (#171). 0.6.1 adds `gg.feedback_message` (#173). 0.5
makes the evidence a list of items (#141): a value can cite its sign, scale, unit, field and key,
and outside sources, under the app's policy, and `gg.candidate_schema()` (#147) gives the
candidate's JSON Schema. 0.5.1 adds `gg.extractor_schema` and `groundgate schema` (#148), a JSON
Schema for a model's structured output. 0.5.2 adds `groundgate schema check` (#168) and batch
`admit` (#169). 0.4 added recorded judgments (#116), an experimental way for a judge's answers to
clear a key flag or add doubt, with no model call in the decision. 0.3 brought a wider change rule
(#51), abbreviation dots that no longer end a sentence for qualifiers (#63, #77), Indian digit
grouping (#59), ASCII digits (#94), and keys that stop at a label line (#52) or read a table by its
lines (#87). A receipt names the spec version it was decided under, and only that version verifies
it.

[Locale packs](https://github.com/mohanraj00/groundgate/blob/main/docs/design/locale-packs.md) for number formats outside English are a design,
not yet code. Of the [hybrid decisions](https://github.com/mohanraj00/groundgate/blob/main/docs/design/hybrid-decisions.md) design, 0.4 has the
recorded judgments for the key and field questions, and the review step of 0.11 has the audit
sample (#409). Model-proposed locations are not code yet.

## License

Apache-2.0.
