{"_id": {"$oid": "6a478c6124b401ab26c43d9c"}, "test_id": "T1195", "benchmark": "library_cards", "date": "2026-07-02", "tags": {"document-type": ["index-card"], "writing": ["typed", "printed", "handwritten"], "century": [20, 19], "language": ["de", "fr", "en", "la", "el", "fi", "sv", "pl"], "layout": ["index"], "entry-type": ["bibliographic"], "task": ["information-extraction"]}, "contributors": ["gabriel_muller", "maximilian_hindermann"], "hidden": false, "config": {"provider": "anthropic", "model": "claude-fable-5", "dataclass": "Document", "temperature": 0.0, "role_description": "You are a historian with keyword knowledge", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "Extract the bibliographic information about a historical dissertation from this index card and return it as a structured JSON object with the following exact format:\n\n```json\n{\n  \"type\": {\n    \"type\": \"Dissertation or thesis\" OR \"Reference\"\n  },\n  \"author\": {\n    \"last_name\": \"string\",\n    \"first_name\": \"string\"\n  },\n  \"publication\": {\n    \"title\": \"string\",\n    \"year\": integer,\n    \"place\": \"string or empty string\",\n    \"pages\": \"string or empty string\",\n    \"publisher\": \"string or empty string\",\n    \"format\": \"string or empty string\"\n  },\n  \"library_reference\": {\n    \"shelfmark\": \"string or empty string\",\n    \"subjects\": \"string or empty string\"\n  }\n}\n```\n\nEXTRACTION RULES:\n1. **Card Type**: If a card contains the note \"s.\" on a separate line, it is a \"Reference\". Otherwise, it is a \"Dissertation or thesis\".\n\n2. **Author**: Extract last_name and first_name. If only one name is given, put it in last_name and leave first_name empty.\n\n3. **Publication**:\n   - title: The main title of the work\n   - year: Publication year as integer\n   - place: Publication place\n   - pages: Page count (remove \" S.\" suffix if present)\n   - publisher: Publishing house/institution\n   - format: Usually \"8\u00b0\", \"8'\", or \"4\u00b0\" - single value only\n\n4. **Library Reference**:\n   - shelfmark: Often begins with \"Diss.\" or \"AT\", may be marked with \"Standort:\"\n   - subjects: Subject classifications or keywords\n\n5. **Missing Information**: Use empty string \"\" for missing text fields, omit year fields entirely if not present.\n\n6. **Ignore**: Disregard any information that doesn't fit into these categories.\n\nReturn ONLY the JSON object, no additional text or explanation.", "results": {"text": "{\"type\":{\"type\":\"Reference\"},\"author\":{\"last_name\":\"Montgomery\",\"first_name\":\"R\"},\"publication\":{\"title\":\"The institutions that train ministers ...\",\"year\":\"1933\",\"place\":\"New York\",\"pages\":\"\",\"publisher\":\"\",\"format\":\"\",\"editor\":null},\"library_reference\":{\"shelfmark\":\"k 1 XI 11, Vol.3\",\"subjects\":\"\"}}", "model": "claude-fable-5", "provider": "anthropic", "finish_reason": "tool_use", "usage": {"input_tokens": 2911, "output_tokens": 209, "total_tokens": 3120, "input_cost_usd": 0.02911, "output_cost_usd": 0.010450000000000001, "estimated_cost_usd": 0.03956}, "duration": 6.28742241859436, "timestamp": "2026-07-02T22:54:35.005621", "parsed": {"type": {"type": "Reference"}, "author": {"last_name": "Montgomery", "first_name": "R"}, "publication": {"title": "The institutions that train ministers ...", "year": "1933", "place": "New York", "pages": "", "publisher": "", "format": ""}, "library_reference": {"shelfmark": "k 1 XI 11, Vol.3", "subjects": ""}}, "conversation_id": "75162df0-5218-4f40-9f97-92f42f3e352a", "score": {"f1_score": 0.57, "precision": 0.5714285714285714, "recall": 0.5714285714285714, "true_positives": 4, "false_positives": 3, "false_negatives": 3, "field_scores": {"author.first_name": {"response": "R", "ground_truth": "Mark Arthur", "score": 0.0}, "publication.place": {"response": "New York", "ground_truth": "New York", "score": 1.0}, "author.last_name": {"response": "Montgomery", "ground_truth": "May", "score": 0.3076923076923077}, "library_reference.subjects": {"response": null, "ground_truth": null, "score": 1.0}, "publication.editor": {"response": null, "ground_truth": null, "score": 1.0}, "type.type": {"response": "Reference", "ground_truth": "Dissertation or thesis", "score": 0.25806451612903225}, "publication.pages": {"response": null, "ground_truth": null, "score": 1.0}, "library_reference.shelfmark": {"response": "k 1 XI 11, Vol.3", "ground_truth": "k 1 XI 11, Vol.3", "score": 1.0}, "publication.format": {"response": null, "ground_truth": null, "score": 1.0}, "publication.title": {"response": "The institutions that train ministers ...", "ground_truth": "The institutions that train ministers", "score": 0.9487179487179486}, "publication.publisher": {"response": null, "ground_truth": null, "score": 1.0}, "publication.year": {"response": "1933", "ground_truth": 1933, "score": 1.0}}, "total_fields": 12}, "raw_response": "{\"id\":\"msg_012afoeus9Z28YcmNdpi4Ras\",\"container\":null,\"content\":[{\"id\":\"toolu_01QV3Mn4EHFDdzD1k3q3ev4D\",\"caller\":{\"type\":\"direct\"},\"input\":{\"type\":{\"type\":\"Reference\"},\"author\":{\"last_name\":\"Montgomery\",\"first_name\":\"R\"},\"publication\":{\"title\":\"The institutions that train ministers ...\",\"year\":\"1933\",\"place\":\"New York\",\"pages\":\"\",\"publisher\":\"\",\"format\":\"\"},\"library_reference\":{\"shelfmark\":\"k 1 XI 11, Vol.3\",\"subjects\":\"\"}},\"name\":\"extract_structured_data\",\"type\":\"tool_use\"}],\"model\":\"claude-fable-5\",\"role\":\"assistant\",\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"cache_creation\":{\"ephemeral_1h_input_tokens\":0,\"ephemeral_5m_input_tokens\":0},\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"inference_geo\":\"global\",\"input_tokens\":2911,\"output_tokens\":209,\"server_tool_use\":null,\"service_tier\":\"standard\",\"output_tokens_details\":{\"thinking_tokens\":0}},\"stop_details\":null}"}, "scoring": {"f1_micro": 0.870756646216769, "f1_macro": 0.8461596958174905, "micro_precision": 0.8602020202020202, "micro_recall": 0.8815734989648033, "total_instances": 263, "total_tp": 2129, "total_fp": 346, "total_fn": 286, "cost_summary": {"total_input_tokens": 770402, "total_output_tokens": 68005, "total_tokens": 838407, "input_cost_usd": 7.704020000000027, "output_cost_usd": 3.400249999999999, "total_cost_usd": 11.104270000000001}}, "normalized_score": 84.61596958174906}