{ "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": "786c043c14b5014fa2c10d6d195fb250d81c16c15c449bc72ab7c8f86bdd8b66", "/home/janko/DP/zp-agent/tools/answer_evaluation/graph_answer_prompt.txt": "c7104ffb08b5b384f38d48fbdad40ccd40de61beace984d8a118cf12bd229860", "/home/janko/DP/zp-agent/tools/answer_evaluation/context_policy.py": "ee3c423772800d3e7368fff9b48bcd464a98a741b87a0c79158398ed22a3dc00", "/home/janko/DP/zp-agent/tools/answer_evaluation/checked_generation.py": "e82b95314b8c0ae9ba82353b98876da7b2a4dce464eb21129ad904bf58b8ef5e", "/home/janko/DP/zp-agent/tools/answer_evaluation/answer_format.py": "86a27b4aebc6a5077e13794b81957a1cf063a1f3e070c583120ba53c1788d2f8" }, "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": "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" } } ] }