{ "protocol": "edge-ocr-text-v1", "dataset": "OmniParseBench text subset", "repo": "datalab-to/omni_parse_bench", "revision": "961c0f89a2da701f5ce53afbd5e80aa469b0369a", "cases": [ { "id": "ocr-columns-1", "group": "columns", "upstream_page_id": "olmo_multi_column-06dda119744c1212fbb39a789dc34f023f6c_page_4_pg1-p1", "document": "olmo_multi_column:06dda119744c1212fbb39a789dc34f023f6c", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-06dda119744c1212fbb39a789dc34f023f6c_page_4_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-06dda119744c1212fbb39a789dc34f023f6c_page_4_pg1-p1.pdf", "pdf_sha256": "260f7ea8b8066a7d3d6b1f5589c09397aa80d9a8c949769a584e765e40ab4148", "gold_path": "gold/olmo_multi_column-06dda119744c1212fbb39a789dc34f023f6c_page_4_pg1-p1.json", "image": "images-2560/ocr-columns-1.png", "image_sha256": "dd0568a493cf69d2108cd1da1746a15bb165fddfe87e10142100f19de51e3786", "width": 1654, "height": 2339, "original_size": [ 1654, 2339 ], "tests": [ { "id": "06dda119744c1212fbb39a789dc34f023f6c_page_4.pdf_order_5d865c94", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "list", "multi_column" ], "args": { "before": { "text": "Advances in Electromyogram Signal Classification to Improve the quality of Life for the Disable and Aged People.", "max_diffs": 2 }, "after": { "text": "And Its Applications, 4(2).", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-columns-2", "group": "columns", "upstream_page_id": "olmo_multi_column-08c9eac4149a44cf8eed7cf1466ce8afa6b7_page_1_pg1-p1", "document": "olmo_multi_column:08c9eac4149a44cf8eed7cf1466ce8afa6b7", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-08c9eac4149a44cf8eed7cf1466ce8afa6b7_page_1_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-08c9eac4149a44cf8eed7cf1466ce8afa6b7_page_1_pg1-p1.pdf", "pdf_sha256": "cc4bc21ab76b5361a5af6e4007089d5d6dfd6114764b4c34df5d57f2cbb6a5a2", "gold_path": "gold/olmo_multi_column-08c9eac4149a44cf8eed7cf1466ce8afa6b7_page_1_pg1-p1.json", "image": "images-2560/ocr-columns-2.png", "image_sha256": "bb527d4a08844edc48725382ab2bceda914012481a4490481981f1f2b0d99570", "width": 1700, "height": 2200, "original_size": [ 1700, 2200 ], "tests": [ { "id": "08c9eac4149a44cf8eed7cf1466ce8afa6b7_page_1.pdf_order_4a73cead", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "Thanks again for the friendships and I wish all of you a Great Christmas and all the best in the New Year.", "max_diffs": 1 }, "after": { "text": "Two of our discerning members, Jean Timmermeister and Valerie Henschel commented that the sky had a dim but noticeable dust spot on it.", "max_diffs": 1 } }, "settings": {} } ] }, { "id": "ocr-columns-3", "group": "columns", "upstream_page_id": "olmo_multi_column-03b953c18a4f7d2bbe390940dec839395cdd_page_37_pg1-p1", "document": "olmo_multi_column:03b953c18a4f7d2bbe390940dec839395cdd", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-03b953c18a4f7d2bbe390940dec839395cdd_page_37_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-03b953c18a4f7d2bbe390940dec839395cdd_page_37_pg1-p1.pdf", "pdf_sha256": "396a97a5d1616d2c44c22cd912d825c6f571911e5f4f0e229ee228eea9347a30", "gold_path": "gold/olmo_multi_column-03b953c18a4f7d2bbe390940dec839395cdd_page_37_pg1-p1.json", "image": "images-2560/ocr-columns-3.png", "image_sha256": "74a7617f78b4a017180d0ee40342322f937799fb39571d599fab4dd0a33c0374", "width": 1700, "height": 2200, "original_size": [ 1700, 2200 ], "tests": [ { "id": "03b953c18a4f7d2bbe390940dec839395cdd_page_37.pdf_order_8433868c", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "If an individual is issued a Final Notification of Threat Assessment, the FAA will deny an application for any airman certificate, rating or authorization.", "max_diffs": 2 }, "after": { "text": "The individual may respond in writing to this initial notification and provide any information the individual believes the TSA should consider.", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-columns-4", "group": "columns", "upstream_page_id": "olmo_multi_column-0514f6672af23035c53e13fa9f5d7e17e4a4_page_4_pg1-p1", "document": "olmo_multi_column:0514f6672af23035c53e13fa9f5d7e17e4a4", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-0514f6672af23035c53e13fa9f5d7e17e4a4_page_4_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-0514f6672af23035c53e13fa9f5d7e17e4a4_page_4_pg1-p1.pdf", "pdf_sha256": "4abd808a7208f61e15d040eb96d7cc335179287ae0a061eac1e5a710eaad584b", "gold_path": "gold/olmo_multi_column-0514f6672af23035c53e13fa9f5d7e17e4a4_page_4_pg1-p1.json", "image": "images-2560/ocr-columns-4.png", "image_sha256": "7f9cefe5c61d6d9ef6dc26f277b336f58995fc9021cc2bfc358482182e92f53b", "width": 1654, "height": 2205, "original_size": [ 1654, 2205 ], "tests": [ { "id": "0514f6672af23035c53e13fa9f5d7e17e4a4_page_4.pdf_order_628017cf", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "This cycle period may not be the same as the averaging period used in the", "max_diffs": 0 }, "after": { "text": "is discussed further in Section 