{"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/llm-real-life-tasks","name":"LLM real-life tasks","slug":"llm-real-life-tasks","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":9,"papers_with_code":9,"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/high-quality-invoice-images-for-ocr","name":"High-Quality Invoice Images for OCR","full_name":"","num_papers_in_archive":3}],"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":9,"of":9,"of_with_code":9,"tagged_in_all":9,"counts":{"archive_papers_tagged":9,"with_a_code_link":9,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/maistro-an-open-source-multi-agentic-system","slug":"maistro-an-open-source-multi-agentic-system","title":"mAIstro: an open-source multi-agentic system for automated end-to-end development of radiomics and deep learning models for medical imaging","date":"2025-04-30","arxiv_id":"2505.03785","repositories_listed":1,"syntology":null},{"url":"/paper/affordable-ai-assistants-with-knowledge-graph","slug":"affordable-ai-assistants-with-knowledge-graph","title":"Affordable AI Assistants with Knowledge Graph of Thoughts","date":"2025-04-03","arxiv_id":"2504.02670","repositories_listed":1,"syntology":null},{"url":"/paper/mygo-multiplex-cot-a-method-for-self","slug":"mygo-multiplex-cot-a-method-for-self","title":"MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking","date":"2025-01-20","arxiv_id":"2501.13117","repositories_listed":1,"syntology":null},{"url":"/paper/using-instruction-tuned-large-language-models","slug":"using-instruction-tuned-large-language-models","title":"Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives","date":"2024-12-16","arxiv_id":"2412.11878","repositories_listed":1,"syntology":null},{"url":"/paper/webcanvas-benchmarking-web-agents-in-online","slug":"webcanvas-benchmarking-web-agents-in-online","title":"WebCanvas: Benchmarking Web Agents in Online Environments","date":"2024-06-18","arxiv_id":"2406.12373","repositories_listed":1,"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/webcanvas-benchmarking-web-agents-in-online#ran","syntology_url":"https://syntology.ai/paper/2406.12373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12373"}},"official":{"repos":["imeanai/webcanvas"],"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/autodefense-multi-agent-llm-defense-against","slug":"autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","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/autodefense-multi-agent-llm-defense-against#ran","syntology_url":"https://syntology.ai/paper/2403.04783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04783"}},"official":{"repos":["xhmy/autodefense"],"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/synergizing-spatial-optimization-with-large","slug":"synergizing-spatial-optimization-with-large","title":"ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning","date":"2024-02-11","arxiv_id":"2402.07204","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/synergizing-spatial-optimization-with-large#ran","syntology_url":"https://syntology.ai/paper/2402.07204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07204"}},"official":{"repos":["YihongT/ITINERA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cloudeval-yaml-a-practical-benchmark-for","slug":"cloudeval-yaml-a-practical-benchmark-for","title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","date":"2023-11-10","arxiv_id":"2401.06786","repositories_listed":1,"syntology":null},{"url":"/paper/llava-plus-learning-to-use-tools-for-creating","slug":"llava-plus-learning-to-use-tools-for-creating","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","date":"2023-11-09","arxiv_id":"2311.05437","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":1,"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/llava-plus-learning-to-use-tools-for-creating#ran","syntology_url":"https://syntology.ai/paper/2311.05437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05437"}},"official":{"repos":["LLaVA-VL/LLaVA-Plus-Codebase"],"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","unlocated"]}}}],"syntology_records":4,"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":4,"papers_where_code_ran_first_page":"/task/llm-real-life-tasks/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/llm-real-life-tasks/papers/ran/1","json":"/task/llm-real-life-tasks/papers/ran/1.json","rows":4}],"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":"e104a945b9f37251e1547b29af71ac44352208f2f349670c9771f46860856931","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}