{"_id": {"$oid": "6ac4c7b6164e0f17c0b23a0d"}, "test_id": "T1875", "benchmark": "library_cards", "date": "2026-09-28", "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-sonnet-5-5", "dataclass": "Document", "temperature": 0.0, "role_description": "You are a historian with keyword knowledge", "prompt_file": "prompt_year-string.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\": \"string\",\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 a string\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": "```json\n{\n  \"type\": {\n    \"type\": \"Reference\"\n  },\n  \"author\": {\n    \"last_name\": \"Montaghemi\",\n    \"first_name\": \"Nourhomadeh\"\n  },\n  \"publication\": {\n    \"title\": \"\",\n    \"year\": \"\",\n    \"place\": \"\",\n    \"pages\": \"\",\n    \"publisher\": \"\",\n    \"format\": \"\"\n  },\n  \"library_reference\": {\n    \"shelfmark\": \"\",\n    \"subjects\": \"\"\n  }\n}\n```", "model": "claude-sonnet-5-5", "provider": "anthropic", "finish_reason": "end_turn", "usage": {"input_tokens": 1348, "output_tokens": 157, "total_tokens": 1505, "reasoning_tokens": 0, "input_cost_usd": 0.002696, "output_cost_usd": 0.00157, "reasoning_cost_usd": 0.0, "estimated_cost_usd": 0.004266}, "duration": 2.5160984992980957, "timestamp": "2026-09-28T21:47:31.834939", "parsed": {"type": {"type": "Reference"}, "author": {"last_name": "Montaghemi", "first_name": "Nourhomadeh"}, "publication": {"title": "", "year": "", "place": "", "pages": "", "publisher": "", "format": ""}, "library_reference": {"shelfmark": "", "subjects": ""}}, "conversation_id": "c43b502f-7b22-4478-b7e4-c2c1b4c4f025", "score": {"f1_score": 0.33, "precision": 0.3333333333333333, "recall": 0.3333333333333333, "true_positives": 1, "false_positives": 2, "false_negatives": 2, "field_scores": {"publication.year": {"response": null, "ground_truth": null, "score": 1.0}, "type.type": {"response": "Reference", "ground_truth": "Reference", "score": 1.0}, "publication.title": {"response": null, "ground_truth": "Montaghemi, Nourhomadeh", "score": 0.0}, "library_reference.subjects": {"response": null, "ground_truth": null, "score": 1.0}, "publication.place": {"response": null, "ground_truth": null, "score": 1.0}, "publication.format": {"response": null, "ground_truth": null, "score": 1.0}, "author.last_name": {"response": "Montaghemi", "ground_truth": "Sonnenbichler", "score": 0.34782608695652173}, "publication.pages": {"response": null, "ground_truth": null, "score": 1.0}, "library_reference.shelfmark": {"response": null, "ground_truth": null, "score": 1.0}, "publication.editor": {"response": null, "ground_truth": null, "score": 1.0}, "publication.publisher": {"response": null, "ground_truth": null, "score": 1.0}, "author.first_name": {"response": "Nourhomadeh", "ground_truth": null, "score": 0.0}}, "total_fields": 12}, "raw_response": "{\"id\":\"msg_011CfWR1H4vWnEcqrr46XE2C\",\"container\":null,\"content\":[{\"citations\":null,\"text\":\"```json\\n{\\n  \\\"type\\\": {\\n    \\\"type\\\": \\\"Reference\\\"\\n  },\\n  \\\"author\\\": {\\n    \\\"last_name\\\": \\\"Montaghemi\\\",\\n    \\\"first_name\\\": \\\"Nourhomadeh\\\"\\n  },\\n  \\\"publication\\\": {\\n    \\\"title\\\": \\\"\\\",\\n    \\\"year\\\": \\\"\\\",\\n    \\\"place\\\": \\\"\\\",\\n    \\\"pages\\\": \\\"\\\",\\n    \\\"publisher\\\": \\\"\\\",\\n    \\\"format\\\": \\\"\\\"\\n  },\\n  \\\"library_reference\\\": {\\n    \\\"shelfmark\\\": \\\"\\\",\\n    \\\"subjects\\\": \\\"\\\"\\n  }\\n}\\n```\",\"type\":\"text\"}],\"model\":\"claude-sonnet-5-5\",\"role\":\"assistant\",\"stop_reason\":\"end_turn\",\"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\":1348,\"output_tokens\":157,\"server_tool_use\":null,\"service_tier\":\"standard\",\"output_tokens_details\":{\"thinking_tokens\":0}},\"stop_details\":null,\"diagnostics\":null}"}, "scoring": {"f1_micro": 0.9224456298727944, "f1_macro": 0.9143726235741444, "micro_precision": 0.9141927612850752, "micro_recall": 0.9308488612836439, "total_instances": 263, "total_tp": 2248, "total_fp": 211, "total_fn": 167, "cost_summary": {"total_input_tokens": 364856, "total_output_tokens": 59457, "total_tokens": 424313, "input_cost_usd": 0.7297120000000018, "output_cost_usd": 0.5945699999999998, "total_cost_usd": 1.324282}}, "pricing": {"bucket_date": "2026-09-28", "age_days": 0, "input_price_per_million": 2.0, "output_price_per_million": 10.0}, "timing": {"total_response_s": 762.89, "mean_response_s": 2.9, "slowest_response_s": 8.97, "inputs_timed": 263, "inputs_stored": 263, "span_s": 75.4}, "normalized_score": 91.43726235741444}