7.", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-columns-5", "group": "columns", "upstream_page_id": "olmo_multi_column-027c390510b2fd3364f5a382f2bc304af018_page_1_pg1-p1", "document": "olmo_multi_column:027c390510b2fd3364f5a382f2bc304af018", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-027c390510b2fd3364f5a382f2bc304af018_page_1_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-027c390510b2fd3364f5a382f2bc304af018_page_1_pg1-p1.pdf", "pdf_sha256": "17a7691791e7f02a935591f5a328ba360aeec7330ce1456b228756e5c7117df1", "gold_path": "gold/olmo_multi_column-027c390510b2fd3364f5a382f2bc304af018_page_1_pg1-p1.json", "image": "images-2560/ocr-columns-5.png", "image_sha256": "e1193ad29500cfa2bf80e89ebbc7e9684bdc7563c6619fbdaefab5d00ecb08fd", "width": 1653, "height": 2245, "original_size": [ 1653, 2245 ], "tests": [ { "id": "027c390510b2fd3364f5a382f2bc304af018_page_1.pdf_order_f64b4474", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "heading" ], "args": { "before": { "text": "Impact of Hypertension on Type 2 Diabetes in Mysore Population of South India", "max_diffs": 1 }, "after": { "text": "However, when creatinine and blood urea nitrogen were included in the model, the significance was nullified.", "max_diffs": 1 } }, "settings": {} } ] }, { "id": "ocr-columns-6", "group": "columns", "upstream_page_id": "olmo_multi_column-01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49_pg1-p1", "document": "olmo_multi_column:01ed6dcc6a3d0237daa88b293d0c0667df1a", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49_pg1-p1.pdf", "pdf_sha256": "6604b2e093552a4c0b64920a86f5a8bda29494b196821ee92e89e5f4c27ffec9", "gold_path": "gold/olmo_multi_column-01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49_pg1-p1.json", "image": "images-2560/ocr-columns-6.png", "image_sha256": "a0095a37f73cdc320eedcc3857fea79aedbf8ad0ee9183243a2cdd76ccab0f64", "width": 1700, "height": 2200, "original_size": [ 1700, 2200 ], "tests": [ { "id": "01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49.pdf_order_e4a5ac92", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "heading", "list", "multi_column" ], "args": { "before": { "text": "No wash steps are required because cellular growth media do not significantly interfere with CyQUANT \u00ae GR fluorescence.", "max_diffs": 2 }, "after": { "text": "CyQUANT \u00ae Direct Cell Proliferation Assay Kit", "max_diffs": 2 } }, "settings": {} }, { "id": "01ed6dcc6a3d0237daa88b293d0c0667df1a_page_49.pdf_order_dd834802", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Grek", "Latn", "eng", "multi_column" ], "args": { "before": { "text": "The kit supplies sufficient materials for performing 1000 assays based on a 200 \u03bcL sample volume or a proportionately lower number of assays with a larger sample volume.", "max_diffs": 1 }, "after": { "text": "The no-wash, homogeneous format and fast add-mix-read protocol makes the CyQUANT \u00ae Direct assay ideal for high-throughput screening (HTS) applications.", "max_diffs": 1 } }, "settings": {} } ] }, { "id": "ocr-columns-7", "group": "columns", "upstream_page_id": "olmo_multi_column-04af23cb9eaaaf1b0462bafa176d0c0c315b_page_6_pg1-p1", "document": "olmo_multi_column:04af23cb9eaaaf1b0462bafa176d0c0c315b", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-04af23cb9eaaaf1b0462bafa176d0c0c315b_page_6_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-04af23cb9eaaaf1b0462bafa176d0c0c315b_page_6_pg1-p1.pdf", "pdf_sha256": "2586d01df073bdf0d3540e028c93cb04b4695c798b5b33b368ffbabd96a6faf7", "gold_path": "gold/olmo_multi_column-04af23cb9eaaaf1b0462bafa176d0c0c315b_page_6_pg1-p1.json", "image": "images-2560/ocr-columns-7.png", "image_sha256": "e481efb7487c7d87d1895972dd2c525bcd9c09d4b5a4f400c469d53b56dc84fb", "width": 1654, "height": 2339, "original_size": [ 1654, 2339 ], "tests": [ { "id": "04af23cb9eaaaf1b0462bafa176d0c0c315b_page_6.pdf_order_3d729704", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "list", "multi_column" ], "args": { "before": { "text": "We express our gratitude to the staff of Biochemistry Laboratory at Endocrine Research Center of Shahid Beheshti University for their skillful technical assistance.", "max_diffs": 2 }, "after": { "text": "Brass EP, Hoppel CL, Hiatt WR. 1994.", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-columns-8", "group": "columns", "upstream_page_id": "olmo_multi_column-027880a87e3c2ad4cf8c05f477597c0c6da7_page_6_pg1-p1", "document": "olmo_multi_column:027880a87e3c2ad4cf8c05f477597c0c6da7", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_multi_column-027880a87e3c2ad4cf8c05f477597c0c6da7_page_6_pg1-p1.pdf", "pdf": "pages/olmo_multi_column-027880a87e3c2ad4cf8c05f477597c0c6da7_page_6_pg1-p1.pdf", "pdf_sha256": "888df0be3704039ecb45a971699da63506f858f23341f88c797cd29f54aa8cda", "gold_path": "gold/olmo_multi_column-027880a87e3c2ad4cf8c05f477597c0c6da7_page_6_pg1-p1.json", "image": "images-2560/ocr-columns-8.png", "image_sha256": "315bcee06f738109488a3d96ae396b33a386e7f09fdaa8f9f6001d19e81dde05", "width": 1625, "height": 2175, "original_size": [ 1625, 2175 ], "tests": [ { "id": "027880a87e3c2ad4cf8c05f477597c0c6da7_page_6.pdf_order_292e204e", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "had reached