{"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/script-generation","name":"Script Generation","slug":"script-generation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":44,"papers_with_code":18,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":44,"of":44,"of_with_code":18,"tagged_in_all":44,"counts":{"archive_papers_tagged":44,"with_a_code_link":18,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":44,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/llmer-crafting-interactive-extended-reality","slug":"llmer-crafting-interactive-extended-reality","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","date":"2025-02-04","arxiv_id":"2502.02441","repositories_listed":1,"syntology":null},{"url":"/paper/blenderllm-training-large-language-models-for","slug":"blenderllm-training-large-language-models-for","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","date":"2024-12-16","arxiv_id":"2412.14203","repositories_listed":1,"syntology":null},{"url":"/paper/videogen-of-thought-a-collaborative-framework","slug":"videogen-of-thought-a-collaborative-framework","title":"VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation","date":"2024-12-03","arxiv_id":"2412.02259","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videogen-of-thought-a-collaborative-framework#ran","syntology_url":"https://syntology.ai/paper/2412.02259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02259"}},"official":{"repos":["DuNGEOnmassster/VideoGen-of-Thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/skyscript-100m-1000000000-pairs-of-scripts","slug":"skyscript-100m-1000000000-pairs-of-scripts","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","date":"2024-08-18","arxiv_id":"2408.09333","repositories_listed":1,"syntology":null},{"url":"/paper/logeval-a-comprehensive-benchmark-suite-for","slug":"logeval-a-comprehensive-benchmark-suite-for","title":"LogEval: A Comprehensive Benchmark Suite for Large Language Models In Log Analysis","date":"2024-07-02","arxiv_id":"2407.01896","repositories_listed":1,"syntology":null},{"url":"/paper/ibsen-director-actor-agent-collaboration-for","slug":"ibsen-director-actor-agent-collaboration-for","title":"IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation","date":"2024-07-01","arxiv_id":"2407.01093","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ibsen-director-actor-agent-collaboration-for#ran","syntology_url":"https://syntology.ai/paper/2407.01093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01093"}},"official":{"repos":["OpenDFM/ibsen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-is-all-you-need-finetuning-llms-for-chip","slug":"data-is-all-you-need-finetuning-llms-for-chip","title":"Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework","date":"2024-03-17","arxiv_id":"2403.11202","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":4,"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/data-is-all-you-need-finetuning-llms-for-chip#ran","syntology_url":"https://syntology.ai/paper/2403.11202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11202"}},"official":{"repos":["aichipdesign/chipgptft"],"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/llm4eda-emerging-progress-in-large-language","slug":"llm4eda-emerging-progress-in-large-language","title":"LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation","date":"2023-12-28","arxiv_id":"2401.12224","repositories_listed":1,"syntology":null},{"url":"/paper/unit-test-generation-using-generative-ai-a","slug":"unit-test-generation-using-generative-ai-a","title":"Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Tools","date":"2023-12-17","arxiv_id":"2312.10622","repositories_listed":1,"syntology":null},{"url":"/paper/ml-bench-large-language-models-leverage-open","slug":"ml-bench-large-language-models-leverage-open","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","date":"2023-11-16","arxiv_id":"2311.09835","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/ml-bench-large-language-models-leverage-open#ran","syntology_url":"https://syntology.ai/paper/2311.09835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09835"}},"official":{"repos":["gersteinlab/ml-bench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mm-vid-advancing-video-understanding-with-gpt","slug":"mm-vid-advancing-video-understanding-with-gpt","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","date":"2023-10-30","arxiv_id":"2310.19773","repositories_listed":1,"syntology":null},{"url":"/paper/multiscript-multimodal-script-learning-for","slug":"multiscript-multimodal-script-learning-for","title":"MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks","date":"2023-10-08","arxiv_id":"2310.04965","repositories_listed":1,"syntology":null},{"url":"/paper/chateda-a-large-language-model-powered","slug":"chateda-a-large-language-model-powered","title":"ChatEDA: A Large Language Model Powered Autonomous Agent for EDA","date":"2023-08-20","arxiv_id":"2308.10204","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/chateda-a-large-language-model-powered#ran","syntology_url":"https://syntology.ai/paper/2308.10204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10204"}},"official":{"repos":["wuhy68/chatedav1"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/take-a-break-in-the-middle-investigating","slug":"take-a-break-in-the-middle-investigating","title":"Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation","date":"2023-05-18","arxiv_id":"2305.10907","repositories_listed":1,"syntology":null},{"url":"/paper/improving-scripts-with-a-memory-of-natural","slug":"improving-scripts-with-a-memory-of-natural","title":"Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback","date":"2021-12-16","arxiv_id":"2112.09737","repositories_listed":1,"syntology":null},{"url":"/paper/scriptwriter-narrative-guided-script","slug":"scriptwriter-narrative-guided-script","title":"ScriptWriter: Narrative-Guided Script Generation","date":"2020-05-20","arxiv_id":"2005.10331","repositories_listed":1,"syntology":null},{"url":"/paper/lstm-vs-gru-vs-bidirectional-rnn-for-script","slug":"lstm-vs-gru-vs-bidirectional-rnn-for-script","title":"LSTM vs. GRU