{"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/negation","name":"Negation","slug":"negation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":608,"papers_with_code":173,"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":0},"benchmarks":[],"datasets":[{"url":"/dataset/ovdeval","name":"OVDEval","full_name":"","num_papers_in_archive":4},{"url":"/dataset/thunder-nubench","name":"Thunder-NUBench","full_name":"","num_papers_in_archive":1}],"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":7,"rows_per_page":100,"shown":100,"of":608,"of_with_code":173,"tagged_in_all":608,"counts":{"archive_papers_tagged":608,"with_a_code_link":173,"where_syntology_ran_a_sample":41,"not_listed_spam_title":0,"listed":608,"listed_where_code_ran":41,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":12,"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/editing-models-with-task-arithmetic","slug":"editing-models-with-task-arithmetic","title":"Editing Models with Task Arithmetic","date":"2022-12-08","arxiv_id":"2212.04089","repositories_listed":9,"syntology":{"n":15,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/editing-models-with-task-arithmetic#ran","syntology_url":"https://syntology.ai/paper/2212.04089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04089"}},"official":{"repos":["mlfoundations/task_vectors"],"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":["listed","unlocated"]}}},{"url":"/paper/beta-embeddings-for-multi-hop-logical","slug":"beta-embeddings-for-multi-hop-logical","title":"Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs","date":"2020-10-22","arxiv_id":"2010.11465","repositories_listed":9,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/beta-embeddings-for-multi-hop-logical#ran","syntology_url":"https://syntology.ai/paper/2010.11465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11465"}},"official":null}},{"url":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","repositories_listed":6,"syntology":{"n":25,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":17,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/qa-gnn-reasoning-with-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2104.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06378"}},"official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/logic-embeddings-for-complex-query-answering","slug":"logic-embeddings-for-complex-query-answering","title":"Logic Embeddings for Complex Query Answering","date":"2021-02-28","arxiv_id":"2103.00418","repositories_listed":4,"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/logic-embeddings-for-complex-query-answering#ran","syntology_url":"https://syntology.ai/paper/2103.00418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00418"}},"official":{"repos":["francoisluus/KGReasoning"],"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":["unlocated"]}}},{"url":"/paper/ratescore-a-metric-for-radiology-report","slug":"ratescore-a-metric-for-radiology-report","title":"RaTEScore: A Metric for Radiology Report Generation","date":"2024-06-24","arxiv_id":"2406.16845","repositories_listed":3,"syntology":null},{"url":"/paper/analogs-of-linguistic-structure-in-deep","slug":"analogs-of-linguistic-structure-in-deep","title":"Analogs of Linguistic Structure in Deep Representations","date":"2017-07-25","arxiv_id":"1707.08139","repositories_listed":3,"syntology":null},{"url":"/paper/fast-and-accurate-sentiment-classification","slug":"fast-and-accurate-sentiment-classification","title":"Fast and accurate sentiment classification using an enhanced Naive Bayes model","date":"2013-05-27","arxiv_id":"1305.6143","repositories_listed":3,"syntology":null},{"url":"/paper/reproducing-nevir-negation-in-neural","slug":"reproducing-nevir-negation-in-neural","title":"Reproducing NevIR: Negation in Neural Information Retrieval","date":"2025-02-19","arxiv_id":"2502.13506","repositories_listed":2,"syntology":null},{"url":"/paper/ask-again-then-fail-large-language-models","slug":"ask-again-then-fail-large-language-models","title":"Ask Again, Then Fail: Large Language Models' Vacillations in Judgment","date":"2023-10-03","arxiv_id":"2310.02174","repositories_listed":2,"syntology":null},{"url":"/paper/resolving-legalese-a-multilingual-exploration","slug":"resolving-legalese-a-multilingual-exploration","title":"Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents","date":"2023-09-15","arxiv_id":"2309.08695","repositories_listed":2,"syntology":null},{"url":"/paper/this-is-not-correct-negation-aware-evaluation","slug":"this-is-not-correct-negation-aware-evaluation","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","date":"2023-07-26","arxiv_id":"2307.13989","repositories_listed":2,"syntology":null},{"url":"/paper/composing-parameter-efficient-modules-with","slug":"composing-parameter-efficient-modules-with","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","date":"2023-06-26","arxiv_id":"2306.14870","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/composing-parameter-efficient-modules-with#ran","syntology_url":"https://syntology.ai/paper/2306