the minimum at t = 10 h, the optical density increased linearly over time.", "max_diffs": 1 }, "after": { "text": "gen mass transfer characteristics, i.e., gassing rate/culture volume ratio and mixing intensity (number of impellers), steady p H\u2082 values were obtained during the linear growth phase that ranged between 1 and 59 kPa.", "max_diffs": 1 } }, "settings": {} } ] }, { "id": "ocr-small-print-1", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-14a_pg1-p1", "document": "olmo_long_tiny_text:14a", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-14a_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-14a_pg1-p1.pdf", "pdf_sha256": "3676826db35a850ada4730dee41d74898d0113797e087817971bad51a9ddda22", "gold_path": "gold/olmo_long_tiny_text-14a_pg1-p1.json", "image": "images-2560/ocr-small-print-1.png", "image_sha256": "7d879995ada4d9b1e5acd21223ae3ceab49711b4642c6aee98882f3b7a7b4b9f", "width": 1839, "height": 2560, "original_size": [ 3417, 4756 ], "tests": [ { "id": "14a_pg1_text_02", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "The Aftonian deposits consist of ancient soil profiles that may also include peat and windblown deposits.", "max_diffs": 3 } }, "settings": {} }, { "id": "14a_pg1_text_04", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "Afro-Shirazi, also known as SHIRAZI, African tribe in Tanzania.", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-small-print-2", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-12_pg174_pg1-p1", "document": "olmo_long_tiny_text:12", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-12_pg174_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-12_pg174_pg1-p1.pdf", "pdf_sha256": "a57f249a920efcc6f077d27dac9b9adf00f547c9d74e4b3f024f7e3c7c250d53", "gold_path": "gold/olmo_long_tiny_text-12_pg174_pg1-p1.json", "image": "images-2560/ocr-small-print-2.png", "image_sha256": "79eba62d5e9b60f21b8c48e731b67884b5a3e3aa2f70e682e07edb42fc1bdc76", "width": 1701, "height": 2174, "original_size": [ 1701, 2174 ], "tests": [ { "id": "12_pg174_pg1_text_00", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "list", "multi_column" ], "args": { "content": { "text": "Darwin, C., 1859. On the Origin of Species by Means of Natural Selection, or the Preservation of Favoured Races in the Struggle for Life.", "max_diffs": 3 } }, "settings": {} } ] }, { "id": "ocr-small-print-3", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-13_pg531_pg1-p1", "document": "olmo_long_tiny_text:13", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-13_pg531_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-13_pg531_pg1-p1.pdf", "pdf_sha256": "be1599e55b5542acebb707a164b2c5cb1d12f84449d8c5a2b94283c99b773888", "gold_path": "gold/olmo_long_tiny_text-13_pg531_pg1-p1.json", "image": "images-2560/ocr-small-print-3.png", "image_sha256": "b48ee7e59cd4db505027db3459f508a5c6b5e4408ebb94b9c745d660c59781d5", "width": 1158, "height": 1616, "original_size": [ 1158, 1616 ], "tests": [ { "id": "13_pg531_pg1_text_01", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "Dissatisfaction arose under Aragonese rule from the periodical grants of Malta, as a marquisate or countship, to great officers of state or illegitimate descendants of the sovereign.", "max_diffs": 2 } }, "settings": {} }, { "id": "13_pg531_pg1_text_02", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "The Maltese joined the Spaniards in a disastrous raid against Gerbi on the African coast in 1432.", "max_diffs": 1 } }, "settings": {} }, { "id": "13_pg531_pg1_text_04", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "In 1551 ravaged Gozo, after an unsuccessful attempt on Malta, repulsed by cavalry under Upton, an English knight.", "max_diffs": 1 } }, "settings": {} }, { "id": "13_pg531_pg1_text_08", "test_type": "present", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "They contain clear indication of the interment of martyrs.", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-small-print-4", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-13_pg475_pg1-p1", "document": "olmo_long_tiny_text:13", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-13_pg475_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-13_pg475_pg1-p1.pdf", "pdf_sha256": "d6b7915547f415233ac6aed7dced0338aaafbad64294dbca8d065df9f1da9e54", "gold_path": "gold/olmo_long_tiny_text-13_pg475_pg1-p1.json", "image": "images-2560/ocr-small-print-4.png", "image_sha256": "328f27723f876f73adf11fa16fa6ee01f1b7baad8eafd2eac6e7ddbcd31030b2", "width": 1158, "height": 1616, "original_size": [ 1158, 1616 ], "tests": [ { "id": "13_pg475_pg1_text_10", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "tears of the daughters of Israel, thrust aside to make way for", "max_diffs": 0 } }, "settings": {} }, { "id": "13_pg475_pg1_text_11", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "malachite is found in greater or less quantity in most", "max_diffs": 3 } }, "settings": {} }, { "id": "13_pg475_pg1_text_06", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "Elijah must reappear to bring back the hearts of fathers and", "max_diffs": 3 } }, "settings": {} } ] }, { "id": "ocr-small-print-5", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-13_pg32_pg1-p1", "document": "olmo_long_tiny_text:13", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-13_pg32_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-13_pg32_pg1-p1.pdf", "pdf_sha256": "c9dbf96ada7fce1b418bec0d620bc03942ae8d88f2798c6a2870e74197fb4b41", "gold_path": "gold/olmo_long_tiny_text-13_pg32_pg1-p1.json", "image": "images-2560/ocr-small-print-5.png", "image_sha256": "087ccf4ac825a62fb4a41d022728fe65fc7ac220beee7dff8e52794f679911d4", "width": 1136, "height": 1609, "original_size": [ 1136, 1609 ], "tests": [ { "id": "13_pg32_pg1_text_17", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "footnote", "multi_column", "tiny" ], "args": { "content": { "text": "French and Italian weekly papers are published in Los Angeles.", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-small-print-6", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-14b_pg1-p1", "document": "olmo_long_tiny_text:14b", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-14b_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-14b_pg1-p1.pdf", "pdf_sha256": "df9084d3c908cc9361a00d5e0dddffcd891f2a3f816ebe1137840cdf33e4c653", "gold_path": "gold/olmo_long_tiny_text-14b_pg1-p1.json", "image": "images-2560/ocr-small-print-6.png", "image_sha256": "9a3afa089b84a3315fee37edefb84e1fa63f25d30992d7631eaeb476a964571e", "width": 1839, "height": 2560, "original_size": [ 3417, 4756 ], "tests": [ { "id": "14b_pg1_text_02", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "Amboise, Jacques (Joseph) d': see d'Amboise, Jacques (Joseph).", "max_diffs": 1 } }, "settings": {} }, { "id": "14b_pg1_text_04", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "The hard and knotty Ambon wood, of great value for ornamental wood-work, is obtained from Ceram.", "max_diffs": 1 } }, "settings": {} }, { "id": "14b_pg1_text_06", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "The town has many houses and structures of stone and wide, often tree-lined, streets;", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-small-print-7", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-20_pg58_pg1-p1", "document": "olmo_long_tiny_text:20", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-20_pg58_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-20_pg58_pg1-p1.pdf", "pdf_sha256": "c4ca786f3992687a3046fe7f66f56367990793f4738b04fba26b0c3e518e955b", "gold_path": "gold/olmo_long_tiny_text-20_pg58_pg1-p1.json", "image": "images-2560/ocr-small-print-7.png", "image_sha256": "7f042b74cba869d2f6f16533b983f7695678e3f5807a6ff48ec526b676b85a03", "width": 1729, "height": 2289, "original_size": [ 1729, 2289 ], "tests": [ { "id": "20_pg58_pg1_text_05", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "It will be fantastic if Christian is going to be committed with the club for [the] long term, and if not it's his right to do what he wants to do.", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-small-print-8", "group": "small-print", "upstream_page_id": "olmo_long_tiny_text-15c_pg1-p1", "document": "olmo_long_tiny_text:15c", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_long_tiny_text-15c_pg1-p1.pdf", "pdf": "pages/olmo_long_tiny_text-15c_pg1-p1.pdf", "pdf_sha256": "526020435b982722b4b3e087518725d9b0457ab05f7f646a86d4ec9a2b5d97f1", "gold_path": "gold/olmo_long_tiny_text-15c_pg1-p1.json", "image": "images-2560/ocr-small-print-8.png", "image_sha256": "7219dcf4db6f0c44b7a4600c9bee6b243747f6789dddf8c549f54af3c42c7c75", "width": 1885, "height": 2560, "original_size": [ 3534, 4800 ], "tests": [ { "id": "15c_pg1_text_03", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "Specifically, search is made for potassium-bearing minerals associated with uraninite specimens that have shown concordant uranium-thorium-lead ages.", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-1", "group": "old-scans", "upstream_page_id": "olmo_old_scans-50-p1", "document": "olmo_old_scans:50", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-50-p1.pdf", "pdf": "pages/olmo_old_scans-50-p1.pdf", "pdf_sha256": "ce87ef2a6779fe7719e0259446f132c95198a314b4427e9c01855cdacce525c7", "gold_path": "gold/olmo_old_scans-50-p1.json", "image": "images-2560/ocr-old-scans-1.png", "image_sha256": "64a078f163adc40a08855406562dc48a8b92736ba08a666f4565ecb7b3f8b6f8", "width": 1597, "height": 2560, "original_size": [ 6925, 11098 ], "tests": [ { "id": "50_262572", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "The language of the 4th commandment is, \"The seventh day is the Sabbath of the Lord\" But the Christians keep the first day not the seventh \u2014 3.", "max_diffs": 1 } }, "settings": {} }, { "id": "50_92582", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "the essence of persecution \u2014 God has given man no authority", "max_diffs": 1 } }, "settings": {} }, { "id": "50_99814", "test_type": "present", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "& in this submission there will be no