{"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/user-simulation","name":"User Simulation","slug":"user-simulation","description_markdown":"Simulation of user interacting with a dialog system","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":"archive_url"},"counts":{"papers_tagged":64,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/lmsys-usp","name":"LMSYS-USP","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vmd","name":"VMD","full_name":"Virtual Moderation Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/goal-oriented-dialog","name":"Goal-Oriented Dialog"}],"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":64,"of":64,"of_with_code":25,"tagged_in_all":64,"counts":{"archive_papers_tagged":64,"with_a_code_link":25,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":64,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/a-user-simulator-for-task-completion","slug":"a-user-simulator-for-task-completion","title":"A User Simulator for Task-Completion Dialogues","date":"2016-12-17","arxiv_id":"1612.05688","repositories_listed":10,"syntology":null},{"url":"/paper/kuairec-a-fully-observed-dataset-for","slug":"kuairec-a-fully-observed-dataset-for","title":"KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems","date":"2022-02-22","arxiv_id":"2202.10842","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kuairec-a-fully-observed-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2202.10842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10842"}},"official":{"repos":["chongminggao/KuaiRec"],"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":["named_in_paper"]}}},{"url":"/paper/in-context-learning-user-simulators-for-task","slug":"in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","repositories_listed":2,"syntology":null},{"url":"/paper/crosswoz-a-large-scale-chinese-cross-domain","slug":"crosswoz-a-large-scale-chinese-cross-domain","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","date":"2020-02-27","arxiv_id":"2002.11893","repositories_listed":2,"syntology":null},{"url":"/paper/thought-augmented-planning-for-llm-powered","slug":"thought-augmented-planning-for-llm-powered","title":"Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent","date":"2025-06-30","arxiv_id":"2506.23485","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-human-like-thinking-in-search","slug":"exploring-human-like-thinking-in-search","title":"Exploring Human-Like Thinking in Search Simulations with Large Language Models","date":"2025-04-10","arxiv_id":"2504.07570","repositories_listed":1,"syntology":null},{"url":"/paper/flow-a-feedback-loop-framework-for","slug":"flow-a-feedback-loop-framework-for","title":"Agentic Feedback Loop Modeling Improves Recommendation and User Simulation","date":"2024-10-26","arxiv_id":"2410.20027","repositories_listed":1,"syntology":null},{"url":"/paper/multi-trait-user-simulation-with-adaptive","slug":"multi-trait-user-simulation-with-adaptive","title":"Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants","date":"2024-10-16","arxiv_id":"2410.12891","repositories_listed":1,"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":0,"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/multi-trait-user-simulation-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2410.12891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12891"}},"official":{"repos":["rafaelhferreira/mtad_cta"],"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/towards-a-formal-characterization-of-user","slug":"towards-a-formal-characterization-of-user","title":"Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access","date":"2024-06-27","arxiv_id":"2406.19007","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/towards-a-formal-characterization-of-user#ran","syntology_url":"https://syntology.ai/paper/2406.19007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19007"}},"official":{"repos":["iai-group/ictir2024-usersim-objectives"],"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/identifying-breakdowns-in-conversational","slug":"identifying-breakdowns-in-conversational","title":"Identifying Breakdowns in Conversational Recommender Systems using User Simulation","date":"2024-05-23","arxiv_id":"2405.14249","repositories_listed":1,"syntology":null},{"url":"/paper/lusifer-llm-based-user-simulated-feedback","slug":"lusifer-llm-based-user-simulated-feedback","title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","date":"2024-05-22","arxiv_id":"2405.13362","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-robustness-of","slug":"investigating-the-robustness-of","title":"Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study","date":"2024-04-04","arxiv_id":"2404.03707","repositories_listed":1,"syntology":null},{"url":"/paper/usimagent-large-language-models-for","slug":"usimagent-large-language-models-for","title":"USimAgent: Large Language Models for Simulating Search Users","date":"2024-03-14","arxiv_id":"2403.09142","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/usimagent-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.09142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09142"}},"official":{"repos":["meow-e/usimagent"],"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/unveiling-the-truth-and-facilitating-change","slug":"unveiling-the-truth-and-facilitating-change","title":"Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation","date":"2024-02-26","arxiv_id":"2402.16333","repositories_listed":1,"syntology":null},{"url":"/paper/recagent-a-novel-simulation-paradigm-for","slug":"recagent-a-novel-simulation-paradigm-for","title":"User Behavior