knowledge_navigate
Submitted arguments
{
"node": 82
}Native result and verdict
{
"does_not_license": {
"reading": "ANCHOR: node 82 (node), resolving to 1 node(s).\n\nVISITED 1 node(s):\n 82 document provider-groups\n TEXT:\nsource: provider-groups\nstate: shipped\ntable_state: converted\ngavel vintage: 2026-08-25\nupstream files: data.parquet\nnamed by: pipelines/coverage-intelligence/build_filed_charge_extract.py names the object, pipelines/coverage-intelligence/probe_hospital_corpus.py names the object\ngavel row count: 146\nnote: [hospital/45 CFR 180.50(d)(6)] Which NPIs are one health system, read from each system's own cms-hpt.txt rather than clustered on name similarity. One row per hospital: the system's slug and EIN, the type_2_npi that addresses its filing in hospital-price-transparency, the name the system giv\n [TEXT CUT AFTER 600 OF 1100 CHARACTERS. The whole span is bytes 0-1100 of this document's normalized text.]\n\nSOURCE DOCUMENTS:\n 82 provider-groups sha256 dc9cc74f48ad9871a7256c346c9c139018400b9515e4fa7c917d8056c2c4fa19\n\nThis answer is stated against numbering e492637bb79c8fa9. A claim about any node id above is only true against that numbering, so name it.\nThe TEXT under a chunk is that chunk's indexed span, verbatim, at the byte offsets named beside it. You may quote it and say the document reads this way there. You may not say the chunk is about your query, answers it, or supports your sentence: the retrieval put the span in front of you and reading it is not evidence that the ranking was right.\n\nNO READING IS ATTACHED. These fields carry no interpretation, and this world does not supply one unasked. To obtain a reading, and to find out whether what you are about to write is supported, call judgement_check with receipt \"r2411\" and the claims you intend to make. A claim written without checking it is a claim this world did not license.\n\nIf you can write your claim as an expression over the figures above, for example {\"op\": \"<=\", \"left\": \"anchor.nodes[0]\", \"right\": 12, \"scope\": \"marginal\"}, call claim_check with the same receipt instead. It decides by entailment over those figures and never reads your sentence, so it answers the same way in any language. The two checks are alternatives and neither falls back to the other."
},
"kind": "served",
"licence": {
"coverage_database": "Contains information from the CMS Medicare Coverage Database.",
"cpt": "CPT is copyright the American Medical Association. Served under a distribution licence.",
"linkback": "https://hammer.ai/coverage-intelligence",
"terms": "https://hammer.ai/terms"
},
"payload": {
"anchor": {
"form": "node",
"nodes": [
82
],
"stated": "node 82"
},
"boundary_crossings": [],
"documents": [
{
"doc_id": "provider-groups",
"node": 82,
"source_sha256": "dc9cc74f48ad9871a7256c346c9c139018400b9515e4fa7c917d8056c2c4fa19"
}
],
"numbering_digest": "e492637bb79c8fa9",
"receipt": "r2411",
"relations": [],
"rollups": [],
"rows": [],
"visited": [
{
"key": "provider-groups",
"kind": "document",
"node": 82,
"step": 0,
"text": "source: provider-groups\nstate: shipped\ntable_state: converted\ngavel vintage: 2026-08-25\nupstream files: data.parquet\nnamed by: pipelines/coverage-intelligence/build_filed_charge_extract.py names the object, pipelines/coverage-intelligence/probe_hospital_corpus.py names the object\ngavel row count: 146\nnote: [hospital/45 CFR 180.50(d)(6)] Which NPIs are one health system, read from each system's own cms-hpt.txt rather than clustered on name similarity. One row per hospital: the system's slug and EIN, the type_2_npi that addresses its filing in hospital-price-transparency, the name the system giv",
"text_byte_end": 1100,
"text_byte_start": 0,
"text_characters": 1100,
"text_truncated": true
}
]
},
"receipt": "r2411",
"session": "e7e2e45e162614c673bd59ad6ba55387",
"tool": "knowledge_navigate",
"world": {
"build": 2,
"description": "What payers publish that they pay, code by code, and what may be said with it.",
"name": "hammer-coverage-intelligence",
"vintage": "2026-10-01"
}
}Permanent saved result
Read this evidence receipt
Explore canonical node 82
claim_check
judgement_check