.14870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14870"}},"official":{"repos":["hkust-nlp/pem_composition","sjtu-lit/pem_composition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-learning-of-negation-and","slug":"multi-task-learning-of-negation-and","title":"Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification","date":"2020-10-16","arxiv_id":"2010.08318","repositories_listed":2,"syntology":null},{"url":"/paper/sentibert-a-transferable-transformer-based","slug":"sentibert-a-transferable-transformer-based","title":"SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics","date":"2020-05-08","arxiv_id":"2005.04114","repositories_listed":2,"syntology":null},{"url":"/paper/negated-lama-birds-cannot-fly","slug":"negated-lama-birds-cannot-fly","title":"Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly","date":"2019-11-08","arxiv_id":"1911.03343","repositories_listed":2,"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/negated-lama-birds-cannot-fly#ran","syntology_url":"https://syntology.ai/paper/1911.03343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03343"}},"official":{"repos":["facebookresearch/LAMA","norakassner/LAMA_primed_negated"],"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/explanation-by-progressive-exaggeration-1","slug":"explanation-by-progressive-exaggeration-1","title":"Explanation by Progressive Exaggeration","date":"2019-11-01","arxiv_id":"1911.00483","repositories_listed":2,"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/explanation-by-progressive-exaggeration-1#ran","syntology_url":"https://syntology.ai/paper/1911.00483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00483"}},"official":{"repos":["batmanlab/Explanation_by_Progressive_Exaggeration"],"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/what-bert-is-not-lessons-from-a-new-suite-of","slug":"what-bert-is-not-lessons-from-a-new-suite-of","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","date":"2019-07-31","arxiv_id":"1907.13528","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/what-bert-is-not-lessons-from-a-new-suite-of#ran","syntology_url":"https://syntology.ai/paper/1907.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13528"}},"official":{"repos":["aetting/lm-diagnostics"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evaluating-scoped-meaning-representations","slug":"evaluating-scoped-meaning-representations","title":"Evaluating Scoped Meaning Representations","date":"2018-02-23","arxiv_id":"1802.08599","repositories_listed":2,"syntology":null},{"url":"/paper/mazebase-a-sandbox-for-learning-from-games","slug":"mazebase-a-sandbox-for-learning-from-games","title":"MazeBase: A Sandbox for Learning from Games","date":"2015-11-23","arxiv_id":"1511.07401","repositories_listed":2,"syntology":null},{"url":"/paper/probing-the-geometry-of-truth-consistency-and","slug":"probing-the-geometry-of-truth-consistency-and","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","date":"2025-06-01","arxiv_id":"2506.00823","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/probing-the-geometry-of-truth-consistency-and#ran","syntology_url":"https://syntology.ai/paper/2506.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00823"}},"official":{"repos":["colored-dye/truthfulness_probe_generalization"],"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/2505-11314","slug":"2505-11314","title":"CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks","date":"2025-05-16","arxiv_id":"2505.11314","repositories_listed":1,"syntology":null},{"url":"/paper/formalmath-benchmarking-formal-mathematical","slug":"formalmath-benchmarking-formal-mathematical","title":"FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models","date":"2025-05-05","arxiv_id":"2505.02735","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/formalmath-benchmarking-formal-mathematical#ran","syntology_url":"https://syntology.ai/paper/2505.02735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02735"}},"official":{"repos":["sphere-ai-lab/formalmath-bench"],"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/negativas-a-prototype-for-searching-and","slug":"negativas-a-prototype-for-searching-and","title":"negativas: a prototype for searching and classifying sentential negation in speech data","date":"2025-04-05","arxiv_id":"2504.04275","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-editing-with-task-localized","slug":"efficient-model-editing-with-task-localized","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","date":"2025-04-03","arxiv_id":"2504.02620","repositories_listed":1,"syntology":null},{"url":"/paper/is-clip-ideal-no-can-we-fix-it-yes","slug":"is-clip-ideal-no-can-we-fix-it-yes","title":"Is CLIP ideal? No. Can we fix it? Yes!","date":"2025-03-10","arxiv_id":"2503.08723","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-editing-with-task-vector","slug":"efficient-model-editing-with-task-vector","title":"Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach","date":"2025-02-03","arxiv_id":"2502.01015","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 