418 lines
11 KiB
JSON
418 lines
11 KiB
JSON
{
|
|
"method": "Live synthetic functional checks; separate from corpus accuracy metrics.",
|
|
"model": "model120-fast",
|
|
"hashes": {
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/check_context_scenarios.py": "99dbae2747183622e0823cd8f6536f4ff38ef56d0e41dd7855096d47af3b1c37",
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/graph_answer_prompt.txt": "fc9f2f8d52e70a8d67b9f4814b3f15e6be64bf88afe53ce4db4f037bde00e064",
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/context_policy.py": "0dc2a056ca0d886d7cc8248ed4632c910c5e35bebd03ef94573df41802297f47",
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/checked_generation.py": "cb821a65327424c19cbd996190b14e6aa30d9b909493f11716552f71249a0529",
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/answer_format.py": "86a27b4aebc6a5077e13794b81957a1cf063a1f3e070c583120ba53c1788d2f8",
|
|
"/home/janko/DP/zp-agent/tools/answer_evaluation/render_answer.py": "609c534a37899b3febcea32d983da4b806c287de8f2ddf9bc0675e3280859002"
|
|
},
|
|
"scenarios": [
|
|
{
|
|
"id": "complete",
|
|
"question": "Uveď názov práce osoby Eva Vzorová a rok práce.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": true,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "incomplete_without_truncated",
|
|
"question": "Uveď názov práce osoby Eva Vzorová a rok práce.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": false,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "truncated",
|
|
"question": "Uveď názov práce osoby Eva Vzorová a rok práce.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": false,
|
|
"truncated": true,
|
|
"truncation_reasons": [
|
|
"limit"
|
|
],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "unknown_completeness",
|
|
"question": "Uveď názov práce osoby Eva Vzorová a rok práce.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": null,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "exact_count_partial_evidence",
|
|
"question": "Aký je počet vyhovujúcich osôb?",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": false,
|
|
"truncated": true,
|
|
"truncation_reasons": [
|
|
"evidence_limit"
|
|
],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": {
|
|
"count": 2,
|
|
"complete": true
|
|
},
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"count": 2
|
|
}
|
|
},
|
|
{
|
|
"id": "same_person_child_tag",
|
|
"question": "Uveď názov práce osoby Eva Vzorová v roku 2026 s kľúčovým slovom python.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": true,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
},
|
|
{
|
|
"source_id": "S2",
|
|
"document_path": "child.md",
|
|
"source_url": "https://example.test/child"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
},
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"keyword": "python",
|
|
"document_path": "child.md",
|
|
"source_url": "https://example.test/child"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"keyword": "python",
|
|
"evidence_documents": [
|
|
"a.md",
|
|
"child.md"
|
|
],
|
|
"source_urls": [
|
|
"https://example.test/a",
|
|
"https://example.test/child"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"keyword": "python"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "same_person_year_child_tag",
|
|
"question": "Ktorá osoba spĺňa kľúčové slovo python a rok práce 2026?",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": true,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
},
|
|
{
|
|
"source_id": "S2",
|
|
"document_path": "child.md",
|
|
"source_url": "https://example.test/child"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
},
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"keyword": "python",
|
|
"document_path": "child.md",
|
|
"source_url": "https://example.test/child"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"year": 2026,
|
|
"keyword": "python",
|
|
"evidence_documents": [
|
|
"a.md",
|
|
"child.md"
|
|
],
|
|
"source_urls": [
|
|
"https://example.test/a",
|
|
"https://example.test/child"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"claims": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"year": 2026,
|
|
"keyword": "python"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": "type_is_not_keyword",
|
|
"question": "Uveď názov diplomového projektu osoby Eva Vzorová a rok.",
|
|
"context": {
|
|
"status": "ok",
|
|
"reason": null,
|
|
"complete": true,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [
|
|
{
|
|
"source_id": "S1",
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"facts": [
|
|
{
|
|
"person": "Eva Vzorová",
|
|
"title": "Vyhľadávanie informácií",
|
|
"year": 2026,
|
|
"document_path": "a.md",
|
|
"source_url": "https://example.test/a"
|
|
}
|
|
],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "ok",
|
|
"no_keyword": true
|
|
}
|
|
},
|
|
{
|
|
"id": "no_answer",
|
|
"question": "Akú prácu má Neexistujúca Osoba?",
|
|
"context": {
|
|
"status": "no_answer",
|
|
"reason": "unknown_person",
|
|
"complete": true,
|
|
"truncated": false,
|
|
"truncation_reasons": [],
|
|
"index_version": {
|
|
"version": "synthetic-functional-fixture"
|
|
},
|
|
"sources": [],
|
|
"facts": [],
|
|
"aggregation": null,
|
|
"answer_candidates": []
|
|
},
|
|
"expected": {
|
|
"status": "no_answer"
|
|
}
|
|
}
|
|
]
|
|
}
|