piety", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-2", "group": "old-scans", "upstream_page_id": "olmo_old_scans-55-p1", "document": "olmo_old_scans:55", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-55-p1.pdf", "pdf": "pages/olmo_old_scans-55-p1.pdf", "pdf_sha256": "248df5221f8b3f5ddaad0f3c8764ab2ed2db1468e2d0332b02e717490aa2a9dd", "gold_path": "gold/olmo_old_scans-55-p1.json", "image": "images-2560/ocr-old-scans-2.png", "image_sha256": "e2f9f2105261e4790ac825ae1868ca7ac96bb3af5eb77856768a6ac5d03a38e9", "width": 1615, "height": 2560, "original_size": [ 6769, 10732 ], "tests": [ { "id": "55_930782", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "of our thoughts in such a manner that their connexion & dependence may be clearly", "max_diffs": 0 } }, "settings": {} }, { "id": "55_150814", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "is the having things back to their source &", "max_diffs": 0 } }, "settings": {} }, { "id": "55_287312", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting", "list" ], "args": { "content": { "text": "What is method? A. the disposal & arrangement of our thoughts", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-3", "group": "old-scans", "upstream_page_id": "olmo_old_scans-54-p1", "document": "olmo_old_scans:54", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-54-p1.pdf", "pdf": "pages/olmo_old_scans-54-p1.pdf", "pdf_sha256": "3ccd35e720d5d32102acd350a66e8638a9f7f30f5be4303b237483125e4fd056", "gold_path": "gold/olmo_old_scans-54-p1.json", "image": "images-2560/ocr-old-scans-3.png", "image_sha256": "e89cbcaf21ae68ebd92b5da15cf3685b69cc8ae66d378254e83ea4829f61aca7", "width": 2560, "height": 1900, "original_size": [ 6836, 5073 ], "tests": [ { "id": "54_705613", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "exclaimed : oh Lord ! what a night -\u2014for catching coons!", "max_diffs": 1 } }, "settings": {} }, { "id": "54_118618", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "heard save the distant tinkling of the", "max_diffs": 0 } }, "settings": {} }, { "id": "54_994539", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "before": { "text": "stood beside a tomb - a deep sigh rent his bosom &", "max_diffs": 1 }, "after": { "text": "what a night -\u2014for catching coons!", "max_diffs": 1 } }, "settings": {} } ] }, { "id": "ocr-old-scans-4", "group": "old-scans", "upstream_page_id": "olmo_old_scans-12-p1", "document": "olmo_old_scans:12", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-12-p1.pdf", "pdf": "pages/olmo_old_scans-12-p1.pdf", "pdf_sha256": "f831e6449359ac6b220c2297a2075b5d5862b0a4473ab30ec591ff5e0d0da334", "gold_path": "gold/olmo_old_scans-12-p1.json", "image": "images-2560/ocr-old-scans-4.png", "image_sha256": "5cd04f4c7b346f593f817df0e3dbaba90ab071e6e12492ceeafb8d1b3f631146", "width": 1644, "height": 2560, "original_size": [ 3380, 5263 ], "tests": [ { "id": "12_898662", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting" ], "args": { "content": { "text": "I know you will forgive the liberty I am taking when I explain my motive.", "max_diffs": 0 } }, "settings": {} }, { "id": "12_287370", "test_type": "order", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "eng", "handwriting" ], "args": { "before": { "text": "connected with the sale of it, and have nothing to", "max_diffs": 0 }, "after": { "text": "locomotive engineer, who contracted the Chagres fever while", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-5", "group": "old-scans", "upstream_page_id": "olmo_old_scans-70-p1", "document": "olmo_old_scans:70", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-70-p1.pdf", "pdf": "pages/olmo_old_scans-70-p1.pdf", "pdf_sha256": "f851b133cc7f7b8aec5765bbbbc1c2ad875f3ce655f9f1855d40deb798f47b87", "gold_path": "gold/olmo_old_scans-70-p1.json", "image": "images-2560/ocr-old-scans-5.png", "image_sha256": "0b88fabac38eff5ab32435579383e58bb9c183ed55f0d8d854faf22405f7cdc2", "width": 2560, "height": 1635, "original_size": [ 11144, 7119 ], "tests": [ { "id": "70_365784", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "content": { "text": "an Infinite Creator than any other gift. Every infringement of the law of continence", "max_diffs": 0 } }, "settings": {} }, { "id": "70_849482", "test_type": "order", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "all false teachers, false prophets, that cry \"peace, peace, when there is no peace.