2 unverified","sample_list":"/paper/efficient-model-editing-with-task-vector#ran","syntology_url":"https://syntology.ai/paper/2502.01015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01015"}},"official":{"repos":["uiuctml/TaskVectorBasis"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-zero-shot-3d-visual-grounding-as","slug":"solving-zero-shot-3d-visual-grounding-as","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","date":"2024-11-21","arxiv_id":"2411.14594","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-language-and-diffusion-models-by","slug":"controlling-language-and-diffusion-models-by","title":"Controlling Language and Diffusion Models by Transporting Activations","date":"2024-10-30","arxiv_id":"2410.23054","repositories_listed":1,"syntology":null},{"url":"/paper/automatically-generating-visual-hallucination","slug":"automatically-generating-visual-hallucination","title":"Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models","date":"2024-10-15","arxiv_id":"2410.11242","repositories_listed":1,"syntology":null},{"url":"/paper/negmerge-consensual-weight-negation-for","slug":"negmerge-consensual-weight-negation-for","title":"NegMerge: Consensual Weight Negation for Strong Machine Unlearning","date":"2024-10-08","arxiv_id":"2410.05583","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 3 unverified","sample_list":"/paper/negmerge-consensual-weight-negation-for#ran","syntology_url":"https://syntology.ai/paper/2410.05583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05583"}},"official":{"repos":["naver-ai/negmerge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-structure-of-game-provenance-and-its","slug":"on-the-structure-of-game-provenance-and-its","title":"On the Structure of Game Provenance and its Applications","date":"2024-10-07","arxiv_id":"2410.05094","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-pretrained-language-models-on","slug":"evaluation-of-pretrained-language-models-on","title":"Evaluation of pretrained language models on music understanding","date":"2024-09-17","arxiv_id":"2409.11449","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluation-of-pretrained-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2409.11449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11449"}},"official":{"repos":["YannisBilly/Evaluation-of-pretrained-language-models-on-music-understanding"],"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/rcone-rough-cone-embedding-for-multi-hop","slug":"rcone-rough-cone-embedding-for-multi-hop","title":"RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs","date":"2024-08-21","arxiv_id":"2408.11526","repositories_listed":1,"syntology":null},{"url":"/paper/reproducibility-study-of-iti-gen-inclusive","slug":"reproducibility-study-of-iti-gen-inclusive","title":"Reproducibility Study of \"ITI-GEN: Inclusive Text-to-Image Generation\"","date":"2024-07-29","arxiv_id":"2407.19996","repositories_listed":1,"syntology":null},{"url":"/paper/through-the-looking-glass-and-what-horn","slug":"through-the-looking-glass-and-what-horn","title":"Through the Looking Glass, and what Horn Clause Programs Found There","date":"2024-07-29","arxiv_id":"2407.20413","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-robustness-of-adverse-drug","slug":"evaluating-the-robustness-of-adverse-drug","title":"Evaluating the Robustness of Adverse Drug Event Classification Models Using Templates","date":"2024-07-02","arxiv_id":"2407.02432","repositories_listed":1,"syntology":null},{"url":"/paper/rublimp-russian-benchmark-of-linguistic","slug":"rublimp-russian-benchmark-of-linguistic","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","date":"2024-06-27","arxiv_id":"2406.19232","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rublimp-russian-benchmark-of-linguistic#ran","syntology_url":"https://syntology.ai/paper/2406.19232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19232"}},"official":{"repos":["russiannlp/rublimp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/worse-than-random-an-embarrassingly-simple","slug":"worse-than-random-an-embarrassingly-simple","title":"Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA","date":"2024-05-30","arxiv_id":"2405.20421","repositories_listed":1,"syntology":null},{"url":"/paper/negation-triplet-extraction-with-syntactic","slug":"negation-triplet-extraction-with-syntactic","title":"Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency","date":"2024-04-15","arxiv_id":"2404.09830","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safer-large-language-models-through","slug":"towards-safer-large-language-models-through","title":"Towards Safer Large Language Models through Machine Unlearning","date":"2024-02-15","arxiv_id":"2402.10058","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/towards-safer-large-language-models-through#ran","syntology_url":"https://syntology.ai/paper/2402.10058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10058"}},"official":{"repos":["franciscoliu/sku"],"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/approximate-attributions-for-off-the-shelf","slug":"approximate-attributions-for-off-the-shelf","title":"Approximate