{"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/common-sense-reasoning","name":"Common Sense Reasoning","slug":"common-sense-reasoning","description_markdown":"Common sense reasoning tasks are intended to require the model to go beyond pattern \nrecognition. Instead, the model should use \"common sense\" or world knowledge\nto make inferences.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":939,"papers_with_code":325,"benchmarks":24,"benchmark_tables_in_archive":24,"benchmark_tables_shown":24,"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":56,"subtasks":17,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","slug":"common-sense-reasoning-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":77,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ST-MoE-32B 269B (fine-tuned)","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_url":"/paper/designing-effective-sparse-expert-models","paper_date":"2022-02-17","arxiv_id":"2202.08906","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","slug":"common-sense-reasoning-on-arc-challenge","dataset":"ARC (Challenge)","dataset_url":"/dataset/arc","rows_in_archive":54,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (few-shot, k=25)","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","slug":"common-sense-reasoning-on-arc-easy","dataset":"ARC (Easy)","dataset_url":"/dataset/arc","rows_in_archive":47,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ST-MoE-32B 269B (fine-tuned)","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_url":"/paper/designing-effective-sparse-expert-models","paper_date":"2022-02-17","arxiv_id":"2202.08906","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-record","slug":"common-sense-reasoning-on-record","dataset":"ReCoRD","dataset_url":"/dataset/record","rows_in_archive":45,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","paper_url":"/paper/toward-efficient-language-model-pretraining","paper_date":"2022-12-04","arxiv_id":"2212.01853","code_links":[],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-commonsenseqa","slug":"common-sense-reasoning-on-commonsenseqa","dataset":"CommonsenseQA","dataset_url":"/dataset/commonsenseqa","rows_in_archive":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4o (HPT)","paper_title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","paper_url":"/paper/hierarchical-prompting-taxonomy-a-universal","paper_date":"2024-06-18","arxiv_id":"2406.12644","code_links":[{"title":"devichand579/HPT","url":"https://github.com/devichand579/HPT"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-parus","slug":"common-sense-reasoning-on-parus","dataset":"PARus","dataset_url":"/dataset/parus","rows_in_archive":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Human Benchmark","paper_title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","paper_url":"/paper/russiansuperglue-a-russian-language","paper_date":"2020-10-29","arxiv_id":"2010.15925","code_links":[{"title":"RussianNLP/RussianSuperGLUE","url":"https://github.com/RussianNLP/RussianSuperGLUE"},{"title":"RussianNLP/MOROCCO","url":"https://github.com/RussianNLP/MOROCCO"}],"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":0,"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/russiansuperglue-a-russian-language#ran","syntology_url":"https://syntology.ai/paper/2010.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15925"}},"official":{"repos":["RussianNLP/RussianSuperGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-rucos","slug":"common-sense-reasoning-on-rucos","dataset":"RuCoS","dataset_url":"/dataset/rucos","rows_in_archive":22,"metrics":["Average F1","EM "],"first_row_in_archive_order":{"model":"Human Benchmark","paper_title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","paper_url":"/paper/russiansuperglue-a-russian-language","paper_date":"2020-10-29","arxiv_id":"2010.15925","code_links":[{"title":"RussianNLP/RussianSuperGLUE","url":"https://github.com/RussianNLP/RussianSuperGLUE"},{"title":"RussianNLP/MOROCCO","url":"https://github.com/RussianNLP/MOROCCO"}],"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":0,"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/russiansuperglue-a-russian-language#ran","syntology_url":"https://syntology.ai/paper/2010.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15925"}},"official":{"repos":["RussianNLP/RussianSuperGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-rwsd","slug":"common-sense-reasoning-on-rwsd","dataset":"RWSD","dataset_url":"/dataset/rwsd","rows_in_archive":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Golden Transformer","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench","slug":"common-sense-reasoning-on-big-bench","dataset":"BIG-bench (Disambiguation QA)","dataset_url":"/dataset/big-bench","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot, k=3, Direct)","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-causal","slug":"common-sense-reasoning-on-big-bench-causal","dataset":"BIG-bench (Causal Judgment)","dataset_url":"/dataset/big-bench","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot, k=3, Direct)","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-date","slug":"common-sense-reasoning-on-big-bench-date","dataset":"BIG-bench (Date Understanding)","dataset_url":"/dataset/big-bench","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot, k=3, CoT)","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-sports","slug":"common-sense-reasoning-on-big-bench-sports","dataset":"BIG-bench (Sports Understanding)","dataset_url":"/dataset/big-bench","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2(few-shot, k=3, CoT)","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-event2mind-test","slug":"common-sense-reasoning-on-event2mind-test","dataset":"Event2Mind test","dataset_url":"/dataset/event2mind","rows_in_archive":7,"metrics":["Average Cross-Ent","BLEU"],"first_row_in_archive_order":{"model":"ConvNet","paper_title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","paper_url":"/paper/event2mind-commonsense-inference-on-events","paper_date":"2018-05-17","arxiv_id":"1805.06939","code_links":[],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-russian-event2mind","slug":"common-sense-reasoning-on-russian-event2mind","dataset":"Russian Event2Mind","dataset_url":"/dataset/russian-event2mind","rows_in_archive":7,"metrics":["recall@10"],"first_row_in_archive_order":{"model":"araneum word2vec (skipgram) + GRU","paper_title":"Event2Mind for Russian: Understanding Emotions and Intents in Texts. Corpus and Model for