tests/test_bioprobench_skill.py

• _skills_on_path · function · L36-L40 — def _skills_on_path()
• kernel · function · L44-L45 — def kernel()
• _write · function · L48-L51 — def _write(tmp_path, name, records)
• _answer · function · L54-L55 — def _answer(value)
• test_kernel_module_scope_needs_no_third_party_imports · function · L61-L64 — def test_kernel_module_scope_needs_no_third_party_imports(kernel)
• test_err_scores_identically_across_label_encodings · function · L93-L107 — def test_err_scores_identically_across_label_encodings(kernel, tmp_path, encode)
• test_err_unrecognized_label_is_counted_as_failed_not_scored · function · L110-L119 — def test_err_unrecognized_label_is_counted_as_failed_not_scored(kernel, tmp_path)
• test_err_missing_label_does_not_shift_later_predictions · function · L122-L137 — def test_err_missing_label_does_not_shift_later_predictions(kernel, tmp_path)
• test_empty_record_list_is_an_error_not_a_successful_zero · function · L144-L154 — def test_empty_record_list_is_an_error_not_a_successful_zero(kernel, tmp_path, task)
• test_non_list_json_is_an_error · function · L157-L163 — def test_non_list_json_is_an_error(kernel, tmp_path)
• test_malformed_json_names_the_decode_failure · function · L166-L173 — def test_malformed_json_names_the_decode_failure(kernel, tmp_path)
• test_pqa_confidence_split_accepts_real_confidences · function · L189-L190 — def test_pqa_confidence_split_accepts_real_confidences(kernel, content, expected)
• test_pqa_confidence_split_rejects_unparseable_content · function · L202-L204 — def test_pqa_confidence_split_rejects_unparseable_content(kernel, content)
• test_pqa_bare_answer_never_yields_a_fabricated_confidence · function · L207-L210 — def test_pqa_bare_answer_never_yields_a_fabricated_confidence(kernel)
• test_pqa_end_to_end_counts_unparseable_answers_as_failed · function · L213-L225 — def test_pqa_end_to_end_counts_unparseable_answers_as_failed(kernel, tmp_path)
• test_pqa_end_to_end_scores_a_well_formed_file · function · L228-L244 — def test_pqa_end_to_end_scores_a_well_formed_file(kernel, tmp_path)
• test_pqa_both_separators_accept_the_same_confidences · function · L252-L255 — def test_pqa_both_separators_accept_the_same_confidences(kernel, token)
• test_pqa_ampersand_branch_rejects_what_the_fallback_rejects · function · L259-L264 — def test_pqa_ampersand_branch_rejects_what_the_fallback_rejects(kernel, token)
• test_pqa_answer_may_itself_contain_an_ampersand · function · L275-L277 — def test_pqa_answer_may_itself_contain_an_ampersand(kernel, content, expected)
• test_pqa_probability_confidence_reaches_failed_rate_not_a_worst_case_brier · function · L280-L294 — def test_pqa_probability_confidence_reaches_failed_rate_not_a_worst_case_brier( kernel, tmp_path )
• test_trigger_batch_inference_exposes_the_endpoint · function · L297-L299 — def test_trigger_batch_inference_exposes_the_endpoint(kernel)