Attributions for Off-the-Shelf Siamese Transformers","date":"2024-02-05","arxiv_id":"2402.02883","repositories_listed":1,"syntology":null},{"url":"/paper/longhealth-a-question-answering-benchmark","slug":"longhealth-a-question-answering-benchmark","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","date":"2024-01-25","arxiv_id":"2401.14490","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":0,"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/longhealth-a-question-answering-benchmark#ran","syntology_url":"https://syntology.ai/paper/2401.14490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14490"}},"official":{"repos":["kbressem/longhealth"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/propres-investigating-the-projectivity-of","slug":"propres-investigating-the-projectivity-of","title":"PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments","date":"2023-12-14","arxiv_id":"2312.08755","repositories_listed":1,"syntology":null},{"url":"/paper/expressive-sign-equivariant-networks-for-1","slug":"expressive-sign-equivariant-networks-for-1","title":"Expressive Sign Equivariant Networks for Spectral Geometric Learning","date":"2023-12-04","arxiv_id":"2312.02339","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/expressive-sign-equivariant-networks-for-1#ran","syntology_url":"https://syntology.ai/paper/2312.02339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02339"}},"official":{"repos":["cptq/sign-equivariant-nets"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/regularization-by-texts-for-latent-diffusion","slug":"regularization-by-texts-for-latent-diffusion","title":"Regularization by Texts for Latent Diffusion Inverse Solvers","date":"2023-11-27","arxiv_id":"2311.15658","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/regularization-by-texts-for-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2311.15658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15658"}},"official":{"repos":["treg-inverse/treg"],"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/you-don-t-need-a-personality-test-to-know","slug":"you-don-t-need-a-personality-test-to-know","title":"You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments","date":"2023-11-16","arxiv_id":"2311.09718","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/you-don-t-need-a-personality-test-to-know#ran","syntology_url":"https://syntology.ai/paper/2311.09718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09718"}},"official":{"repos":["orange0629/llm-personas"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/instant3d-instant-text-to-3d-generation","slug":"instant3d-instant-text-to-3d-generation","title":"Instant3D: Instant Text-to-3D Generation","date":"2023-11-14","arxiv_id":"2311.08403","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/instant3d-instant-text-to-3d-generation#ran","syntology_url":"https://syntology.ai/paper/2311.08403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08403"}},"official":{"repos":["ming1993li/instant3dcodes"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/this-is-not-a-dataset-a-large-negation","slug":"this-is-not-a-dataset-a-large-negation","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","date":"2023-10-24","arxiv_id":"2310.15941","repositories_listed":1,"syntology":null},{"url":"/paper/generating-prototypes-for-contradiction","slug":"generating-prototypes-for-contradiction","title":"Generating Prototypes for Contradiction Detection Using Large Language Models and Linguistic Rules","date":"2023-10-23","arxiv_id":"2310.14732","repositories_listed":1,"syntology":null},{"url":"/paper/automated-verification-of-equivalence","slug":"automated-verification-of-equivalence","title":"Automated Verification of Equivalence Properties in Advanced Logic Programs -- Bachelor Thesis","date":"2023-10-11","arxiv_id":"2310.19806","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-contrast-consistent-ranking-with","slug":"unsupervised-contrast-consistent-ranking-with","title":"Unsupervised Contrast-Consistent Ranking with Language Models","date":"2023-09-13","arxiv_id":"2309.06991","repositories_listed":1,"syntology":null},{"url":"/paper/can-linguistic-knowledge-improve-multimodal","slug":"can-linguistic-knowledge-improve-multimodal","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","date":"2023-08-24","arxiv_id":"2308.12898","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/can-linguistic-knowledge-improve-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.12898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12898"}},"official":{"repos":["wangfei-2019/snare"],"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/clipn-for-zero-shot-ood-detection-teaching","slug":"clipn-for-zero-shot-ood-detection-teaching","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","date":"2023-08-23","arxiv_id":"2308.12213","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":1,"n_ran_checked":8,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/clipn-for-zero-shot-ood-detection-teaching#ran","syntology_url":"https://syntology.ai/paper/2308.12213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12213"}},"official":{"repos":["xmed-lab/clipn"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-phenotype-recognition-in-clinical","slug":"enhancing-phenotype-recognition-in-clinical","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","date":"2023-08-11","arxiv_id":"2308.06294","repositories_listed":1,"syntology":null},{"url":"/paper/biomedical-knowledge-graph-embeddings-with","slug":"biomedical-knowledge-graph-embeddings-with","title":"Biomedical