{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/document-understanding/papers/ran/1","list_of":"/task/document-understanding","task":"document understanding","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,39],"of":39,"counts":{"archive_papers_tagged":309,"with_a_code_link":140,"where_syntology_ran_a_sample":39,"not_listed_spam_title":0,"listed":309,"listed_where_code_ran":39,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/document-understanding/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/glm-4-1v-thinking-towards-versatile","slug":"glm-4-1v-thinking-towards-versatile","title":"GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","date":"2025-07-01","arxiv_id":"2507.01006","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glm-4-1v-thinking-towards-versatile#ran","syntology_url":"https://syntology.ai/paper/2507.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.01006"}},"official":{"repos":["thudm/glm-4.1v-thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/simpledoc-multi-modal-document-understanding","slug":"simpledoc-multi-modal-document-understanding","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","date":"2025-06-16","arxiv_id":"2506.14035","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpledoc-multi-modal-document-understanding#ran","syntology_url":"https://syntology.ai/paper/2506.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14035"}},"official":{"repos":["ag2ai/simpledoc"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mdocagent-a-multi-modal-multi-agent-framework","slug":"mdocagent-a-multi-modal-multi-agent-framework","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","date":"2025-03-18","arxiv_id":"2503.13964","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mdocagent-a-multi-modal-multi-agent-framework#ran","syntology_url":"https://syntology.ai/paper/2503.13964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13964"}},"official":{"repos":["aiming-lab/mdocagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/marten-visual-question-answering-with-mask","slug":"marten-visual-question-answering-with-mask","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","date":"2025-03-18","arxiv_id":"2503.14140","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/marten-visual-question-answering-with-mask#ran","syntology_url":"https://syntology.ai/paper/2503.14140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14140"}},"official":null}},{"url":"/paper/a-token-level-text-image-foundation-model-for","slug":"a-token-level-text-image-foundation-model-for","title":"A Token-level Text Image Foundation Model for Document Understanding","date":"2025-03-04","arxiv_id":"2503.02304","repositories_listed":0,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-token-level-text-image-foundation-model-for#ran","syntology_url":"https://syntology.ai/paper/2503.02304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02304"}},"official":null}},{"url":"/paper/qwen2-5-vl-technical-report","slug":"qwen2-5-vl-technical-report","title":"Qwen2.5-VL Technical Report","date":"2025-02-19","arxiv_id":"2502.13923","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/qwen2-5-vl-technical-report#ran","syntology_url":"https://syntology.ai/paper/2502.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13923"}},"official":null}},{"url":"/paper/docmia-document-level-membership-inference","slug":"docmia-document-level-membership-inference","title":"DocMIA: Document-Level Membership Inference Attacks against DocVQA Models","date":"2025-02-06","arxiv_id":"2502.03692","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/docmia-document-level-membership-inference#ran","syntology_url":"https://syntology.ai/paper/2502.03692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03692"}},"official":{"repos":["khanhnguyen21006/mia_docvqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/longdocurl-a-comprehensive-multimodal-long","slug":"longdocurl-a-comprehensive-multimodal-long","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","date":"2024-12-24","arxiv_id":"2412.18424","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longdocurl-a-comprehensive-multimodal-long#ran","syntology_url":"https://syntology.ai/paper/2412.18424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18424"}},"official":{"repos":["dengc2023/longdocurl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-times-mapreduce-simplified-long-sequence","slug":"llm-times-mapreduce-simplified-long-sequence","title":"LLM$\\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models","date":"2024-10-12","arxiv_id":"2410.09342","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-times-mapreduce-simplified-long-sequence#ran","syntology_url":"https://syntology.ai/paper/2410.09342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09342"}},"official":{"repos":["thunlp/llmxmapreduce"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/oryx-mllm-on-demand-spatial-temporal","slug":"oryx-mllm-on-demand-spatial-temporal","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","date":"2024-09-19","arxiv_id":"2409.12961","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/oryx-mllm-on-demand-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2409.12961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12961"}},"official":{"repos":["oryx-mllm/oryx"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/doclayllm-an-efficient-and-effective-multi","slug":"doclayllm-an-efficient-and-effective-multi","title":"DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding","date":"2024-08-27","arxiv_id":"2408.15045","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/doclayllm-an-efficient-and-effective-multi#ran","syntology_url":"https://syntology.ai/paper/2408.15045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15045"}},"official":{"repos":["whlscut/DocLayLLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02034","slug":"2408-02034","title":"Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid","date":"2024-08-04","arxiv_id":"2408.02034","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-02034#ran","syntology_url":"https://syntology.ai/paper/2408.