{"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/lambada","name":"LAMBADA","slug":"lambada","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":"archive_url"},"counts":{"papers_tagged":30,"papers_with_code":15,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1},"benchmarks":[{"leaderboard":"/sota/lambada-on-big-bench","slug":"lambada-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"Chinchilla-70B (zero-shot)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/reading-comprehension","name":"Reading Comprehension"}],"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":30,"of":30,"of_with_code":15,"tagged_in_all":30,"counts":{"archive_papers_tagged":30,"with_a_code_link":15,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":30,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","repositories_listed":10,"syntology":{"n":47,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":35,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/megatron-lm-training-multi-billion-parameter#ran","syntology_url":"https://syntology.ai/paper/1909.08053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08053"}},"official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/universal-transformers","slug":"universal-transformers","title":"Universal Transformers","date":"2018-07-10","arxiv_id":"1807.03819","repositories_listed":8,"syntology":{"n":25,"n_ran":17,"n_constructed":8,"n_ran_checked":17,"n_instrument":0,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":16,"n_pointer_only":24,"phrase":"17 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/universal-transformers#ran","syntology_url":"https://syntology.ai/paper/1807.03819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03819"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/the-lambada-dataset-word-prediction-requiring","slug":"the-lambada-dataset-word-prediction-requiring","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","date":"2016-06-20","arxiv_id":"1606.06031","repositories_listed":3,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/residual-shuffle-exchange-networks-for-fast","slug":"residual-shuffle-exchange-networks-for-fast","title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","date":"2020-04-06","arxiv_id":"2004.04662","repositories_listed":2,"syntology":null},{"url":"/paper/explaining-and-improving-contrastive-decoding","slug":"explaining-and-improving-contrastive-decoding","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","date":"2024-11-03","arxiv_id":"2411.01610","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-autoregression-fast-llms-via-self","slug":"beyond-autoregression-fast-llms-via-self","title":"Beyond Autoregression: Fast LLMs via Self-Distillation Through Time","date":"2024-10-28","arxiv_id":"2410.21035","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-autoregression-fast-llms-via-self#ran","syntology_url":"https://syntology.ai/paper/2410.21035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21035"}},"official":{"repos":["jdeschena/sdtt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spectra-a-comprehensive-study-of-ternary","slug":"spectra-a-comprehensive-study-of-ternary","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","date":"2024-07-17","arxiv_id":"2407.12327","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-inconsistencies-of-conditionals","slug":"on-the-inconsistencies-of-conditionals","title":"Inconsistencies in Masked Language Models","date":"2022-12-30","arxiv_id":"2301.00068","repositories_listed":1,"syntology":null},{"url":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence-1","slug":"neural-shuffle-exchange-networks-sequence-1","title":"Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/not-enough-data-deep-learning-to-the-rescue","slug":"not-enough-data-deep-learning-to-the-rescue","title":"Not Enough Data? Deep Learning to the Rescue!","date":"2019-11-08","arxiv_id":"1911.03118","repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence","slug":"neural-shuffle-exchange-networks-sequence","title":"Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time","date":"2019-07-18","arxiv_id":"1907.07897","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-shuffle-exchange-networks-sequence#ran","syntology_url":"https://syntology.ai/paper/1907.07897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07897"}},"official":{"repos":["LUMII-Syslab/shuffle-exchange"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/entity-tracking-improves-cloze-style-reading","slug":"entity-tracking-improves-cloze-style-reading","title":"Entity Tracking Improves Cloze-style Reading Comprehension","date":"2018-10-05","arxiv_id":"1810.02891","repositories_listed":1,"syntology":null},{"url":null,"slug":"matryoshka-model-learning-for-improved","title":"Matryoshka Model Learning for Improved Elastic Student Models","date":"2025-05-29","arxiv_id":"2505.23337","repositories_listed":0,"syntology":null},{"url":null,"slug":"adagc-improving-training-stability-for-large","title":"AdaGC: Improving Training Stability for Large Language Model Pretraining","date":"2025-02-16","arxiv_id":"2502.11034","repositories_listed":0,"syntology":null},{"url":null,"slug":"symba-symbolic-backward-chaining-for-multi","title":"SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning","date":"2024-02-20","arxiv_id":"2402.12806","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixar-auto-regressive-language-modeling-in","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","date":"2024-01-06","arxiv_id":"2401.03321","repositories_listed":0,"syntology":null},{"url":null,"slug":"concise-and-organized-perception-facilitates","title":"Concise and Organized Perception Facilitates Reasoning in Large Language Models","date":"2023-10-05","arxiv_id":"2310.03309","repositories_listed":0,"syntology":null},{"url":null,"slug":"headless-language-models-learning-without","title":"Headless Language Models: Learning without Predicting with Contrastive Weight Tying","date":"2023-09-15","arxiv_id":"2309.08351","repositories_listed":0,"syntology":null},{"url":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","repositories_listed":0,"syntology":null},{"url":null,"slug":"lambada-backward-chaining-for-automated","title":"LAMBADA: Backward Chaining for Automated Reasoning in Natural Language","date":"2022-12-20","arxiv_id":"2212.13894","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-relaxed-equilibrium-by-lazy","title":"Leveraging Relaxed Equilibrium by Lazy Transition for Sequence Modeling","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corelm-coreference-aware-language-model-fine-1","title":"CoreLM: Coreference-aware Language Model Fine-Tuning","date":"2021-11-04","arxiv_id":"2111.02687","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-t-entity-transformers-coreference-augmented","title":"E.T.: Entity-Transformers. Coreference augmented Neural Language Model for richer mention representations via Entity-Transformer blocks","date":"2020-11-10","arxiv_id":"2011.05431","repositories_listed":0,"syntology":null},{"url":null,"slug":"attending-to-entities-for-better-text","title":"Attending to Entities for Better Text Understanding","date":"2019-11-11","arxiv_id":"1911.04361","repositories_listed":0,"syntology":null},{"url":"/paper/neural-models-for-reasoning-over-multiple","slug":"neural-models-for-reasoning-over-multiple","title":"Neural Models for Reasoning over Multiple Mentions using Coreference","date":"2018-04-16","arxiv_id":"1804.05922","repositories_listed":0,"syntology":null},{"url":"/paper/linguistic-knowledge-as-memory-for-recurrent","slug":"linguistic-knowledge-as-memory-for-recurrent","title":"Linguistic Knowledge as Memory for Recurrent Neural Networks","date":"2017-03-07","arxiv_id":"1703.02620","repositories_listed":0,"syntology":null},{"url":"/paper/broad-context-language-modeling-as-reading","slug":"broad-context-language-modeling-as-reading","title":"Broad Context Language Modeling as Reading Comprehension","date":"2016-10-26","arxiv_id":"1610.08431","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":5,"papers_where_code_ran_first_page":"/task/lambada/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/lambada/papers/ran/1","json":"/task/lambada/papers/ran/1.json","rows":5}],"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":"5507d08de079cb4f7459b2245ec4d53c89643aa5a6239396873e6c26a0edcb23","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}