Knowledge Graph Embeddings with Negative Statements","date":"2023-08-07","arxiv_id":"2308.03447","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-dataset-for-evaluating-complex","slug":"synthetic-dataset-for-evaluating-complex","title":"Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference","date":"2023-07-11","arxiv_id":"2307.05034","repositories_listed":1,"syntology":null},{"url":"/paper/spacenli-evaluating-the-consistency-of","slug":"spacenli-evaluating-the-consistency-of","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","date":"2023-07-05","arxiv_id":"2307.02269","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-cross-temporal-summarization","slug":"cross-lingual-cross-temporal-summarization","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","date":"2023-06-22","arxiv_id":"2306.12916","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-chinese-english-machine","slug":"evaluation-of-chinese-english-machine","title":"Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation","date":"2023-06-20","arxiv_id":"2306.11900","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","repositories_listed":1,"syntology":null},{"url":"/paper/scone-benchmarking-negation-reasoning-in","slug":"scone-benchmarking-negation-reasoning-in","title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","date":"2023-05-30","arxiv_id":"2305.19426","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-positive-scaling-how-negation-impacts","slug":"beyond-positive-scaling-how-negation-impacts","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","date":"2023-05-27","arxiv_id":"2305.17311","repositories_listed":1,"syntology":null},{"url":"/paper/an-examination-of-the-robustness-of-reference","slug":"an-examination-of-the-robustness-of-reference","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","date":"2023-05-24","arxiv_id":"2305.14998","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-examination-of-the-robustness-of-reference#ran","syntology_url":"https://syntology.ai/paper/2305.14998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14998"}},"official":{"repos":["saba96/img-cap-metrics-robustness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quest-a-retrieval-dataset-of-entity-seeking","slug":"quest-a-retrieval-dataset-of-entity-seeking","title":"QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations","date":"2023-05-19","arxiv_id":"2305.11694","repositories_listed":1,"syntology":null},{"url":"/paper/nevir-negation-in-neural-information","slug":"nevir-negation-in-neural-information","title":"NevIR: Negation in Neural Information Retrieval","date":"2023-05-12","arxiv_id":"2305.07614","repositories_listed":1,"syntology":null},{"url":"/paper/factkg-fact-verification-via-reasoning-on","slug":"factkg-fact-verification-via-reasoning-on","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","date":"2023-05-11","arxiv_id":"2305.06590","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/factkg-fact-verification-via-reasoning-on#ran","syntology_url":"https://syntology.ai/paper/2305.06590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06590"}},"official":{"repos":["jiho283/FactKG"],"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/say-what-you-mean-large-language-models-speak","slug":"say-what-you-mean-large-language-models-speak","title":"Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge","date":"2023-05-10","arxiv_id":"2305.05976","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/say-what-you-mean-large-language-models-speak#ran","syntology_url":"https://syntology.ai/paper/2305.05976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05976"}},"official":{"repos":["jiangjiechen/uncommongen"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-statistical-language-models-as","slug":"evaluating-statistical-language-models-as","title":"Evaluating statistical language models as pragmatic reasoners","date":"2023-05-01","arxiv_id":"2305.01020","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-boundaries-of-tractable","slug":"pushing-the-boundaries-of-tractable","title":"Pushing the Boundaries of Tractable Multiperspective Reasoning: A Deduction Calculus for Standpoint EL+","date":"2023-04-27","arxiv_id":"2304.14323","repositories_listed":1,"syntology":null},{"url":"/paper/larger-probes-tell-a-different-story","slug":"larger-probes-tell-a-different-story","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","date":"2023-03-29","arxiv_id":"2303.16445","repositories_listed":1,"syntology":null},{"url":"/paper/generalisation-through-negation-and-predicate","slug":"generalisation-through-negation-and-predicate","title":"Generalisation