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02034"}},"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hypergraph-based-understanding-for-document","slug":"hypergraph-based-understanding-for-document","title":"Hypergraph based Understanding for Document Semantic Entity Recognition","date":"2024-07-09","arxiv_id":"2407.06904","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hypergraph-based-understanding-for-document#ran","syntology_url":"https://syntology.ai/paper/2407.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06904"}},"official":{"repos":["Line-Kite/HGALayoutLM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmlongbench-doc-benchmarking-long-context","slug":"mmlongbench-doc-benchmarking-long-context","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","date":"2024-07-01","arxiv_id":"2407.01523","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mmlongbench-doc-benchmarking-long-context#ran","syntology_url":"https://syntology.ai/paper/2407.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01523"}},"official":null}},{"url":"/paper/colpali-efficient-document-retrieval-with","slug":"colpali-efficient-document-retrieval-with","title":"ColPali: Efficient Document Retrieval with Vision Language Models","date":"2024-06-27","arxiv_id":"2407.01449","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colpali-efficient-document-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2407.01449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01449"}},"official":null}},{"url":"/paper/leveraging-visual-tokens-for-extended-text","slug":"leveraging-visual-tokens-for-extended-text","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","date":"2024-06-04","arxiv_id":"2406.02547","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":14,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/leveraging-visual-tokens-for-extended-text#ran","syntology_url":"https://syntology.ai/paper/2406.02547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02547"}},"official":{"repos":["showlab/VisInContext"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/focus-anywhere-for-fine-grained-multi-page","slug":"focus-anywhere-for-fine-grained-multi-page","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","date":"2024-05-23","arxiv_id":"2405.14295","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/focus-anywhere-for-fine-grained-multi-page#ran","syntology_url":"https://syntology.ai/paper/2405.14295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14295"}},"official":null}},{"url":"/paper/layoutllm-layout-instruction-tuning-with","slug":"layoutllm-layout-instruction-tuning-with","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","date":"2024-04-08","arxiv_id":"2404.05225","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layoutllm-layout-instruction-tuning-with#ran","syntology_url":"https://syntology.ai/paper/2404.05225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05225"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/omniparser-a-unified-framework-for-text","slug":"omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omniparser-a-unified-framework-for-text#ran","syntology_url":"https://syntology.ai/paper/2403.19128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19128"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mplug-docowl-1-5-unified-structure-learning","slug":"mplug-docowl-1-5-unified-structure-learning","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","date":"2024-03-19","arxiv_id":"2403.12895","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mplug-docowl-1-5-unified-structure-learning#ran","syntology_url":"https://syntology.ai/paper/2403.12895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12895"}},"official":{"repos":["x-plug/mplug-docowl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/textmonkey-an-ocr-free-large-multimodal-model","slug":"textmonkey-an-ocr-free-large-multimodal-model","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","date":"2024-03-07","arxiv_id":"2403.04473","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textmonkey-an-ocr-free-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2403.04473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04473"}},"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-affinity-rationality-and-diversity-of","slug":"on-the-affinity-rationality-and-diversity-of","title":"On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling","date":"2024-01-25","arxiv_id":"2401.14113","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":5,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-affinity-rationality-and-diversity-of#ran","syntology_url":"https://syntology.ai/paper/2401.14113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14113"}},"official":{"repos":["bobxwu/traco"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/inters-unlocking-the-power-of-large-language