Evaluation","paper_url":"/paper/event2mind-for-russian-understanding-emotions","paper_date":"2020-06-17","arxiv_id":null,"code_links":[{"title":"Alenush/russian_event2mind","url":"https://github.com/Alenush/russian_event2mind"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-swag","slug":"common-sense-reasoning-on-swag","dataset":"SWAG","dataset_url":"/dataset/swag","rows_in_archive":5,"metrics":["Test","Dev"],"first_row_in_archive_order":{"model":"DeBERTalarge","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","paper_url":"/paper/deberta-decoding-enhanced-bert-with","paper_date":"2020-06-05","arxiv_id":"2006.03654","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"microsoft/DeBERTa","url":"https://github.com/microsoft/DeBERTa"},{"title":"osu-nlp-group/mind2web","url":"https://github.com/osu-nlp-group/mind2web"},{"title":"neuralmind-ai/coliee","url":"https://github.com/neuralmind-ai/coliee"},{"title":"huberemanuel/DeBERTa","url":"https://github.com/huberemanuel/DeBERTa"},{"title":"Jason-J-Choi/DeBERTa_TxtClassifier","url":"https://github.com/Jason-J-Choi/DeBERTa_TxtClassifier"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta_v2"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta_v2"},{"title":"JONGWE1/Paddle-DeBERTa","url":"https://github.com/JONGWE1/Paddle-DeBERTa"},{"title":"Mind23-2/MindCode-161","url":"https://github.com/Mind23-2/MindCode-161"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta_v2"}],"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}},"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]}}}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-winowhy","slug":"common-sense-reasoning-on-big-bench-winowhy","dataset":"BIG-bench (Winowhy)","dataset_url":"/dataset/big-bench","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM-540B (few-shot, k=5)","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_url":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_date":"2022-04-05","arxiv_id":"2204.02311","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-known","slug":"common-sense-reasoning-on-big-bench-known","dataset":"BIG-bench (Known Unknowns)","dataset_url":"/dataset/big-bench","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM-540B (few-shot, k=5)","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_url":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_date":"2022-04-05","arxiv_id":"2204.02311","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}}},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-logical","slug":"common-sense-reasoning-on-big-bench-logical","dataset":"BIG-bench (Logical Sequence)","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}}},{"leaderboard":"/sota/common-sense-reasoning-on-event2mind-dev","slug":"common-sense-reasoning-on-event2mind-dev","dataset":"Event2Mind dev","dataset_url":"/dataset/event2mind","rows_in_archive":2,"metrics":["Average Cross-Ent"],"first_row_in_archive_order":{"model":"ConvNet","paper_title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","paper_url":"/paper/event2mind-commonsense-inference-on-events","paper_date":"2018-05-17","arxiv_id":"1805.06939","code_links":[],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-codah","slug":"common-sense-reasoning-on-codah","dataset":"CODAH","dataset_url":"/dataset/codah","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BERT Large","paper_title":"CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense","paper_url":"/paper/aqua-an-adversarially-authored-question","paper_date":"2019-04-08","arxiv_id":"1904.04365","code_links":[{"title":"Websail-NU/AQuA","url":"https://github.com/Websail-NU/AQuA"},{"title":"iit-nlp-research/chatgpt-crawler","url":"https://github.com/iit-nlp-research/chatgpt-crawler"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-crowdsource-qa-1","slug":"common-sense-reasoning-on-crowdsource-qa-1","dataset":"CrowdSource QA","dataset_url":null,"rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"BERT","paper_title":"Predicting Subjective Features of Questions of QA Websites using BERT","paper_url":"/paper/predicting-subjective-features-from-questions","paper_date":"2020-02-24","arxiv_id":"2002.10107","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp"},{"title":"google-research/bert","url":"https://github.com/google-research/bert"},{"title":"graykode/nlp-tutorial","url":"https://github.com/graykode/nlp-tutorial"},{"title":"Moradnejad/Predicting-Subjective-Features-on-QA-Websites","url":"https://github.com/Moradnejad/Predicting-Subjective-Features-on-QA-Websites"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-visual-dialog-v0-9","slug":"common-sense-reasoning-on-visual-dialog-v0-9","dataset":"Visual Dialog v0.9","dataset_url":"/dataset/visdial","rows_in_archive":1,"metrics":["1 in 10 R@5"],"first_row_in_archive_order":{"model":"NMN [kottur2018visual]","paper_title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","paper_url":"/paper/visual-coreference-resolution-in-visual","paper_date":"2018-09-06","arxiv_id":"1809.01816","code_links":[{"title":"facebookresearch/corefnmn","url":"https://github.com/facebookresearch/corefnmn"}],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-visual-dialog-v09","slug":"common-sense-reasoning-on-visual-dialog-v09","dataset":"Visual Dialog  v0.9","dataset_url":"/dataset/visdial","rows_in_archive":1,"metrics":["1 in 10 R@5","Recall@10"],"first_row_in_archive_order":{"model":"PDUN","paper_title":"Probabilistic framework for solving Visual Dialog","paper_url":"/paper/probabilistic-framework-for-solving-visual","paper_date":"2019-09-11","arxiv_id":"1909.04800","code_links":[],"syntology":null}},{"leaderboard":"/sota/common-sense-reasoning-on-winogavil","slug":"common-sense-reasoning-on-winogavil","dataset":"WinoGAViL","dataset_url":"/dataset/winogavil","rows_in_archive":1,"metrics":["Jaccard Index"],"first_row_in_archive_order":{"model":"ViLT","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","paper_url":"/paper/winogavil-gamified-association-benchmark-to","paper_date":"2022-07-25","arxiv_id":"2207.12576","code_links":[{"title":"winogavil/winogavil-experiments","url":"https://github.com/winogavil/winogavil-experiments"}],"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/winogavil-gamified-association-benchmark-to#ran","syntology_url":"https://syntology.ai/paper/2207.12576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12576"}},"official":{"repos":["winogavil/winogavil-experiments"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703},{"url":"/dataset/commonsenseqa","name":"CommonsenseQA","full_name":"CSQA","num_papers_in_archive":483},{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/arc","name":"ARC (AI2 Reasoning Challenge)","full_name":"","num_papers_in_archive":178},{"url":"/dataset/swag","name":"SWAG","full_name":"Situations