Through Negation and Predicate Invention","date":"2023-01-18","arxiv_id":"2301.07629","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","repositories_listed":1,"syntology":null},{"url":"/paper/crepe-can-vision-language-foundation-models","slug":"crepe-can-vision-language-foundation-models","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","date":"2022-12-13","arxiv_id":"2212.07796","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crepe-can-vision-language-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.07796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07796"}},"official":{"repos":["raivnlab/crepe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-high-order-complementary","slug":"towards-high-order-complementary","title":"Towards High-Order Complementary Recommendation via Logical Reasoning Network","date":"2022-12-09","arxiv_id":"2212.04966","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-latent-knowledge-in-language","slug":"discovering-latent-knowledge-in-language","title":"Discovering Latent Knowledge in Language Models Without Supervision","date":"2022-12-07","arxiv_id":"2212.03827","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/discovering-latent-knowledge-in-language#ran","syntology_url":"https://syntology.ai/paper/2212.03827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03827"}},"official":{"repos":["collin-burns/discovering_latent_knowledge"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/nqe-n-ary-query-embedding-for-complex-query","slug":"nqe-n-ary-query-embedding-for-complex-query","title":"NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphs","date":"2022-11-24","arxiv_id":"2211.13469","repositories_listed":1,"syntology":null},{"url":"/paper/condaqa-a-contrastive-reading-comprehension","slug":"condaqa-a-contrastive-reading-comprehension","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","date":"2022-11-01","arxiv_id":"2211.00295","repositories_listed":1,"syntology":null},{"url":"/paper/gammae-gamma-embeddings-for-logical-queries","slug":"gammae-gamma-embeddings-for-logical-queries","title":"GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs","date":"2022-10-27","arxiv_id":"2210.15578","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gammae-gamma-embeddings-for-logical-queries#ran","syntology_url":"https://syntology.ai/paper/2210.15578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15578"}},"official":{"repos":["dyang67/GammaE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-affirmative-interpretations-from","slug":"leveraging-affirmative-interpretations-from","title":"Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding","date":"2022-10-26","arxiv_id":"2210.14486","repositories_listed":1,"syntology":null},{"url":"/paper/are-all-spurious-features-in-natural-language","slug":"are-all-spurious-features-in-natural-language","title":"Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens","date":"2022-10-25","arxiv_id":"2210.14011","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/are-all-spurious-features-in-natural-language#ran","syntology_url":"https://syntology.ai/paper/2210.14011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14011"}},"official":{"repos":["joshinh/spurious-correlations-nlp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sda-simple-discrete-augmentation-for","slug":"sda-simple-discrete-augmentation-for","title":"SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning","date":"2022-10-08","arxiv_id":"2210.03963","repositories_listed":1,"syntology":null},{"url":"/paper/inferes-a-natural-language-inference-corpus","slug":"inferes-a-natural-language-inference-corpus","title":"InferES : A Natural Language Inference Corpus for Spanish Featuring Negation-Based Contrastive and Adversarial Examples","date":"2022-10-06","arxiv_id":"2210.03068","repositories_listed":1,"syntology":null},{"url":"/paper/not-another-negation-benchmark-the-nan-nli","slug":"not-another-negation-benchmark-the-nan-nli","title":"Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation","date":"2022-10-06","arxiv_id":"2210.03256","repositories_listed":1,"syntology":null},{"url":"/paper/neural-methods-for-logical-reasoning-over-1","slug":"neural-methods-for-logical-reasoning-over-1","title":"Neural Methods for Logical Reasoning Over Knowledge Graphs","date":"2022-09-28","arxiv_id":"2209.14464","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-methods-for-logical-reasoning-over-1#ran","syntology_url":"https://syntology.ai/paper/2209.14464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14464"}},"official":{"repos":["amayuelas/NNKGReasoning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/negation-detection-in-dutch-clinical-texts-an","slug":"negation-detection-in-dutch-clinical-texts-an","title":"Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods","date":"2022-09-01","arxiv_id":"2209.00470","repositories_listed":1,"syntology":null},{"url":"/paper/accelerated-and-interpretable-oblique-random","slug":"accelerated-and-interpretable-oblique-random","title":"Accelerated