{"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/nethack","name":"NetHack","slug":"nethack","description_markdown":"Mean in-game score over 1000 episodes with random seeds not seen during training. See https://arxiv.org/abs/2006.13760 (Section 2.4 Evaluation Protocol) for details.","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":28,"papers_with_code":22,"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":1,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[{"url":"/task/score","name":"NetHack Score"}],"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":28,"of":28,"of_with_code":22,"tagged_in_all":28,"counts":{"archive_papers_tagged":28,"with_a_code_link":22,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":28,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/the-nethack-learning-environment","slug":"the-nethack-learning-environment","title":"The NetHack Learning Environment","date":"2020-06-24","arxiv_id":"2006.13760","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"6 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-nethack-learning-environment#ran","syntology_url":"https://syntology.ai/paper/2006.13760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13760"}},"official":{"repos":["facebookresearch/nle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hierarchical-kickstarting-for-skill-transfer","slug":"hierarchical-kickstarting-for-skill-transfer","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","date":"2022-07-23","arxiv_id":"2207.11584","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/hierarchical-kickstarting-for-skill-transfer#ran","syntology_url":"https://syntology.ai/paper/2207.11584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11584"}},"official":{"repos":["ucl-dark/skillhack"],"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/cora-benchmarks-baselines-and-metrics-as-a","slug":"cora-benchmarks-baselines-and-metrics-as-a","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","date":"2021-10-19","arxiv_id":"2110.10067","repositories_listed":2,"syntology":null},{"url":"/paper/bebold-exploration-beyond-the-boundary-of-1","slug":"bebold-exploration-beyond-the-boundary-of-1","title":"BeBold: Exploration Beyond the Boundary of Explored Regions","date":"2020-12-15","arxiv_id":"2012.08621","repositories_listed":2,"syntology":null},{"url":"/paper/syllabus-portable-curricula-for-reinforcement","slug":"syllabus-portable-curricula-for-reinforcement","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","date":"2024-11-18","arxiv_id":"2411.11318","repositories_listed":1,"syntology":null},{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pufferlib-making-reinforcement-learning","slug":"pufferlib-making-reinforcement-learning","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","date":"2024-06-11","arxiv_id":"2406.12905","repositories_listed":1,"syntology":null},{"url":"/paper/playing-nethack-with-llms-potential","slug":"playing-nethack-with-llms-potential","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","date":"2024-03-01","arxiv_id":"2403.00690","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/playing-nethack-with-llms-potential#ran","syntology_url":"https://syntology.ai/paper/2403.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00690"}},"official":{"repos":["commandercero/netplay"],"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/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":14,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-reinforcement-learning-models-is","slug":"fine-tuning-reinforcement-learning-models-is","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","date":"2024-02-05","arxiv_id":"2402.02868","repositories_listed":1,"syntology":null},{"url":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skill-set-optimization-reinforcing-language#ran","syntology_url":"https://syntology.ai/paper/2402.03244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03244"}},"official":{"repos":["allenai/sso"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diff-history-for-long-context-language-agents","slug":"diff-history-for-long-context-language-agents","title":"diff History for Neural Language Agents","date":"2023-12-12","arxiv_id":"2312.07540","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diff-history-for-long-context-language-agents#ran","syntology_url":"https://syntology.ai/paper/2312.07540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07540"}},"official":{"repos":["upiterbarg/diff_history"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/motif-intrinsic-motivation-from-artificial","slug":"motif-intrinsic-motivation-from-artificial","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","date":"2023-09-29","arxiv_id":"2310.00166","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motif-intrinsic-motivation-from-artificial#ran","syntology_url":"https://syntology.ai/paper/2310.00166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00166"}},"official":{"repos":["facebookresearch/motif"],"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/scaling-laws-for-imitation-learning-in","slug":"scaling-laws-for-imitation-learning-in","title":"Scaling Laws for Imitation