With Adversarial Generations","num_papers_in_archive":163},{"url":"/dataset/visdial","name":"VisDial","full_name":"Visual Dialog","num_papers_in_archive":159},{"url":"/dataset/record","name":"ReCoRD","full_name":"ReCoRD","num_papers_in_archive":111},{"url":"/dataset/cos-e","name":"CoS-E","full_name":"Commonsense Explanations Dataset","num_papers_in_archive":46},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/phyre","name":"PHYRE","full_name":"PHYsical REasoning","num_papers_in_archive":35},{"url":"/dataset/creak","name":"CREAK","full_name":"","num_papers_in_archive":30},{"url":"/dataset/codah","name":"CODAH","full_name":"COmmonsense Dataset Adversarially-authored by Humans","num_papers_in_archive":29},{"url":"/dataset/onestopenglish","name":"OneStopEnglish","full_name":"","num_papers_in_archive":29},{"url":"/dataset/xstorycloze","name":"XStoryCloze","full_name":"","num_papers_in_archive":26},{"url":"/dataset/mcscript","name":"MCScript","full_name":"MCScript","num_papers_in_archive":24},{"url":"/dataset/moral-stories","name":"Moral Stories","full_name":"","num_papers_in_archive":24},{"url":"/dataset/recipeqa","name":"RecipeQA","full_name":"","num_papers_in_archive":24},{"url":"/dataset/riddle-sense","name":"RiddleSense","full_name":"","num_papers_in_archive":23},{"url":"/dataset/event2mind","name":"Event2Mind","full_name":"","num_papers_in_archive":21},{"url":"/dataset/x-csqa","name":"X-CSQA","full_name":"","num_papers_in_archive":18},{"url":"/dataset/stepgame","name":"StepGame","full_name":"StepGame","num_papers_in_archive":15},{"url":"/dataset/whoops","name":"WHOOPS!","full_name":"","num_papers_in_archive":14},{"url":"/dataset/com2sense","name":"Com2Sense","full_name":"Complementary Commonsense","num_papers_in_archive":11},{"url":"/dataset/housekeep","name":"Housekeep","full_name":"","num_papers_in_archive":11},{"url":"/dataset/protoqa","name":"ProtoQA","full_name":null,"num_papers_in_archive":11},{"url":"/dataset/timedial","name":"TimeDial","full_name":"","num_papers_in_archive":11},{"url":"/dataset/cc-stories","name":"CC-Stories","full_name":"CC-Stories","num_papers_in_archive":10},{"url":"/dataset/criticbench","name":"CriticBench","full_name":"","num_papers_in_archive":10},{"url":"/dataset/fig-qa","name":"Fig-QA","full_name":"","num_papers_in_archive":10},{"url":"/dataset/rainbow","name":"Rainbow","full_name":"","num_papers_in_archive":10},{"url":"/dataset/parus","name":"PARus","full_name":"Choice of Plausible Alternatives for Russian language","num_papers_in_archive":7},{"url":"/dataset/rwsd","name":"RWSD","full_name":"The Winograd Schema Challenge (Russian)","num_papers_in_archive":7},{"url":"/dataset/cite","name":"CITE","full_name":"","num_papers_in_archive":6},{"url":"/dataset/omics","name":"OMICS","full_name":"Open Mind Indoor Common Sense","num_papers_in_archive":6},{"url":"/dataset/smart-101","name":"SMART-101","full_name":"Simple Multimodal Algorithmic Reasoning Task Dataset","num_papers_in_archive":6},{"url":"/dataset/numersense","name":"NumerSense","full_name":"","num_papers_in_archive":5},{"url":"/dataset/rucos","name":"RuCoS","full_name":"Russian Reading Comprehension with Commonsense Reasoning","num_papers_in_archive":5},{"url":"/dataset/sarcasm-corpus-v2","name":"Sarcasm Corpus V2","full_name":"","num_papers_in_archive":5},{"url":"/dataset/winogavil","name":"WinoGAViL","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mindgames","name":"Mindgames","full_name":"","num_papers_in_archive":4},{"url":"/dataset/bcopa-ce","name":"BCOPA-CE","full_name":"A Balanced COPA Test Set with cause-effect as alternatives","num_papers_in_archive":3},{"url":"/dataset/pacs-commonsense","name":"Physical Audiovisual CommonSense","full_name":"","num_papers_in_archive":3},{"url":"/dataset/chegeka","name":"CheGeKa","full_name":"CheGeKa","num_papers_in_archive":2},{"url":"/dataset/cofar","name":"COFAR","full_name":"Commonsense and Factual Reasoning in Image Search","num_papers_in_archive":2},{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","num_papers_in_archive":2},{"url":"/dataset/machine-number-sense","name":"Machine Number Sense","full_name":"","num_papers_in_archive":2},{"url":"/dataset/qure","name":"QuRe","full_name":"","num_papers_in_archive":2},{"url":"/dataset/situation-puzzle","name":"Situation Puzzle","full_name":"","num_papers_in_archive":2},{"url":"/dataset/accord-csqa-0-5","name":"ACCORD CSQA 0-5","full_name":"","num_papers_in_archive":1},{"url":"/dataset/advice-seeking-questions","name":"Advice Seeking Questions","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/discosense","name":"DiscoSense","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dpgmedia2019","name":"DpgMedia2019","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/russian-event2mind","name":"Russian Event2Mind","full_name":"","num_papers_in_archive":1},{"url":"/dataset/this-is-not-a-dataset","name":"This is not a Dataset","full_name":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","num_papers_in_archive":1},{"url":"/dataset/winograd-automatic","name":"Winograd Automatic","full_name":"Winograd","num_papers_in_archive":1},{"url":"/dataset/cvr-tasks","name":"Compositional Visual Reasoning (CVR)","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/anachronisms","name":"Anachronisms"},{"url":"/task/causal-judgment","name":"Causal Judgment"},{"url":"/task/crash-blossom","name":"Crash Blossom"},{"url":"/task/crass-ai","name":"Crass AI"},{"url":"/task/disambiguation-qa","name":"Disambiguation QA"},{"url":"/task/discourse-marker-prediction","name":"Discourse Marker Prediction"},{"url":"/task/empirical-judgments","name":"Empirical Judgments"},{"url":"/task/hellaswag","name":"HellaSwag"},{"url":"/task/irony-identification","name":"Irony Identification"},{"url":"/task/multiview-contextual-commonsense-inference","name":"Multiview Contextual Commonsense Inference"},{"url":"/task/physical-commonsense-reasoning","name":"Physical Commonsense Reasoning"},{"url":"/task/riddle-sense","name":"Riddle Sense"},{"url":"/task/timedial","name":"Timedial"},{"url":"/task/understanding-fables","name":"Understanding Fables"},{"url":"/task/visual-commonsense-tests","name":"Visual Commonsense