Comparable Map
comparable_mapWhat is one thing I hold comparable to at a school I am considering? One learning unit of any kind - a course at the school it was taken at, an exam at a score, a learning unit by id, or a certification - compared with any target school: the combined check. Two equal sources, four steps run side by side: (1) comparability direct from CourseShelf - the receiver's own published mappings; (2) known equivalencies direct from CourseAtlas, live - what institutions report, CollegeBoard's among them as CourseAtlas carries them; (3) inferred comparability from CourseShelf's comparability anchors (hop 1: an exam at a shared score, a state course, a mapping, crossing kinds); (4) inferred equivalency from CourseAtlas's equivalency anchors (hop 2, its own chain). kind narrows them: known runs 1 and 2, inferred runs 3 and 4, both runs all four. The inferred comparability walks the published links of every kind (a published rule one way; an exam, through its learning unit, at a shared score, a common course number, or an agreement's or state's course both ways), crossing kinds, up to depth links. Each step says found, none, not held, error, timeout or skipped, with its time in ms. The known mappings (steps 1 and 2) decide the state - covered, missing or unknown - and the same mapping in both sources is corroboration, both rows shown; an exam lays out every score tier the target holds with the held score placed and the highest tier met marked. The inferred landings sit beside it, each with its path of published links and the rows it rests on, never counted, and not listed again on a course a known mapping reaches. Every row says its kind: comparable, known equivalent, inferred comparable, inferred equivalent. An exam is read by its learning unit under its board. Recognition is the target school's act. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"target_unitid": "<target_unitid>",
"item": "<item>"
},
"name": "comparable_map"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| item | Yes | One learning unit: a course { unitid, code as printed (e.g. BIOL 100) }, an exam { program (e.g. AP), exam (its code or title), score }, { learning_unit_id }, or { certification_ctid } | |
| kind | No | Optional: known (steps 1-2), inferred (steps 3-4) or both (default) | |
| depth | No | Optional: the most published links an inferred path may take, 1 to 3 (default 2) | |
| sources | No | Optional information-source selection: all (default), or a nonempty array of distinct numbers: 1 gathered published CourseShelf comparables, 2 school-published CourseAtlas equivalencies, 3 inferred CourseShelf comparability through anchors, 4 inferred CourseAtlas equivalency through anchors. Any combination is allowed. An explicit kind intersects this selection; an empty intersection is invalid. Unselected engines report not_requested. Required identity/reference reads may still be needed. Send continuation arguments unchanged. | |
| audience | No | Optional: who the answer is for. student (the default): a course at the target school itself is met from the student's own transcript, or as entered, unless its grade is failing (F, U, NC) or withdrawn (W). institution: the target's own course counts only with explicit earned-credit or completion evidence. Carried in continue.arguments; send it back unchanged. | |
| target_unitid | Yes | The school to compare with, any school, by IPEDS UNITID, e.g. 240727 | |
| courseatlas_depth | No | Optional: CourseAtlas's chain depth, 1 to 3 (default 2, the transfer map's own) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| item | No | The learning unit as read | |
| known | No | Each known row (comparable, known equivalent) with its band and corroboration | |
| state | No | covered | missing | unknown, from the known steps alone (reason says why; candidates when the exam or school fits several) | |
| steps | No | Each read as it ran, in order: { step, source, asked, outcome, count, ms, records, detail } - request, item, courseatlas_identity, courseshelf_published, courseatlas_direct, courseshelf_inferred, courseatlas_inferred, target_course_join | |
| tiers | No | For an exam: every score tier the target holds - minimum, scores, the courses it earns, met, highest_met | |
| target | No | The target, with its CourseAtlas identity and the time that read took | |
| contract | Yes | ||
| inferred | No | Each inferred landing (inferred comparable, inferred equivalent): its path (inferred_through) and the published rows it rests on (inferred_from_ids); never counted | |
| lands_as | No | Known receiving landings and distinct receiver-owned coursework, with actual identity, full rule/source/target/connective evidence, and applicability_support {established,missing_inputs}. A known comparison is evidence; conditional policy, additional-source packages or unresolved OR awards are not established completion or additive credits. | |
| exam_unit | No | For an exam, its learning unit under its board, which it was read by | |
| statement | Yes | ||
| understood | No | ||
| next_actions | No | ||
| held_at_receiver | No | When actual course identity is owned by the receiver: origin, learning_unit_id, retained transcript evidence, earned_status and missing_evidence. Identity establishes applicability; only explicit earned/completed evidence establishes earned completion. No transfer rule is manufactured | |
| source_reads_complete | No | Whether selected source evidence completed, distinct from held-item pagination. A response-window limit, failed read or retained incomplete page prevents a complete-source claim; checklist_map includes prior-learning evidence in this scope. |