Learning in Single-Agent Games","date":"2023-07-18","arxiv_id":"2307.09423","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":3,"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/scaling-laws-for-imitation-learning-in#ran","syntology_url":"https://syntology.ai/paper/2307.09423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09423"}},"official":{"repos":["princeton-nlp/il-scaling-in-games"],"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/luckymera-a-modular-ai-framework-for-building","slug":"luckymera-a-modular-ai-framework-for-building","title":"LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents","date":"2023-07-17","arxiv_id":"2307.08532","repositories_listed":1,"syntology":null},{"url":"/paper/katakomba-tools-and-benchmarks-for-data","slug":"katakomba-tools-and-benchmarks-for-data","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","date":"2023-06-14","arxiv_id":"2306.08772","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/katakomba-tools-and-benchmarks-for-data#ran","syntology_url":"https://syntology.ai/paper/2306.08772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08772"}},"official":{"repos":["corl-team/katakomba"],"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/dungeons-and-data-a-large-scale-nethack","slug":"dungeons-and-data-a-large-scale-nethack","title":"Dungeons and Data: A Large-Scale NetHack Dataset","date":"2022-11-01","arxiv_id":"2211.00539","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/dungeons-and-data-a-large-scale-nethack#ran","syntology_url":"https://syntology.ai/paper/2211.00539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00539"}},"official":{"repos":["facebookresearch/nle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-policy-learning-via-language","slug":"improving-policy-learning-via-language","title":"Improving Policy Learning via Language Dynamics Distillation","date":"2022-09-30","arxiv_id":"2210.00066","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/improving-policy-learning-via-language#ran","syntology_url":"https://syntology.ai/paper/2210.00066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00066"}},"official":{"repos":["vzhong/language-dynamics-distillation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/insights-from-the-neurips-2021-nethack","slug":"insights-from-the-neurips-2021-nethack","title":"Insights From the NeurIPS 2021 NetHack Challenge","date":"2022-03-22","arxiv_id":"2203.11889","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/insights-from-the-neurips-2021-nethack#ran","syntology_url":"https://syntology.ai/paper/2203.11889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11889"}},"official":null}},{"url":"/paper/noveld-a-simple-yet-effective-exploration","slug":"noveld-a-simple-yet-effective-exploration","title":"NovelD: A Simple yet Effective Exploration Criterion","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/silg-the-multi-environment-symbolic","slug":"silg-the-multi-environment-symbolic","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","date":"2021-10-20","arxiv_id":"2110.10661","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/silg-the-multi-environment-symbolic#ran","syntology_url":"https://syntology.ai/paper/2110.10661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10661"}},"official":{"repos":["vzhong/silg"],"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"]}}},{"url":"/paper/minihack-the-planet-a-sandbox-for-open-ended","slug":"minihack-the-planet-a-sandbox-for-open-ended","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","date":"2021-09-27","arxiv_id":"2109.13202","repositories_listed":1,"syntology":null},{"url":null,"slug":"maestromotif-skill-design-from-artificial","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","date":"2024-12-11","arxiv_id":"2412.08542","repositories_listed":0,"syntology":null},{"url":null,"slug":"balrog-benchmarking-agentic-llm-and-vlm","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","date":"2024-11-20","arxiv_id":"2411.13543","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-perception-optimizing-state","title":"Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors","date":"2023-07-21","arxiv_id":"2307.11922","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-exploration-and-representation","title":"Accelerating exploration and representation learning with offline pre-training","date":"2023-03-31","arxiv_id":"2304.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"silg-the-multi-domain-symbolic-interactive","title":"SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-nethack-with-secret-discovery","title":"Exploration in NetHack With Secret Discovery","date":"2017-11-08","arxiv_id":"1711.03087","repositories_listed":0,"syntology":null}],"syntology_records":14,"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":14,"papers_where_code_ran_first_page":"/task/nethack/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/nethack/papers/ran/1","json":"/task/nethack/papers/ran/1.json","rows":14}],"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":"17eeead5095573a5892270f58ce97cc1e3a1f9bc6fd113f9fd338a6be2725bd1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}