Tests"},{"url":"/task/winogrande","name":"Winogrande"},{"url":"/task/winowhy","name":"Winowhy"}],"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":10,"rows_per_page":100,"shown":100,"of":939,"of_with_code":325,"tagged_in_all":939,"counts":{"archive_papers_tagged":939,"with_a_code_link":325,"where_syntology_ran_a_sample":114,"not_listed_spam_title":0,"listed":939,"listed_where_code_ran":114,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":95,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":95,"listed_every_run_a_failure_of_syntologys_instrument":19,"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/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","repositories_listed":534,"syntology":{"n":659,"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_honours":18,"n_violates":5,"n_no_contract":211,"n_pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}},"official":{"repos":["google-research/bert"],"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/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_honours":3,"n_violates":2,"n_no_contract":32,"n_pointer_only":7,"phrase":"45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}},"official":{"repos":["openai/gpt-3"],"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/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":37,"n_constructed":11,"n_ran_checked":36,"n_instrument":1,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":34,"n_pointer_only":24,"phrase":"37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}},"official":{"repos":["pytorch/fairseq"],"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/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_honours":3,"n_violates":0,"n_no_contract":22,"n_pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}},"official":{"repos":["facebookresearch/llama"],"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/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","repositories_listed":57,"syntology":{"n":31,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}},"official":null}},{"url":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","repositories_listed":48,"syntology":{"n":126,"n_ran":81,"n_constructed":17,"n_ran_checked":56,"n_instrument":25,"n_unverified":45,"n_honours":4,"n_violates":0,"n_no_contract":52,"n_pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}},"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mamba-linear-time-sequence-modeling-with","slug":"mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","repositories_listed":35,"syntology":{"n":62,"n_ran":28,"n_constructed":7,"n_ran_checked":20,"n_instrument":8,"n_unverified":34,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":29,"phrase":"28 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 34 unverified","sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}},"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"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/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","repositories_listed":19,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-thought-prompting-elicits-reasoning#ran","syntology_url":"https://syntology.ai/paper/2201.11903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11903"}},"official":null}},{"url":"/paper/a-neural-conversational-model","slug":"a-neural-conversational-model","title":"A Neural Conversational Model","date":"2015-06-19","arxiv_id":"1506.05869","repositories_listed":18,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/a-neural-conversational-model#ran","syntology_url":"https://syntology.ai/paper/1506.05869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.05869"}},"official":null}},{"url":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}},"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]}}},{"url":"/paper/awq-activation-aware-weight-quantization-for","slug":"awq-activation-aware-weight-quantization-for","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","date":"2023-06-01","arxiv_id":"2306.00978","repositories_listed":12,"syntology":{"n":18,"n_ran":16,"n_constructed":1,"n_ran_checked":6,"n_instrument":10,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"16 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/awq-activation-aware-weight-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2306.00978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00978"}},"official":{"repos":["internlm/lmdeploy","mit-han-lab/llm-awq","nvidia/tensorrt-llm","vllm-project/vllm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"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/winogrande-an-adversarial-winograd-schema","slug":"winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","date":"2019-07-24","arxiv_id":"1907.10641","repositories_listed":10,"syntology":null},{"url":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","repositories_listed":9,"syntology":{"n":10,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 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) · 7 unverified","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}},"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","repositories_listed":8,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}},"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/mt5-a-massively-multilingual-pre-trained-text","slug":"mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","date":"2020-10-22","arxiv_id":"2010.11934","repositories_listed":8,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mt5-a-massively-multilingual-pre-trained-text#ran","syntology_url":"https://syntology.ai/paper/2010.11934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11934"}},"official":{"repos":["google-research/multilingual-t5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}},{"url":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"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":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) · 2 unverified","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}},"official":{"repos":["qwenlm/qwen2.5"],"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/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}},"official":null}},{"url":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/massive-language-models-can-be-accurately","slug":"massive-language-models-can-be-accurately","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","date":"2023-01-02","arxiv_id":"2301.00774","repositories_listed":6,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"9 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}},"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/beyond-the-imitation-game-quantifying-and","slug":"beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","repositories_listed":6,"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/beyond-the-imitation-game-quantifying-and#ran","syntology_url":"https://syntology.ai/paper/2206.04615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04615"}},"official":{"repos":["google/BIG-bench"],"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/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/temporal-relational-reasoning-in-videos","slug":"temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","arxiv_id":"1711.08496","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/temporal-relational-reasoning-in-videos#ran","syntology_url":"https://syntology.ai/paper/1711.08496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.08496"}},"official":null}},{"url":"/paper/the-something-something-video-database-for","slug":"the-something-something-video-database-for","title":"The \"something something\" video database for learning and evaluating visual common sense","date":"2017-06-13","arxiv_id":"1706.04261","repositories_listed":5,"syntology":null},{"url":"/paper/gated-delta-networks-improving-mamba2-with","slug":"gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","arxiv_id":"2412.06464","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gated-delta-networks-improving-mamba2-with#ran","syntology_url":"https://syntology.ai/paper/2412.