and interpretable oblique random survival forests","date":"2022-08-01","arxiv_id":"2208.01129","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-symbol-grounding-with-complex","slug":"interactive-symbol-grounding-with-complex","title":"Interactive Symbol Grounding with Complex Referential Expressions","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sbert-studies-meaning-representations","slug":"sbert-studies-meaning-representations","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","date":"2022-06-14","arxiv_id":"2206.07023","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/sbert-studies-meaning-representations#ran","syntology_url":"https://syntology.ai/paper/2206.07023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07023"}},"official":{"repos":["flipz357/S3BERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-associative-switchable-and","slug":"investigating-associative-switchable-and","title":"Investigating associative, switchable and negatable Winograd items on renewed French data sets","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/robustlr-evaluating-robustness-to-logical#ran","syntology_url":"https://syntology.ai/paper/2205.12598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12598"}},"official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-question-answer-driven-approach-to-reveal","slug":"a-question-answer-driven-approach-to-reveal","title":"A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations","date":"2022-05-23","arxiv_id":"2205.11467","repositories_listed":1,"syntology":null},{"url":"/paper/flex-feature-logic-embedding-framework-for","slug":"flex-feature-logic-embedding-framework-for","title":"FLEX: Feature-Logic Embedding Framework for CompleX Knowledge Graph Reasoning","date":"2022-05-23","arxiv_id":"2205.11039","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-distributional-hypothesis-let-language","slug":"beyond-distributional-hypothesis-let-language","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","date":"2022-05-08","arxiv_id":"2205.03815","repositories_listed":1,"syntology":null},{"url":"/paper/when-a-sentence-does-not-introduce-a-1","slug":"when-a-sentence-does-not-introduce-a-1","title":"When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it","date":"2022-05-06","arxiv_id":"2205.03472","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-n-grams-induced-by-recurrence","slug":"implicit-n-grams-induced-by-recurrence","title":"Implicit N-grams Induced by Recurrence","date":"2022-05-05","arxiv_id":"2205.02724","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-language-models-evaluating-1","slug":"pre-trained-language-models-evaluating-1","title":"Pre-trained language models evaluating themselves - A comparative study","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learn-to-understand-negation-in-video","slug":"learn-to-understand-negation-in-video","title":"Learn to Understand Negation in Video Retrieval","date":"2022-04-30","arxiv_id":"2205.00132","repositories_listed":1,"syntology":null},{"url":"/paper/developmental-negation-processing-in","slug":"developmental-negation-processing-in","title":"Developmental Negation Processing in Transformer Language Models","date":"2022-04-29","arxiv_id":"2204.14114","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-meaning-representation-for-task","slug":"dialogue-meaning-representation-for-task","title":"Dialogue Meaning Representation for Task-Oriented Dialogue Systems","date":"2022-04-23","arxiv_id":"2204.10989","repositories_listed":1,"syntology":null},{"url":"/paper/learning-disentangled-representations-of-5","slug":"learning-disentangled-representations-of-5","title":"Learning Disentangled Representations of Negation and Uncertainty","date":"2022-04-01","arxiv_id":"2204.00511","repositories_listed":1,"syntology":null}],"syntology_records":32,"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":41,"papers_where_code_ran_first_page":"/task/negation/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":"archive","page":2,"of":7,"url":"/task/negation/papers/2","json":"/task/negation/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/negation/papers/3","json":"/task/negation/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/negation/papers/4","json":"/task/negation/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/negation/papers/5","json":"/task/negation/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/negation/papers/6","json":"/task/negation/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/negation/papers/7","json":"/task/negation/papers/7.json","rows":8},{"order":"ran","page":1,"of":1,"url":"/task/negation/papers/ran/1","json":"/task/negation/papers/ran/1.json","rows":41}],"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":"805ef3cc4dae5f9bc153d348ed416f9523436e5bb20e5756851b79282bc356a3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}