Simulation with Large Language Model based Agents","date":"2023-06-05","arxiv_id":"2306.02552","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-interactive-lung-lesion","slug":"multimodal-interactive-lung-lesion","title":"Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues","date":"2023-01-24","arxiv_id":"2301.09914","repositories_listed":1,"syntology":null},{"url":"/paper/usersimcrs-a-user-simulation-toolkit-for","slug":"usersimcrs-a-user-simulation-toolkit-for","title":"UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems","date":"2023-01-13","arxiv_id":"2301.05544","repositories_listed":1,"syntology":null},{"url":"/paper/botsim-an-end-to-end-bot-simulation-toolkit","slug":"botsim-an-end-to-end-bot-simulation-toolkit","title":"BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems","date":"2022-11-29","arxiv_id":"2211.15916","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-simulating-user-utterance","slug":"analyzing-and-simulating-user-utterance","title":"Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems","date":"2022-05-03","arxiv_id":"2205.01763","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-mixed-initiative-conversational","slug":"evaluating-mixed-initiative-conversational","title":"Evaluating Mixed-initiative Conversational Search Systems via User Simulation","date":"2022-04-17","arxiv_id":"2204.08046","repositories_listed":1,"syntology":null},{"url":"/paper/reactive-and-safe-road-user-simulations-using","slug":"reactive-and-safe-road-user-simulations-using","title":"Reactive and Safe Road User Simulations using Neural Barrier Certificates","date":"2021-09-14","arxiv_id":"2109.06689","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-user-satisfaction-for-the","slug":"simulating-user-satisfaction-for-the","title":"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems","date":"2021-05-08","arxiv_id":"2105.03748","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-conversational-recommender-systems","slug":"evaluating-conversational-recommender-systems","title":"Evaluating Conversational Recommender Systems via User Simulation","date":"2020-06-15","arxiv_id":"2006.08732","repositories_listed":1,"syntology":null},{"url":"/paper/variational-hierarchical-dialog-autoencoder","slug":"variational-hierarchical-dialog-autoencoder","title":"Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation","date":"2020-01-23","arxiv_id":"2001.08604","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-build-user-simulators-to-train-rl","slug":"how-to-build-user-simulators-to-train-rl","title":"How to Build User Simulators to Train RL-based Dialog Systems","date":"2019-09-03","arxiv_id":"1909.01388","repositories_listed":1,"syntology":null},{"url":null,"slug":"ecom-bench-can-llm-agent-resolve-real-world-e","title":"ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?","date":"2025-07-08","arxiv_id":"2507.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-is-agentic-definitions","title":"The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems","date":"2025-07-02","arxiv_id":"2507.02097","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-user-simulation-for-low-knowledge","title":"LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems","date":"2025-05-18","arxiv_id":"2505.13528","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-impact-of-personality-traits-on-1","title":"Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models","date":"2025-04-09","arxiv_id":"2504.12313","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-simulation-in-the-era-of-generative-ai","title":"User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation","date":"2025-01-08","arxiv_id":"2501.04410","repositories_listed":0,"syntology":null},{"url":null,"slug":"vicsim-enhancing-victim-simulation-with","title":"VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity","date":"2025-01-06","arxiv_id":"2501.03139","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulation-free-hierarchical-latent-policy","title":"Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues","date":"2024-12-19","arxiv_id":"2412.14584","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmagent-a-large-scale-multimodal-agents","title":"LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation","date":"2024-12-12","arxiv_id":"2412.09237","repositories_listed":0,"syntology":null},{"url":null,"slug":"stop-playing-the-guessing-game-target-free","title":"Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems","date":"2024-11-25","arxiv_id":"2411.16160","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoautoarena-an-automated-arena-for","title":"VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation","date":"2024-11-20","arxiv_id":"2411.13281","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimizing-live-experiments-in-recommender","title":"Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies","date":"2024-09-26","arxiv_id":"2409.17436","repositories_listed":0,"syntology":null},{"url":null,"slug":"reformulating-conversational-recommender","title":"Reformulating Conversational Recommender Systems as Tri-Phase Offline Policy Learning","date":"2024-08-13","arxiv_id":"2408.06809","repositories_listed":0,"syntology":null},{"url":null,"slug":"strength-lies-in-differences-towards","title":"Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation","date":"2024-03-11","arxiv_id":"2403.06769","repositories_listed":0,"syntology":null},{"url":null,"slug":"bases-large-scale-web-search-user-simulation","title":"BASES: Large-scale Web Search User Simulation with Large Language Model based Agents","date":"2024-02-27","arxiv_id":"2402.17505","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-llm-based-user-simulator-for-task","title":"Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems","date":"2024-02-20","arxiv_id":"2402.13374","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-user-simulation-to-develop-and","title":"Leveraging User Simulation to Develop and Evaluate Conversational Information Access Agents","date":"2023-12-13","arxiv_id":"2312.08041","repositories_listed":0,"syntology":null},{"url":null,"slug":"circle-multi-turn-query-clarifications-with","title":"CIRCLE: Multi-Turn Query Clarifications with Reinforcement Learning","date":"2023-11-05","arxiv_id":"2311.