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06464"}},"official":{"repos":["NVlabs/GatedDeltaNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/smart-agent-based-modeling-on-the-use-of","slug":"smart-agent-based-modeling-on-the-use-of","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","date":"2023-11-10","arxiv_id":"2311.06330","repositories_listed":4,"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":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) · 0 unverified","sample_list":"/paper/smart-agent-based-modeling-on-the-use-of#ran","syntology_url":"https://syntology.ai/paper/2311.06330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06330"}},"official":{"repos":["roihn/sabm"],"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/pythia-a-suite-for-analyzing-large-language","slug":"pythia-a-suite-for-analyzing-large-language","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","date":"2023-04-03","arxiv_id":"2304.01373","repositories_listed":4,"syntology":null},{"url":"/paper/large-language-models-are-zero-shot-reasoners","slug":"large-language-models-are-zero-shot-reasoners","title":"Large Language Models are Zero-Shot Reasoners","date":"2022-05-24","arxiv_id":"2205.11916","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}},"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/image-generation-from-small-datasets-via","slug":"image-generation-from-small-datasets-via","title":"Image Generation From Small Datasets via Batch Statistics Adaptation","date":"2019-04-03","arxiv_id":"1904.01774","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/image-generation-from-small-datasets-via#ran","syntology_url":"https://syntology.ai/paper/1904.01774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01774"}},"official":{"repos":["nogu-atsu/small-dataset-image-generation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fake-news-detection-on-social-media-using","slug":"fake-news-detection-on-social-media-using","title":"Fake News Detection on Social Media using Geometric Deep Learning","date":"2019-02-10","arxiv_id":"1902.06673","repositories_listed":4,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"10 ran (of which 0 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) · 2 unverified","sample_list":"/paper/fake-news-detection-on-social-media-using#ran","syntology_url":"https://syntology.ai/paper/1902.06673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06673"}},"official":null}},{"url":"/paper/commonsenseqa-a-question-answering-challenge","slug":"commonsenseqa-a-question-answering-challenge","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","date":"2018-11-02","arxiv_id":"1811.00937","repositories_listed":4,"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/commonsenseqa-a-question-answering-challenge#ran","syntology_url":"https://syntology.ai/paper/1811.00937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00937"}},"official":{"repos":["jonathanherzig/commonsenseqa"],"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/dkn-deep-knowledge-aware-network-for-news","slug":"dkn-deep-knowledge-aware-network-for-news","title":"DKN: Deep Knowledge-Aware Network for News Recommendation","date":"2018-01-25","arxiv_id":"1801.08284","repositories_listed":4,"syntology":null},{"url":"/paper/knowledge-fusion-of-large-language-models","slug":"knowledge-fusion-of-large-language-models","title":"Knowledge Fusion of Large Language Models","date":"2024-01-19","arxiv_id":"2401.10491","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/knowledge-fusion-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.10491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10491"}},"official":{"repos":["fanqiwan/fusellm"],"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/pointllm-empowering-large-language-models-to","slug":"pointllm-empowering-large-language-models-to","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","date":"2023-08-31","arxiv_id":"2308.16911","repositories_listed":3,"syntology":null},{"url":"/paper/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}},"official":{"repos":["jshilong/gpt4roi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"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/commongen-a-constrained-text-generation","slug":"commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","date":"2019-11-09","arxiv_id":"1911.03705","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/commongen-a-constrained-text-generation#ran","syntology_url":"https://syntology.ai/paper/1911.03705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03705"}},"official":null}},{"url":"/paper/a-hybrid-neural-network-model-for-commonsense","slug":"a-hybrid-neural-network-model-for-commonsense","title":"A Hybrid Neural Network Model for Commonsense Reasoning","date":"2019-07-27","arxiv_id":"1907.11983","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/pair2vec-compositional-word-pair-embeddings","slug":"pair2vec-compositional-word-pair-embeddings","title":"pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference","date":"2018-10-20","arxiv_id":"1810.08854","repositories_listed":3,"syntology":null},{"url":"/paper/relational-neural-expectation-maximization","slug":"relational-neural-expectation-maximization","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","date":"2018-02-28","arxiv_id":"1802.10353","repositories_listed":3,"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/relational-neural-expectation-maximization#ran","syntology_url":"https://syntology.ai/paper/1802.10353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10353"}},"official":{"repos":["sjoerdvansteenkiste/Relational-NEM"],"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/the-argument-reasoning-comprehension-task","slug":"the-argument-reasoning-comprehension-task","title":"The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants","date":"2017-08-04","arxiv_id":"1708.01425","repositories_listed":3,"syntology":null},{"url":"/paper/wise-a-world-knowledge-informed-semantic","slug":"wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","date":"2025-03-10","arxiv_id":"2503.07265","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/wise-a-world-knowledge-informed-semantic#ran","syntology_url":"https://syntology.ai/paper/2503.07265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07265"}},"official":{"repos":["pku-yuangroup/wise"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"12 