{"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/implicatures","name":"Implicatures","slug":"implicatures","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":29,"papers_with_code":7,"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/implicatures-on-big-bench","slug":"implicatures-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 (few-shot, k=5)","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":29,"of":29,"of_with_code":7,"tagged_in_all":29,"counts":{"archive_papers_tagged":29,"with_a_code_link":7,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":29,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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/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/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/do-large-language-models-understand","slug":"do-large-language-models-understand","title":"Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom","date":"2024-04-30","arxiv_id":"2404.19509","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/do-large-language-models-understand#ran","syntology_url":"https://syntology.ai/paper/2404.19509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19509"}},"official":{"repos":["sjtu-compling/llm-pragmatics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/probing-large-language-models-for-scalar","slug":"probing-large-language-models-for-scalar","title":"Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics","date":"2024-04-04","arxiv_id":"2404.03301","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-acquisition-of-fine-grained","slug":"interactive-acquisition-of-fine-grained","title":"Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse","date":"2023-05-05","arxiv_id":"2305.03461","repositories_listed":1,"syntology":null},{"url":"/paper/psycholinguistic-diagnosis-of-language-models","slug":"psycholinguistic-diagnosis-of-language-models","title":"Psycholinguistic Diagnosis of Language Models’ Commonsense Reasoning","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/are-natural-language-inference-models","slug":"are-natural-language-inference-models","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","date":"2020-04-07","arxiv_id":"2004.03066","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/are-natural-language-inference-models#ran","syntology_url":"https://syntology.ai/paper/2004.03066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03066"}},"official":{"repos":["alexwarstadt/data_generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["found_in_text"]}}},{"url":null,"slug":"pragmatics-in-the-era-of-large-language","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","date":"2025-02-17","arxiv_id":"2502.12378","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-influence-of-visual-and-linguistic-cues","title":"Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues","date":"2025-02-13","arxiv_id":"2502.09120","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurosymbolic-graph-enrichment-for-grounded","title":"Neurosymbolic Graph Enrichment for Grounded World Models","date":"2024-11-19","arxiv_id":"2411.12671","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-language-models-capture-implied-discourse","title":"Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology","date":"2024-05-15","arxiv_id":"2405.09293","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-pragmatics-with-machines-testing","title":"Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctions","date":"2024-05-09","arxiv_id":"2405.05776","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-conventions-equilibrium","title":"Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning","date":"2023-11-16","arxiv_id":"2311.09712","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-the-pope-catholic-applying-chain-of","title":"\"Is the Pope Catholic?\" Applying Chain-of-Thought Reasoning to Understanding Conversational Implicatures","date":"2023-05-23","arxiv_id":"2305.13826","repositories_listed":0,"syntology":null},{"url":null,"slug":"pragmatic-competence-of-pre-trained-language","title":"Pragmatic competence of pre-trained language models through the lens of discourse connectives","date":"2021-09-27","arxiv_id":"2109.12951","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-semiotics","title":"Machine Semiotics","date":"2020-08-24","arxiv_id":"2008.10522","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-implicatures-in-english","title":"Conversational implicatures in English dialogue: Annotated dataset","date":"2019-11-25","arxiv_id":"1911.10704","repositories_listed":0,"syntology":null},{"url":null,"slug":"coverage-of-information-extraction-from","title":"Coverage of Information Extraction from Sentences and Paragraphs","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"controlled-natural-languages-and-default","title":"Controlled Natural Languages and Default Reasoning","date":"2019-05-11","arxiv_id":"1905.04422","repositories_listed":0,"syntology":null},{"url":null,"slug":"sensala-a-dynamic-semantics-system-for","title":"Sensala: a Dynamic Semantics System for Natural Language Processing","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-structure-syntax-and-pragmatics","title":"Information structure, syntax, and pragmatics and other factors in resolving scope ambiguity","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-semantic-models-with-word-sentence","title":"Evaluating semantic models with word-sentence relatedness","date":"2016-03-23","arxiv_id":"1603.07253","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-compositional-semantics-using","title":"Cognitive Compositional Semantics using Continuation Dependencies","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-conceptual-framework-for-inferring","title":"A Conceptual Framework for Inferring Implicatures","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigation-for-implicatures-in-chinese","title":"An Investigation for Implicatures in Chinese : Implicatures in Chinese and in English are similar !","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-account-of-opinion-implicatures","title":"An Account of Opinion Implicatures","date":"2014-04-23","arxiv_id":"1404.6491","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-approach-to-scalar-implicatures-in","title":"Global Approach to Scalar Implicatures in Dynamic Semantics","date":"2013-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"implicatures-and-nested-beliefs-in","title":"Implicatures and Nested Beliefs in Approximate Decentralized-POMDPs","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tool-for-extracting-conversational","title":"A Tool for Extracting Conversational Implicatures","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"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/implicatures/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/implicatures/papers/ran/1","json":"/task/implicatures/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":"c51b9574abdecb49338f836a48a94c89c34043b3e61df7f1a99db5ed57dfab61","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}