\"", "max_diffs": 0 }, "after": { "text": "Occasionally circumstances require that shipwrecked persons should be outfitted with clothing.", "max_diffs": 0 } }, "settings": {} }, { "id": "70_913529", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "multi_column" ], "args": { "before": { "text": "hell can never prevail against it, for it will stand upon a rock.", "max_diffs": 0 }, "after": { "text": "imperative necessity arising from conflagration or other disaster, epidemics, famine or war,", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-6", "group": "old-scans", "upstream_page_id": "olmo_old_scans-83-p1", "document": "olmo_old_scans:83", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-83-p1.pdf", "pdf": "pages/olmo_old_scans-83-p1.pdf", "pdf_sha256": "5f07c3795250afb3d066ea39bc0e33049ef8ab8b4853fbce98138a3d97fee34b", "gold_path": "gold/olmo_old_scans-83-p1.json", "image": "images-2560/ocr-old-scans-6.png", "image_sha256": "d4a51053467968e9f41e4584f5d5a8e133701bf40cabeceb468b1198d2d5023c", "width": 2560, "height": 2128, "original_size": [ 5861, 4873 ], "tests": [ { "id": "83_622554", "test_type": "present", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "degraded", "eng", "handwriting", "multi_column" ], "args": { "content": { "text": "almost ruin. There were one hundred for one, persons here food hunters thus met. If", "max_diffs": 0 } }, "settings": {} }, { "id": "83_509948", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting", "multi_column" ], "args": { "content": { "text": "for however dimly & slowly I discern other points, this has", "max_diffs": 0 } }, "settings": {} }, { "id": "83_974047", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting", "multi_column" ], "args": { "before": { "text": "strengthened by eight months daily observation.", "max_diffs": 0 }, "after": { "text": "their absence will create with regard to our 23 25 & 27 regts I", "max_diffs": 0 } }, "settings": {} }, { "id": "83_904141", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting", "multi_column" ], "args": { "before": { "text": "depot in this city and I should have no fears", "max_diffs": 0 }, "after": { "text": "no activity on the part of friends at home can prevent the suffering which", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-old-scans-7", "group": "old-scans", "upstream_page_id": "olmo_old_scans-92-p1", "document": "olmo_old_scans:92", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-92-p1.pdf", "pdf": "pages/olmo_old_scans-92-p1.pdf", "pdf_sha256": "4db1570ae00efbcd7350efe6f9f1ae815fbc66280181c5857c238b20a3b5124f", "gold_path": "gold/olmo_old_scans-92-p1.json", "image": "images-2560/ocr-old-scans-7.png", "image_sha256": "868b5614ef784f49157fcab8bfe456ed512b8cd6a5e090b3e4d29be5af53a703", "width": 2560, "height": 2174, "original_size": [ 8617, 7317 ], "tests": [ { "id": "92_990110", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting" ], "args": { "content": { "text": "fears they may not be well treated\nThis Mission is transmitted to \nRosa, who will make inquiry", "max_diffs": 0 } }, "settings": {} }, { "id": "92_283432", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting", "multi_column" ], "args": { "before": { "text": "As a preface \nto a request that I desire to make\nat your hnds, allow me without charge", "max_diffs": 1 }, "after": { "text": "- Whn our first regt of troop enterss ths city came to the defen of Washington I commenced to look after ther wants - and", "max_diffs": 1 } }, "settings": {} }, { "id": "92_224181", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting" ], "args": { "content": { "text": "dance They must address their letter to Mrs. Nellie Churchill", "max_diffs": 1 } }, "settings": {} }, { "id": "92_712258", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "content": { "text": "Fairfax Station with a car load of", "max_diffs": 0 } }, "settings": {} }, { "id": "92_339445", "test_type": "order", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "degraded", "eng", "handwriting" ], "args": { "before": { "text": "Gen Pope At the Battle of Cedar Mountain I was", "max_diffs": 2 }, "after": { "text": "Bull Run I reached Fairfax Station with", "max_diffs": 2 } }, "settings": {} } ] }, { "id": "ocr-old-scans-8", "group": "old-scans", "upstream_page_id": "olmo_old_scans-30-p1", "document": "olmo_old_scans:30", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/olmo_old_scans-30-p1.pdf", "pdf": "pages/olmo_old_scans-30-p1.pdf", "pdf_sha256": "c9dcb7275a900778547cb02875b244d664113db7488ab4106ad0c905b7695e88", "gold_path": "gold/olmo_old_scans-30-p1.json", "image": "images-2560/ocr-old-scans-8.png", "image_sha256": "c31423a34cb7253c13e2de161e416a2ac146803920cf6e7336dc0b8e99044dcd", "width": 2560, "height": 2098, "original_size": [ 6511, 5336 ], "tests": [ { "id": "30_697277", "test_type": "present", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting", "multi_column" ], "args": { "content": { "text": "same steamer. Believe I pray you in my sincere", "max_diffs": 0 } }, "settings": {} }, { "id": "30_533481", "test_type": "present", "output_type": "html", "derivation": "model_review", "tags": [ "Latn", "eng", "handwriting", "multi_column" ], "args": { "content": { "text": "a letter in response to yours and get it into Lawrence's hands, for consultation between", "max_diffs": 0 } }, "settings": {} }, { "id": "30_968972", "test_type": "order", "output_type": "html", "derivation": "upstream_olmocr", "tags": [ "Latn", "eng", "handwriting", "multi_column" ], "args": { "before": { "text": "With this change I am quite sure that we can do more to", "max_diffs": 0 }, "after": { "text": "esteem for you and my faith in what you have", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-1", "group": "forms", "upstream_page_id": "forms_federal-scan_faa_337-p1", "document": "form:faa_337", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_faa_337-p1.png", "pdf": "pages/forms_federal-scan_faa_337-p1.png", "pdf_sha256": "e3d0f5aa223f60a14c87781c4051c9bf157e325b7be393d53792fe71b616dbe7", "gold_path": "gold/forms_federal-scan_faa_337-p1.json", "image": "images-2560/ocr-forms-1.png", "image_sha256": "ac4bad5ec6fbe1fd9e72a6186fe94b4214c6a26e655f9b411fcedad424d94863", "width": 1746, "height": 2236, "original_size": [ 1746, 2236 ], "tests": [ { "id": "ff2_faa_337_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "handwriting" ], "args": { "content": { "text": "United States", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-2", "group": "forms", "upstream_page_id": "forms_federal-scan_irs_4506t-p1", "document": "form:irs_4506t", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_irs_4506t-p1.png", "pdf": "pages/forms_federal-scan_irs_4506t-p1.png", "pdf_sha256": "de7cf6aa2d80a9d7d7f3e7f4bc55858abc005c5ccd71e18020f7511f45454c38", "gold_path": "gold/forms_federal-scan_irs_4506t-p1.json", "image": "images-2560/ocr-forms-2.png", "image_sha256": "6b435f35f99e08c3cbbd99b54c29d002f5e36aedc8cd918c58daa42c4810fa2b", "width": 1870, "height": 2370, "original_size": [ 1870, 2370 ], "tests": [ { "id": "ff2_irs_4506t_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "1814 Ryan Trafficway Apt. 193, Port Danielle, SD 83822", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_4506t_worn_value_1", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "8213 Eric Lodge Suite 513", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_4506t_worn_value_2", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "2863 Adams Expressway", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_4506t_worn_value_3", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "Darlene Clements", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-3", "group": "forms", "upstream_page_id": "forms_federal-scan_fda_3454-p1", "document": "form:fda_3454", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_fda_3454-p1.png", "pdf": "pages/forms_federal-scan_fda_3454-p1.png", "pdf_sha256": "e351f8d9212f7aa90a5264f4c81870feabc710bd21ca8c659df10157b34c93d4", "gold_path": "gold/forms_federal-scan_fda_3454-p1.json", "image": "images-2560/ocr-forms-3.png", "image_sha256": "abd5ac800cc4037e1dd2da111ee2419fba330400568f62cb4222c012d0bb25c9", "width": 1746, "height": 2236, "original_size": [ 1746, 2236 ], "tests": [ { "id": "ff2_fda_3454_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "table" ], "args": { "content": { "text": "Rebecca Roberts", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_fda_3454_worn_value_1", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "degraded", "eng", "form" ], "args": { "content": { "text": "Stephanie Glass", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_fda_3454_worn_value_2", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "table" ], "args": { "content": { "text": "Spencer Powell", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_fda_3454_worn_value_3", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "degraded", "eng", "form", "table" ], "args": { "content": { "text": "Randall Fuller", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-4", "group": "forms", "upstream_page_id": "forms_federal-scan_irs_9465-p1", "document": "form:irs_9465", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_irs_9465-p1.png", "pdf": "pages/forms_federal-scan_irs_9465-p1.png", "pdf_sha256": "d2db49a71f7337669d3dadacb78295babe9fa2cdabb3c71922481bd829560a04", "gold_path": "gold/forms_federal-scan_irs_9465-p1.json", "image": "images-2560/ocr-forms-4.png", "image_sha256": "1d0a53534a5fd35c84c0e7028b7f971fcf9df51071706411bc96a0d56120d294", "width": 1714, "height": 2212, "original_size": [ 1714, 2212 ], "tests": [ { "id": "ff2_irs_9465_worn_value_1", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "Lawrencemouth", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_9465_worn_value_2", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form" ], "args": { "content": { "text": "East Kenneth", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-5", "group": "forms", "upstream_page_id": "forms_federal-scan_irs_8821-p1", "document": "form:irs_8821", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_irs_8821-p1.png", "pdf": "pages/forms_federal-scan_irs_8821-p1.png", "pdf_sha256": "f5f4e27cdbdd251ebf8ee72082dbec7dec7d2ded8269a91da0362ceda48cdd7a", "gold_path": "gold/forms_federal-scan_irs_8821-p1.json", "image": "images-2560/ocr-forms-5.png", "image_sha256": "033434e4484f9981c1b4ae78d0f22e9da41f0c2f47173253c02e99de2b076ca9", "width": 1870, "height": 2370, "original_size": [ 1870, 2370 ], "tests": [ { "id": "ff2_irs_8821_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "handwriting" ], "args": { "content": { "text": "Michael Mathis", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_8821_worn_value_3", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "handwriting" ], "args": { "content": { "text": "0619 Hernandez Junctions Suite 801", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-6", "group": "forms", "upstream_page_id": "forms_federal-scan_faa_8710_1-p1", "document": "form:faa_8710_1", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_faa_8710_1-p1.png", "pdf": "pages/forms_federal-scan_faa_8710_1-p1.png", "pdf_sha256": "cdc7557541ed82f3ca0f38116f4938acc362425c56a5699543c5a6187439a967", "gold_path": "gold/forms_federal-scan_faa_8710_1-p1.json", "image": "images-2560/ocr-forms-6.png", "image_sha256": "e9adad9429de03939c1a11f8faeb1864d28a331d83689f59e6cb6da8338e4ba2", "width": 1752, "height": 2240, "original_size": [ 1752, 2240 ], "tests": [ { "id": "ff2_faa_8710_1_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "degraded", "eng", "form" ], "args": { "content": { "text": "Johnson-Johnson", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_faa_8710_1_worn_value_2", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "degraded", "eng", "form", "tiny" ], "args": { "content": { "text": "Canada", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_faa_8710_1_worn_value_3", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "degraded", "eng", "form" ], "args": { "content": { "text": "Terry", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-7", "group": "forms", "upstream_page_id": "forms_federal-scan_osha_300a-p1", "document": "form:osha_300a", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_osha_300a-p1.png", "pdf": "pages/forms_federal-scan_osha_300a-p1.png", "pdf_sha256": "04a344da2c147b2839207aa7ef0809704e2f8602d319014f1f3b17217689d645", "gold_path": "gold/forms_federal-scan_osha_300a-p1.json", "image": "images-2560/ocr-forms-7.png", "image_sha256": "1c0d30fd8a930381e26816b5126ce52d4bb38d16a8793c02803600e45c79d151", "width": 2560, "height": 1646, "original_size": [ 3080, 1980 ], "tests": [ { "id": "ff2_osha_300a_worn_value_1", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "multi_column" ], "args": { "content": { "text": "50811 Ramsey Flats Suite 781", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_osha_300a_worn_value_2", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "multi_column" ], "args": { "content": { "text": "Tucker, Castro and Horton", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_osha_300a_worn_value_3", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "multi_column" ], "args": { "content": { "text": "Hospital, acute care", "max_diffs": 0 } }, "settings": {} } ] }, { "id": "ocr-forms-8", "group": "forms", "upstream_page_id": "forms_federal-scan_irs_w7-p1", "document": "form:irs_w7", "source_url": "https://huggingface.co/datasets/datalab-to/omni_parse_bench/resolve/961c0f89a2da701f5ce53afbd5e80aa469b0369a/pages/forms_federal-scan_irs_w7-p1.png", "pdf": "pages/forms_federal-scan_irs_w7-p1.png", "pdf_sha256": "edcaa7ff5b24983fb17b2eae1f8c89400ebec0a76b3f39efe6337b462cd84ba5", "gold_path": "gold/forms_federal-scan_irs_w7-p1.json", "image": "images-2560/ocr-forms-8.png", "image_sha256": "3389297c7e3fed492b3170468910137e0112cfe926dd3d0c31c2b8acd1b44985", "width": 1870, "height": 2370, "original_size": [ 1870, 2370 ], "tests": [ { "id": "ff2_irs_w7_worn_value_0", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "handwriting" ], "args": { "content": { "text": "Joan Mendoza", "max_diffs": 0 } }, "settings": {} }, { "id": "ff2_irs_w7_worn_value_1", "test_type": "present", "output_type": "html", "derivation": "authored", "tags": [ "Latn", "eng", "form", "handwriting" ], "args": { "content": { "text": "Scott-Bishop", "max_diffs": 0 } }, "settings": {} } ] } ], "probes": [ "ocr-columns-1", "ocr-small-print-1", "ocr-old-scans-1", "ocr-forms-1", "ocr-columns-5", "ocr-old-scans-5" ], "render": { "dpi": 200, "max_long_side": 2560, "resize": "Pillow 12.0.0 Lanczos, never upscale", "source_images": "Original pixels before shared size cap", "mode": "RGB PNG", "pypdfium2": "5.14.0", "compression": 6 }, "sampling": "SHA256(edge-ocr-v1, page_id) order; first eight renderable pages per fixed category containing an English-tagged HTML text-family test; fixed independently of engine scores.", "excluded_before_inference": [], "scorer": { "package": "omni-parse-bench", "version": "1.0.0rc1", "types": [ "present", "order", "repeat" ], "input": "Identical HTML-escaped plain text in a pre element for all engines; no engine-specific normalization.", "overall": "Mean of the four category pass rates, each weighted equally. Not the full OmniParseBench score." }, "licenses": [ "ODC-BY 1.0: converted olmOCR-bench pages/tests; source document rights retained.", "US federal forms: public-domain documents; added tests CC-BY-4.0." ], "credits": [ "Allen Institute for AI: olmOCR-bench (Poznanski et al., 2025).", "Datalab: OmniParseBench conversion and added tests.", "Issuing US government agencies: forms." ], "limitations": [ "32 English pages; a screening test, not a comprehensive OCR ranking.", "Tests check selected passages and reading order, not every character, tables, formulas or layout labels.", "Public test data may overlap model training. The benchmark maintainer also makes Indra; most selected tests originate with Ai2." ], "suite_id": "decf6212023d7e74d44000bf02db43bc2a9d9a35b176b5dff57dff268c77f7fd" }