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domainrag-a-chinese-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.05654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05654"}},"official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/buffer-of-thoughts-thought-augmented","slug":"buffer-of-thoughts-thought-augmented","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","date":"2024-06-06","arxiv_id":"2406.04271","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 1 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) · 1 unverified","sample_list":"/paper/buffer-of-thoughts-thought-augmented#ran","syntology_url":"https://syntology.ai/paper/2406.04271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04271"}},"official":{"repos":["yangling0818/buffer-of-thought-llm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/alice-in-wonderland-simple-tasks-showing","slug":"alice-in-wonderland-simple-tasks-showing","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","date":"2024-06-04","arxiv_id":"2406.02061","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/alice-in-wonderland-simple-tasks-showing#ran","syntology_url":"https://syntology.ai/paper/2406.02061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02061"}},"official":{"repos":["laion-ai/aiw"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}},"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-spatial-proximity-reasoning-for","slug":"hierarchical-spatial-proximity-reasoning-for","title":"Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation","date":"2024-03-18","arxiv_id":"2403.11541","repositories_listed":2,"syntology":null},{"url":"/paper/g-retriever-retrieval-augmented-generation","slug":"g-retriever-retrieval-augmented-generation","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","date":"2024-02-12","arxiv_id":"2402.07630","repositories_listed":2,"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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/g-retriever-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2402.07630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07630"}},"official":{"repos":["xiaoxinhe/g-retriever"],"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/parameter-efficient-sparsity-crafting-from","slug":"parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/dilu-a-knowledge-driven-approach-to","slug":"dilu-a-knowledge-driven-approach-to","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","date":"2023-09-28","arxiv_id":"2309.16292","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dilu-a-knowledge-driven-approach-to#ran","syntology_url":"https://syntology.ai/paper/2309.16292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16292"}},"official":{"repos":["PJLab-ADG/DiLu"],"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":["listed","official"]}}},{"url":"/paper/omniquant-omnidirectionally-calibrated","slug":"omniquant-omnidirectionally-calibrated","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","date":"2023-08-25","arxiv_id":"2308.13137","repositories_listed":2,"syntology":{"n":16,"n_ran":10,"n_constructed":1,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/omniquant-omnidirectionally-calibrated#ran","syntology_url":"https://syntology.ai/paper/2308.13137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13137"}},"official":{"repos":["opengvlab/omniquant"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-populating-generalizable-engineering","slug":"towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-driven-robot-program-synthesis-from","slug":"knowledge-driven-robot-program-synthesis-from","title":"Knowledge-Driven Robot Program Synthesis from Human VR Demonstrations","date":"2023-06-05","arxiv_id":"2306.02739","repositories_listed":2,"syntology":null},{"url":"/paper/llm-grounded-diffusion-enhancing-prompt","slug":"llm-grounded-diffusion-enhancing-prompt","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","date":"2023-05-23","arxiv_id":"2305.13655","repositories_listed":2,"syntology":null},{"url":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","repositories_listed":2,"syntology":null},{"url":"/paper/reasoning-implicit-sentiment-with-chain-of","slug":"reasoning-implicit-sentiment-with-chain-of","title":"Reasoning Implicit Sentiment with Chain-of-Thought Prompting","date":"2023-05-18","arxiv_id":"2305.11255","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reasoning-implicit-sentiment-with-chain-of#ran","syntology_url":"https://syntology.ai/paper/2305.11255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11255"}},"official":{"repos":["scofield7419/thor-isa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ar-diffusion-auto-regressive-diffusion-model-1","slug":"ar-diffusion-auto-regressive-diffusion-model-1","title":"AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation","date":"2023-05-16","arxiv_id":"2305.09515","repositories_listed":2,"syntology":null},{"url":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","repositories_listed":2,"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":3,"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/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}},"official":{"repos":["joeljang/elm"],"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","unlocated"]}}},{"url":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","repositories_listed":2,"syntology":null},{"url":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","repositories_listed":2,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 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; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deep-bidirectional-language-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2210.09338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09338"}},"official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/textworldexpress-simulating-text-games-at-one","slug":"textworldexpress-simulating-text-games-at-one","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","date":"2022-08-01","arxiv_id":"2208.01174","repositories_listed":2,"syntology":null},{"url":"/paper/n-grammer-augmenting-transformers-with-latent-1","slug":"n-grammer-augmenting-transformers-with-latent-1","title":"N-Grammer: Augmenting Transformers with latent n-grams","date":"2022-07-13","arxiv_id":"2207.06366","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/n-grammer-augmenting-transformers-with-latent-1#ran","syntology_url":"https://syntology.ai/paper/2207.06366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06366"}},"official":{"repos":["tensorflow/lingvo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-label-classification-with-high-rank-and","slug":"multi-label-classification-with-high-rank-and","title":"Multi-label Classification with High-rank and High-order Label Correlations","date":"2022-07-09","arxiv_id":"2207.04197","repositories_listed":2,"syntology":null},{"url":"/paper/planbench-an-extensible-benchmark-for","slug":"planbench-an-extensible-benchmark-for","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","date":"2022-06-21","arxiv_id":"2206.10498","repositories_listed":2,"syntology":null},{"url":"/paper/intermediate-training-on-question-answering","slug":"intermediate-training-on-question-answering","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","date":"2022-05-25","arxiv_id":"2205.12604","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","repositories_listed":2,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}},"official":{"repos":["google-research/google-research"],"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/learning-to-detect-mobile-objects-from-lidar","slug":"learning-to-detect-mobile-objects-from-lidar","title":"Learning to Detect Mobile Objects from LiDAR Scans Without Labels","date":"2022-03-29","arxiv_id":"2203.15882","repositories_listed":2,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":0,"n_honours":5,"n_violates":3,"n_no_contract":5,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 5 honoured, 3 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-detect-mobile-objects-from-lidar#ran","syntology_url":"https://syntology.ai/paper/2203.15882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15882"}},"official":{"repos":["yurongyou/modest"],"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":["listed","official"]}}},{"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/the-web-is-your-oyster-knowledge-intensive","slug":"the-web-is-your-oyster-knowledge-intensive","title":"The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web Corpus","date":"2021-12-18","arxiv_id":"2112.09924","repositories_listed":2,"syntology":null},{"url":"/paper/human-parity-on-commonsenseqa-augmenting-self","slug":"human-parity-on-commonsenseqa-augmenting-self","title":"Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention","date":"2021-12-06","arxiv_id":"2112.03254","repositories_listed":2,"syntology":null},{"url":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","repositories_listed":2,"syntology":null},{"url":"/paper/fusing-context-into-knowledge-graph-for","slug":"fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","repositories_listed":2,"syntology":null},{"url":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/russiansuperglue-a-russian-language","slug":"russiansuperglue-a-russian-language","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","date":"2020-10-29","arxiv_id":"2010.15925","repositories_listed":2,"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":0,"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/russiansuperglue-a-russian-language#ran","syntology_url":"https://syntology.ai/paper/2010.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15925"}},"official":{"repos":["RussianNLP/RussianSuperGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-based-rl-agents-with-commonsense","slug":"text-based-rl-agents-with-commonsense","title":"Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines","date":"2020-10-08","arxiv_id":"2010.03790","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/text-based-rl-agents-with-commonsense#ran","syntology_url":"https://syntology.ai/paper/2010.03790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03790"}},"official":{"repos":["IBM/commonsense-rl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/perceiving-3d-human-object-spatial","slug":"perceiving-3d-human-object-spatial","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","date":"2020-07-30","arxiv_id":"2007.15649","repositories_listed":2,"syntology":null},{"url":"/paper/the-sensitivity-of-language-models-and-humans","slug":"the-sensitivity-of-language-models-and-humans","title":"The Sensitivity of Language Models and Humans to Winograd Schema Perturbations","date":"2020-05-04","arxiv_id":"2005.01348","repositories_listed":2,"syntology":null},{"url":"/paper/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}},"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/piqa-reasoning-about-physical-commonsense-in","slug":"piqa-reasoning-about-physical-commonsense-in","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","date":"2019-11-26","arxiv_id":"1911.11641","repositories_listed":2,"syntology":null},{"url":"/paper/kagnet-knowledge-aware-graph-networks-for","slug":"kagnet-knowledge-aware-graph-networks-for","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","date":"2019-09-04","arxiv_id":"1909.02151","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kagnet-knowledge-aware-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1909.02151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02151"}},"official":{"repos":["INK-USC/KagNet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/190600363","slug":"190600363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","date":"2019-06-02","arxiv_id":"1906.00363","repositories_listed":2,"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/190600363#ran","syntology_url":"https://syntology.ai/paper/1906.00363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00363"}},"official":{"repos":["wangcunxiang/Sen-Making-and-Explanation"],"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/a-surprisingly-robust-trick-for-winograd","slug":"a-surprisingly-robust-trick-for-winograd","title":"A Surprisingly Robust Trick for Winograd Schema Challenge","date":"2019-05-15","arxiv_id":"1905.06290","repositories_listed":2,"syntology":null},{"url":"/paper/aqua-an-adversarially-authored-question","slug":"aqua-an-adversarially-authored-question","title":"CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense","date":"2019-04-08","arxiv_id":"1904.04365","repositories_listed":2,"syntology":null},{"url":"/paper/compositional-language-understanding-with","slug":"compositional-language-understanding-with","title":"Compositional