vs. Bidirectional RNN for script generation","date":"2019-08-12","arxiv_id":"1908.04332","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-quantized-representations-for","slug":"hierarchical-quantized-representations-for","title":"Hierarchical Quantized Representations for Script Generation","date":"2018-08-28","arxiv_id":"1808.09542","repositories_listed":1,"syntology":null},{"url":null,"slug":"automated-web-application-testing-end-to-end","title":"Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs","date":"2025-06-03","arxiv_id":"2506.02529","repositories_listed":0,"syntology":null},{"url":null,"slug":"jarvis-a-multi-agent-code-assistant-for-high","title":"JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation","date":"2025-05-20","arxiv_id":"2505.14978","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-framework-for-automated-1","title":"A Multi-Agent Framework for Automated Qinqiang Opera Script Generation Using Large Language Models","date":"2025-04-22","arxiv_id":"2504.15552","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-case-based-reasoning-system-for","title":"Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models","date":"2025-03-26","arxiv_id":"2503.20576","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-video-audio-synthesis-with-multi-agent","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","date":"2025-03-13","arxiv_id":"2503.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"narrative-driven-travel-planning","title":"Narrative-Driven Travel Planning: Geoculturally-Grounded Script Generation with Evolutionary Itinerary Optimization","date":"2025-02-20","arxiv_id":"2502.14456","repositories_listed":0,"syntology":null},{"url":null,"slug":"eicopilot-search-and-explore-enterprise","title":"EICopilot: Search and Explore Enterprise Information over Large-scale Knowledge Graphs with LLM-driven Agents","date":"2025-01-23","arxiv_id":"2501.13746","repositories_listed":0,"syntology":null},{"url":null,"slug":"nowyousee-me-context-aware-automatic-audio","title":"NowYouSee Me: Context-Aware Automatic Audio Description","date":"2024-12-13","arxiv_id":"2412.10002","repositories_listed":0,"syntology":null},{"url":null,"slug":"sims-simulating-human-scene-interactions-with","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","date":"2024-11-29","arxiv_id":"2411.19921","repositories_listed":0,"syntology":null},{"url":null,"slug":"aegis-an-agent-based-framework-for-general","title":"AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions","date":"2024-11-27","arxiv_id":"2411.18015","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-openai-o1-opportunities-and","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","date":"2024-09-27","arxiv_id":"2409.18486","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-prompt-enhancement-via-script","title":"Task-oriented Prompt Enhancement via Script Generation","date":"2024-09-24","arxiv_id":"2409.16418","repositories_listed":0,"syntology":null},{"url":null,"slug":"scriptsmith-a-unified-llm-framework-for","title":"ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement","date":"2024-09-12","arxiv_id":"2409.17166","repositories_listed":0,"syntology":null},{"url":null,"slug":"iicpilot-an-intelligent-integrated-circuit","title":"IICPilot: An Intelligent Integrated Circuit Backend Design Framework Using Open EDA","date":"2024-07-17","arxiv_id":"2407.12576","repositories_listed":0,"syntology":null},{"url":null,"slug":"too-late-to-train-too-early-to-use-a-study-on","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","date":"2024-06-29","arxiv_id":"2407.00416","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-large-vision-language-models","title":"DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks","date":"2024-06-06","arxiv_id":"2406.04470","repositories_listed":0,"syntology":null},{"url":"/paper/m-3-av-a-multimodal-multigenre-and","slug":"m-3-av-a-multimodal-multigenre-and","title":"M$^3$AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset","date":"2024-03-21","arxiv_id":"2403.14168","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-automatic-ai-agent-for-reaction","title":"Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis","date":"2023-11-16","arxiv_id":"2311.10776","repositories_listed":0,"syntology":null},{"url":null,"slug":"chipnemo-domain-adapted-llms-for-chip-design","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","date":"2023-10-31","arxiv_id":"2311.00176","repositories_listed":0,"syntology":null},{"url":null,"slug":"kurosawa-a-script-writer-s-assistant","title":"\"Kurosawa\": A Script Writer's Assistant","date":"2023-08-06","arxiv_id":"2308.03122","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-2-based-human-in-the-loop-theatre-play","title":"GPT-2-based Human-in-the-loop Theatre Play Script Generation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vscript-controllable-script-generation-with","title":"VScript: Controllable Script Generation with Visual Presentation","date":"2022-03-01","arxiv_id":"2203.00314","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-repair-repairing-model-output","title":"Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"proscript-partially-ordered-scripts-1","title":"proScript: Partially Ordered Scripts Generation","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"examgan-and-twin-examgan-for-exam-script","title":"ExamGAN and Twin-ExamGAN for Exam Script Generation","date":"2021-08-22","arxiv_id":"2108.09656","repositories_listed":0,"syntology":null},{"url":null,"slug":"proscript-partially-ordered-scripts","title":"proScript: Partially Ordered Scripts Generation via Pre-trained Language Models","date":"2021-04-16","arxiv_id":"2104.08251","repositories_listed":0,"syntology":null}],"syntology_records":5,"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/script-generation/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/script-generation/papers/ran/1","json":"/task/script-generation/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":"35760ebeb019f7e9606321f761edef5f3b8194ea2469a56a06e860546c324302","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}