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-simulation-with-large-language-models","title":"User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue","date":"2023-09-23","arxiv_id":"2309.13233","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-simulation-for-evaluating-information","title":"User Simulation for Evaluating Information Access Systems","date":"2023-06-14","arxiv_id":"2306.08550","repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-analysis-on-the-efficiency-of","title":"Theoretical Analysis on the Efficiency of Interleaved Comparisons","date":"2023-05-31","arxiv_id":"2306.10023","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-in-depth-investigation-of-user-response","title":"An In-depth Investigation of User Response Simulation for Conversational Search","date":"2023-04-17","arxiv_id":"2304.07944","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-centric-data-federated-learning","title":"Leveraging Centric Data Federated Learning Using Blockchain For Integrity Assurance","date":"2022-06-09","arxiv_id":"2206.04731","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-query-clarification-and","title":"Interactive Query Clarification and Refinement via User Simulation","date":"2022-05-31","arxiv_id":"2205.15918","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-of-the-art-of-user-simulation","title":"State of the Art of User Simulation approaches for conversational information retrieval","date":"2022-01-10","arxiv_id":"2201.03435","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-independent-user-simulation-with","title":"Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems","date":"2021-06-16","arxiv_id":"2106.08838","repositories_listed":0,"syntology":null},{"url":null,"slug":"advances-and-challenges-in-conversational","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","date":"2021-01-23","arxiv_id":"2101.09459","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-efficient-deployment-of-multiple-uavs","title":"Energy-efficient Deployment of Multiple UAVs Using Ellipse Clustering to Establish Base Stations","date":"2020-03-12","arxiv_id":"2003.05668","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-modeling-for-task-oriented-dialogues","title":"User Modeling for Task Oriented Dialogues","date":"2018-11-11","arxiv_id":"1811.04369","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-user-simulation-for-corpus-based","title":"Neural User Simulation for Corpus-based Policy Optimisation of Spoken Dialogue Systems","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-agreement-through-simulation-for","title":"Explainable Agreement through Simulation for Tasks with Subjective Labels","date":"2018-06-13","arxiv_id":"1806.05004","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-user-simulation-for-corpus-based-1","title":"Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems","date":"2018-05-17","arxiv_id":"1805.06966","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-mimo-relaying-with-linear-precoding","title":"Massive MIMO relaying with linear precoding in correlated channels under limited feedback","date":"2018-02-28","arxiv_id":"1802.10255","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sequence-to-sequence-model-for-user","title":"A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems","date":"2016-06-30","arxiv_id":"1607.00070","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuously-learning-neural-dialogue","title":"Continuously Learning Neural Dialogue Management","date":"2016-06-08","arxiv_id":"1606.02689","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-human-interpretable-dialog","title":"Optimizing human-interpretable dialog management policy using Genetic Algorithm","date":"2016-05-12","arxiv_id":"1605.03915","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-model-for-user-simulation-in-a","title":"A Generative Model for User Simulation in a Spatial Navigation Domain","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-approach-to-user-simulation","title":"An Unsupervised Approach to User Simulation: Toward Self-Improving Dialog Systems","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-goal-driven-user-simulation-for","title":"Generative Goal-Driven User Simulation for Dialog Management","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-user-simulation-for-spoken","title":"Statistical User Simulation for Spoken Dialogue Systems: What for, Which Data, Which Future?","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"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":3,"papers_where_code_ran_first_page":"/task/user-simulation/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/user-simulation/papers/ran/1","json":"/task/user-simulation/papers/ran/1.json","rows":3}],"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":"97e343ed5cc19c4be27c2e88acfced99a556845a1d0db9200d99944566b015d6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}