Language Understanding with Text-based Relational Reasoning","date":"2018-11-07","arxiv_id":"1811.02959","repositories_listed":2,"syntology":null},{"url":"/paper/a-simple-method-for-commonsense-reasoning","slug":"a-simple-method-for-commonsense-reasoning","title":"A Simple Method for Commonsense Reasoning","date":"2018-06-07","arxiv_id":"1806.02847","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 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) · 3 unverified","sample_list":"/paper/a-simple-method-for-commonsense-reasoning#ran","syntology_url":"https://syntology.ai/paper/1806.02847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02847"}},"official":null}},{"url":"/paper/unsupervised-learning-from-continuous-video","slug":"unsupervised-learning-from-continuous-video","title":"Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network","date":"2016-07-22","arxiv_id":"1607.06854","repositories_listed":2,"syntology":null},{"url":"/paper/losia-efficient-high-rank-fine-tuning-via","slug":"losia-efficient-high-rank-fine-tuning-via","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","date":"2025-07-06","arxiv_id":"2507.04487","repositories_listed":1,"syntology":null},{"url":"/paper/prime-the-search-using-large-language-models","slug":"prime-the-search-using-large-language-models","title":"Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search","date":"2025-06-08","arxiv_id":"2506.07062","repositories_listed":1,"syntology":null},{"url":"/paper/ambik-dataset-of-ambiguous-tasks-in-kitchen","slug":"ambik-dataset-of-ambiguous-tasks-in-kitchen","title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","date":"2025-06-04","arxiv_id":"2506.04089","repositories_listed":1,"syntology":null},{"url":"/paper/3d-visual-illusion-depth-estimation","slug":"3d-visual-illusion-depth-estimation","title":"3D Visual Illusion Depth Estimation","date":"2025-05-19","arxiv_id":"2505.13061","repositories_listed":1,"syntology":null},{"url":"/paper/videohallu-evaluating-and-mitigating-multi","slug":"videohallu-evaluating-and-mitigating-multi","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","date":"2025-05-02","arxiv_id":"2505.01481","repositories_listed":1,"syntology":null},{"url":"/paper/chexworld-exploring-image-world-modeling-for","slug":"chexworld-exploring-image-world-modeling-for","title":"CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning","date":"2025-04-18","arxiv_id":"2504.13820","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chexworld-exploring-image-world-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2504.13820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13820"}},"official":{"repos":["LeapLabTHU/CheXWorld"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flip-reasoning-challenge","slug":"flip-reasoning-challenge","title":"FLIP Reasoning Challenge","date":"2025-04-16","arxiv_id":"2504.12256","repositories_listed":1,"syntology":null},{"url":"/paper/what-the-hellaswag-on-the-validity-of-common","slug":"what-the-hellaswag-on-the-validity-of-common","title":"What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks","date":"2025-04-10","arxiv_id":"2504.07825","repositories_listed":1,"syntology":null},{"url":"/paper/dynmole-boosting-mixture-of-lora-experts-fine","slug":"dynmole-boosting-mixture-of-lora-experts-fine","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","date":"2025-04-01","arxiv_id":"2504.00661","repositories_listed":1,"syntology":null},{"url":"/paper/information-gain-is-not-all-you-need","slug":"information-gain-is-not-all-you-need","title":"Information Gain Is Not All You Need","date":"2025-03-28","arxiv_id":"2504.01980","repositories_listed":1,"syntology":null}],"syntology_records":57,"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":60,"papers_placed":3,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","since_archive":"/sota/common-sense-reasoning-on-winogrande#since-judged","papers_judged":31,"placed":1},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","since_archive":"/sota/common-sense-reasoning-on-arc-challenge#since-judged","papers_judged":21,"placed":0},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","since_archive":"/sota/common-sense-reasoning-on-arc-easy#since-judged","papers_judged":17,"placed":0},{"leaderboard":"/sota/common-sense-reasoning-on-commonsenseqa","since_archive":"/sota/common-sense-reasoning-on-commonsenseqa#since-judged","papers_judged":16,"placed":2},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-causal","since_archive":"/sota/common-sense-reasoning-on-big-bench-causal#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/common-sense-reasoning-on-swag","since_archive":"/sota/common-sense-reasoning-on-swag#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":114,"papers_where_code_ran_first_page":"/task/common-sense-reasoning/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":10,"url":"/task/common-sense-reasoning/papers/2","json":"/task/common-sense-reasoning/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/common-sense-reasoning/papers/3","json":"/task/common-sense-reasoning/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/common-sense-reasoning/papers/4","json":"/task/common-sense-reasoning/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/common-sense-reasoning/papers/5","json":"/task/common-sense-reasoning/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/common-sense-reasoning/papers/6","json":"/task/common-sense-reasoning/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/common-sense-reasoning/papers/7","json":"/task/common-sense-reasoning/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/common-sense-reasoning/papers/8","json":"/task/common-sense-reasoning/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/common-sense-reasoning/papers/9","json":"/task/common-sense-reasoning/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/common-sense-reasoning/papers/10","json":"/task/common-sense-reasoning/papers/10.json","rows":39},{"order":"ran","page":1,"of":2,"url":"/task/common-sense-reasoning/papers/ran/1","json":"/task/common-sense-reasoning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/common-sense-reasoning/papers/ran/2","json":"/task/common-sense-reasoning/papers/ran/2.json","rows":14}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"af0fcd17ce9659a2e41f7e359d39e38f9f7599d0f7bb55cfc2a3f6bfd50695f4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}