","slug":"inters-unlocking-the-power-of-large-language","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","date":"2024-01-12","arxiv_id":"2401.06532","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inters-unlocking-the-power-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2401.06532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06532"}},"official":{"repos":["daod/inters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wordscape-a-pipeline-to-extract-multilingual-1","slug":"wordscape-a-pipeline-to-extract-multilingual-1","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","date":"2023-12-15","arxiv_id":"2312.10188","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wordscape-a-pipeline-to-extract-multilingual-1#ran","syntology_url":"https://syntology.ai/paper/2312.10188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10188"}},"official":{"repos":["DS3Lab/WordScape"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-improving-document-understanding-an","slug":"towards-improving-document-understanding-an","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","date":"2023-11-22","arxiv_id":"2311.13194","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-improving-document-understanding-an#ran","syntology_url":"https://syntology.ai/paper/2311.13194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13194"}},"official":{"repos":["harrytea/tgdoc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scob-universal-text-understanding-via","slug":"scob-universal-text-understanding-via","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","date":"2023-09-21","arxiv_id":"2309.12382","repositories_listed":0,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scob-universal-text-understanding-via#ran","syntology_url":"https://syntology.ai/paper/2309.12382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12382"}},"official":null}},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/document-understanding-dataset-and-evaluation#ran","syntology_url":"https://syntology.ai/paper/2305.08455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08455"}},"official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-vision-text-and-layout-for-universal","slug":"unifying-vision-text-and-layout-for-universal","title":"Unifying Vision, Text, and Layout for Universal Document Processing","date":"2022-12-05","arxiv_id":"2212.02623","repositories_listed":5,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":12,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unifying-vision-text-and-layout-for-universal#ran","syntology_url":"https://syntology.ai/paper/2212.02623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02623"}},"official":{"repos":["microsoft/i-code","microsoft/udop"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/kalm-knowledge-aware-integration-of-local","slug":"kalm-knowledge-aware-integration-of-local","title":"KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding","date":"2022-10-08","arxiv_id":"2210.04105","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kalm-knowledge-aware-integration-of-local#ran","syntology_url":"https://syntology.ai/paper/2210.04105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04105"}},"official":{"repos":["bunsenfeng/kalm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-document-recognition-and","slug":"end-to-end-document-recognition-and","title":"End-to-end Document Recognition and Understanding with Dessurt","date":"2022-03-30","arxiv_id":"2203.16618","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-document-recognition-and#ran","syntology_url":"https://syntology.ai/paper/2203.16618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16618"}},"official":{"repos":["herobd/dessurt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}},"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}},"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/docformer-end-to-end-transformer-for-document","slug":"docformer-end-to-end-transformer-for-document","title":"DocFormer: End-to-End Transformer for Document Understanding","date":"2021-06-22","arxiv_id":"2106.11539","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/docformer-end-to-end-transformer-for-document#ran","syntology_url":"https://syntology.ai/paper/2106.11539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11539"}},"official":null}},{"url":"/paper/icdar-2021-competition-on-scientific","slug":"icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","date":"2021-06-08","arxiv_id":"2106.14616","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/icdar-2021-competition-on-scientific#ran","syntology_url":"https://syntology.ai/paper/2106.14616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14616"}},"official":{"repos":["ibm-aur-nlp/PubLayNet","ibm-aur-nlp/PubTabNet","wenwenyu/MASTER-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-discrete-variational-recurrent-topic-model","slug":"a-discrete-variational-recurrent-topic-model","title":"A Discrete Variational Recurrent Topic Model without the Reparametrization Trick","date":"2020-10-22","arxiv_id":"2010.12055","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-discrete-variational-recurrent-topic-model#ran","syntology_url":"https://syntology.ai/paper/2010.12055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12055"}},"official":{"repos":["mmrezaee/VRTM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"8a832e4f3c4f62944059695213cf82851eb00e0286100704a1b02e035f7c1200","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}