{"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/image-comprehension","name":"Image Comprehension","slug":"image-comprehension","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":49,"papers_with_code":25,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/visual7w","name":"Visual7W","full_name":"","num_papers_in_archive":112}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":49,"of":49,"of_with_code":25,"tagged_in_all":49,"counts":{"archive_papers_tagged":49,"with_a_code_link":25,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":49,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"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"},"items":[{"url":"/paper/internlm-xcomposer-a-vision-language-large","slug":"internlm-xcomposer-a-vision-language-large","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","date":"2023-09-26","arxiv_id":"2309.15112","repositories_listed":3,"syntology":null},{"url":"/paper/enhancing-visual-language-modality-alignment","slug":"enhancing-visual-language-modality-alignment","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","date":"2024-05-24","arxiv_id":"2405.15973","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-visual-language-modality-alignment#ran","syntology_url":"https://syntology.ai/paper/2405.15973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15973"}},"official":{"repos":["umd-huang-lab/sima"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mini-gemini-mining-the-potential-of-multi#ran","syntology_url":"https://syntology.ai/paper/2403.18814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18814"}},"official":{"repos":["dvlab-research/minigemini"],"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/new-dataset-and-methods-for-fine-grained","slug":"new-dataset-and-methods-for-fine-grained","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","date":"2025-02-27","arxiv_id":"2502.20104","repositories_listed":1,"syntology":null},{"url":"/paper/rrhf-v-ranking-responses-to-mitigate","slug":"rrhf-v-ranking-responses-to-mitigate","title":"RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rsunivlm-a-unified-vision-language-model-for","slug":"rsunivlm-a-unified-vision-language-model-for","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05679","repositories_listed":1,"syntology":null},{"url":"/paper/divot-diffusion-powers-video-tokenizer-for","slug":"divot-diffusion-powers-video-tokenizer-for","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","date":"2024-12-05","arxiv_id":"2412.04432","repositories_listed":1,"syntology":null},{"url":"/paper/mmgenbench-evaluating-the-limits-of-lmms-from","slug":"mmgenbench-evaluating-the-limits-of-lmms-from","title":"MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective","date":"2024-11-21","arxiv_id":"2411.14062","repositories_listed":1,"syntology":null},{"url":"/paper/clic-contrastive-learning-framework-for","slug":"clic-contrastive-learning-framework-for","title":"CLIC: Contrastive Learning Framework for Unsupervised Image Complexity Representation","date":"2024-11-19","arxiv_id":"2411.12792","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-multimodal-query-representation-via","slug":"enhancing-multimodal-query-representation-via","title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","date":"2024-11-13","arxiv_id":"2411.08334","repositories_listed":1,"syntology":null},{"url":"/paper/streamingbench-assessing-the-gap-for-mllms-to","slug":"streamingbench-assessing-the-gap-for-mllms-to","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","date":"2024-11-06","arxiv_id":"2411.03628","repositories_listed":1,"syntology":null},{"url":"/paper/ftii-bench-a-comprehensive-multimodal","slug":"ftii-bench-a-comprehensive-multimodal","title":"FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion","date":"2024-10-16","arxiv_id":"2410.12564","repositories_listed":1,"syntology":null},{"url":"/paper/finecops-ref-a-new-dataset-and-task-for-fine","slug":"finecops-ref-a-new-dataset-and-task-for-fine","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","date":"2024-09-23","arxiv_id":"2409.14750","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finecops-ref-a-new-dataset-and-task-for-fine#ran","syntology_url":"https://syntology.ai/paper/2409.14750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14750"}},"official":{"repos":["liujunzhuo/FineCops-Ref"],"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","unlocated"]}}},{"url":"/paper/2408-02718","slug":"2408-02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","date":"2024-08-05","arxiv_id":"2408.02718","repositories_listed":1,"syntology":null},{"url":"/paper/paying-more-attention-to-image-a-training","slug":"paying-more-attention-to-image-a-training","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","date":"2024-07-31","arxiv_id":"2407.21771","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/paying-more-attention-to-image-a-training#ran","syntology_url":"https://syntology.ai/paper/2407.21771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21771"}},"official":null}},{"url":"/paper/internlm-xcomposer-2-5-a-versatile-large","slug":"internlm-xcomposer-2-5-a-versatile-large","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","date":"2024-07-03","arxiv_id":"2407.03320","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/internlm-xcomposer-2-5-a-versatile-large#ran","syntology_url":"https://syntology.ai/paper/2407.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03320"}},"official":{"repos":["internlm/internlm-xcomposer"],"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":["unlocated"]}}},{"url":"/paper/vga-vision-gui-assistant-minimizing","slug":"vga-vision-gui-assistant-minimizing","title":"VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning","date":"2024-06-20","arxiv_id":"2406.14056","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-large-vision-language-models-with","slug":"enhancing-large-vision-language-models-with","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","date":"2024-05-30","arxiv_id":"2405.19716","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/enhancing-large-vision-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2405.19716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19716"}},"official":{"repos":["yihedeng9/stic"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/advancing-geometric-problem-solving-a","slug":"advancing-geometric-problem-solving-a","title":"MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification","date":"2024-04-07","arxiv_id":"2404.05091","repositories_listed":1,"syntology":null},{"url":"/paper/earthgpt-a-universal-multi-modal-large","slug":"earthgpt-a-universal-multi-modal-large","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","date":"2024-01-30","arxiv_id":"2401.16822","repositories_listed":1,"syntology":null},{"url":"/paper/cocot-contrastive-chain-of-thought-prompting","slug":"cocot-contrastive-chain-of-thought-prompting","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","date":"2024-01-05","arxiv_id":"2401.02582","repositories_listed":1,"syntology":null},{"url":"/paper/regionblip-a-unified-multi-modal-pre-training","slug":"regionblip-a-unified-multi-modal-pre-training","title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","date":"2023-08-03","arxiv_id":"2308.02299","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/regionblip-a-unified-multi-modal-pre-training#ran","syntology_url":"https://syntology.ai/paper/2308.02299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02299"}},"official":{"repos":["mightyzau/regionblip"],"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/hierarchical-open-vocabulary-universal-image-1","slug":"hierarchical-open-vocabulary-universal-image-1","title":"Hierarchical Open-vocabulary Universal Image Segmentation","date":"2023-07-03","arxiv_id":"2307.00764","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchical-open-vocabulary-universal-image-1#ran","syntology_url":"https://syntology.ai/paper/2307.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00764"}},"official":{"repos":["berkeley-hipie/hipie"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/journeydb-a-benchmark-for-generative-image","slug":"journeydb-a-benchmark-for-generative-image","title":"JourneyDB: A Benchmark for Generative Image Understanding","date":"2023-07-03","arxiv_id":"2307.00716","repositories_listed":1,"syntology":null},{"url":"/paper/artgpt-4-artistic-vision-language","slug":"artgpt-4-artistic-vision-language","title":"ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter","date":"2023-05-12","arxiv_id":"2305.07490","repositories_listed":1,"syntology":null},{"url":null,"slug":"csvqa-a-chinese-multimodal-benchmark-for","title":"CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs","date":"2025-05-30","arxiv_id":"2505.24120","repositories_listed":0,"syntology":null},{"url":null,"slug":"rgb-th-bench-a-dense-benchmark-for-visual","title":"RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models","date":"2025-03-25","arxiv_id":"2503.19654","repositories_listed":0,"syntology":null},{"url":null,"slug":"rad-retrieval-augmented-decision-making-of","title":"RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving","date":"2025-03-18","arxiv_id":"2503.13861","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmmcot-enhancing-complex-multi-image","title":"CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation","date":"2025-03-07","arxiv_id":"2503.05255","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplevqa-multimodal-factuality-evaluation","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","date":"2025-02-18","arxiv_id":"2502.13059","repositories_listed":0,"syntology":null},{"url":null,"slug":"migician-revealing-the-magic-of-free-form","title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models","date":"2025-01-10","arxiv_id":"2501.05767","repositories_listed":0,"syntology":null},{"url":null,"slug":"easyref-omni-generalized-group-image","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM","date":"2024-12-12","arxiv_id":"2412.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-different-large-language-model","title":"Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges","date":"2024-12-04","arxiv_id":"2412.03220","repositories_listed":0,"syntology":null},{"url":null,"slug":"aquila-a-hierarchically-aligned-visual","title":"Aquila: A Hierarchically Aligned Visual-Language Model for Enhanced Remote Sensing Image Comprehension","date":"2024-11-09","arxiv_id":"2411.06074","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-multimodal-llms-to-comprehend","title":"Teach Multimodal LLMs to Comprehend Electrocardiographic Images","date":"2024-10-21","arxiv_id":"2410.19008","repositories_listed":0,"syntology":null},{"url":null,"slug":"fullanno-a-data-engine-for-enhancing-image","title":"FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs","date":"2024-09-20","arxiv_id":"2409.13540","repositories_listed":0,"syntology":null},{"url":null,"slug":"iw-bench-evaluating-large-multimodal-models","title":"IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web","date":"2024-09-14","arxiv_id":"2409.18980","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00555","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","date":"2024-08-01","arxiv_id":"2408.00555","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-glitches-a-deep-dive-into-image","title":"Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP","date":"2024-06-30","arxiv_id":"2407.00592","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiplane-prior-guided-few-shot-aerial-scene","title":"Multiplane Prior Guided Few-Shot Aerial Scene Rendering","date":"2024-06-07","arxiv_id":"2406.04961","repositories_listed":0,"syntology":null},{"url":null,"slug":"rec-gpt4v-multimodal-recommendation-with","title":"Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models","date":"2024-02-13","arxiv_id":"2402.08670","repositories_listed":0,"syntology":null},{"url":null,"slug":"muffin-or-chihuahua-challenging-large-vision","title":"Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA","date":"2024-01-29","arxiv_id":"2401.15847","repositories_listed":0,"syntology":null},{"url":null,"slug":"slideavsr-a-dataset-of-paper-explanation","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","date":"2024-01-18","arxiv_id":"2401.09759","repositories_listed":0,"syntology":null},{"url":null,"slug":"hidden-flaws-behind-expert-level-accuracy-of","title":"Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine","date":"2024-01-16","arxiv_id":"2401.08396","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-large-multimodal-model-is-watching","title":"GeoLocator: a location-integrated large multimodal model for inferring geo-privacy","date":"2023-11-21","arxiv_id":"2311.13018","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-large-language-models-bring-to-text-rich","title":"What Large Language Models Bring to Text-rich VQA?","date":"2023-11-13","arxiv_id":"2311.07306","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-performance-of-multimodal-language","title":"On the Performance of Multimodal Language Models","date":"2023-10-04","arxiv_id":"2310.03211","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-practical-and-efficient-image-to","title":"Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokens","date":"2023-09-15","arxiv_id":"2309.08531","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-ocr-text-re-organization","title":"An End-to-End OCR Text Re-organization Sequence Learning for Rich-text Detail Image Comprehension","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/image-comprehension/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/image-comprehension/papers/ran/1","json":"/task/image-comprehension/papers/ran/1.json","rows":8}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"36e3aea677626c8f1744bfa18d6fc71b68b87ff5f39307b745b719bf00682f55","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}