{"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/fact-checking","name":"Fact Checking","slug":"fact-checking","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":669,"papers_with_code":297,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":12,"subtasks":5,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/fact-checking-on-scifact-beir","slug":"fact-checking-on-scifact-beir","dataset":"SciFact (BEIR)","dataset_url":"/dataset/beir","rows_in_archive":5,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper_title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","paper_url":"/paper/no-parameter-left-behind-how-distillation-and","paper_date":"2022-06-06","arxiv_id":"2206.02873","code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}],"syntology":null}},{"leaderboard":"/sota/fact-checking-on-climate-fever-beir","slug":"fact-checking-on-climate-fever-beir","dataset":"CLIMATE-FEVER (BEIR)","dataset_url":"/dataset/beir","rows_in_archive":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-BE-5.8B","paper_title":"SGPT: GPT Sentence Embeddings for Semantic Search","paper_url":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","paper_date":"2022-02-17","arxiv_id":"2202.08904","code_links":[{"title":"muennighoff/sgpt","url":"https://github.com/muennighoff/sgpt"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sgpt-gpt-sentence-embeddings-for-semantic#ran","syntology_url":"https://syntology.ai/paper/2202.08904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08904"}},"official":{"repos":["muennighoff/sgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/fact-checking-on-fever-beir","slug":"fact-checking-on-fever-beir","dataset":"FEVER (BEIR)","dataset_url":"/dataset/beir","rows_in_archive":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper_title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","paper_url":"/paper/no-parameter-left-behind-how-distillation-and","paper_date":"2022-06-06","arxiv_id":"2206.02873","code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}],"syntology":null}},{"leaderboard":"/sota/fact-checking-on-averitec","slug":"fact-checking-on-averitec","dataset":"AVeriTeC","dataset_url":"/dataset/averitec","rows_in_archive":3,"metrics":["Question Only score","Question + Answer score","AveriTeC"],"first_row_in_archive_order":{"model":"HerO","paper_title":"HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims","paper_url":"/paper/hero-at-averitec-the-herd-of-open-large","paper_date":"2024-10-16","arxiv_id":"2410.12377","code_links":[{"title":"ssu-humane/hero","url":"https://github.com/ssu-humane/hero"}],"syntology":null}},{"leaderboard":"/sota/fact-checking-on","slug":"fact-checking-on","dataset":"^(#$!@#$)(()))******","dataset_url":null,"rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"Abc","paper_title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","paper_url":"/paper/minicheck-efficient-fact-checking-of-llms-on","paper_date":"2024-04-16","arxiv_id":"2404.10774","code_links":[{"title":"vectara/hallucination-leaderboard","url":"https://github.com/vectara/hallucination-leaderboard"},{"title":"liyan06/minicheck","url":"https://github.com/liyan06/minicheck"}],"syntology":{"n":8,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/minicheck-efficient-fact-checking-of-llms-on#ran","syntology_url":"https://syntology.ai/paper/2404.10774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10774"}},"official":{"repos":["liyan06/minicheck"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/fact-checking-on-cdcd","slug":"fact-checking-on-cdcd","dataset":"CDCD","dataset_url":null,"rows_in_archive":1,"metrics":["Precision","Recall"],"first_row_in_archive_order":{"model":"MA-CIN","paper_title":"Self-Supervised Claim Identification for Automated Fact Checking","paper_url":"/paper/self-supervised-claim-identification-for","paper_date":"2021-02-03","arxiv_id":"2102.02335","code_links":[{"title":"architapathak/Self-Supervised-ClaimIdentification","url":"https://github.com/architapathak/Self-Supervised-ClaimIdentification"}],"syntology":null}},{"leaderboard":"/sota/fact-checking-on-liar2","slug":"fact-checking-on-liar2","dataset":"LIAR2","dataset_url":"/dataset/liar2","rows_in_archive":1,"metrics":["Accuracy (Test)","F1-Macro (Test)","F1-Micro (Test)"],"first_row_in_archive_order":{"model":"FDHN","paper_title":"An Enhanced Fake News Detection System With Fuzzy Deep Learning","paper_url":"/paper/an-enhanced-fake-news-detection-system-with","paper_date":"2024-06-24","arxiv_id":null,"code_links":[{"title":"chengxuphd/liar2","url":"https://github.com/chengxuphd/liar2"}],"syntology":null}}],"datasets":[{"url":"/dataset/beir","name":"BEIR","full_name":"Benchmarking IR","num_papers_in_archive":311},{"url":"/dataset/vitaminc","name":"VitaminC","full_name":"Fact Verification with Contrastive Evidence","num_papers_in_archive":42},{"url":"/dataset/averitec","name":"AVeriTeC","full_name":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","num_papers_in_archive":17},{"url":"/dataset/mocheg","name":"Mocheg","full_name":"","num_papers_in_archive":10},{"url":"/dataset/politi-hop","name":"Politi Hop","full_name":"","num_papers_in_archive":7},{"url":"/dataset/covert","name":"CoVERT","full_name":"A Corpus of Fact-checked Biomedical COVID-19 Tweets","num_papers_in_archive":4},{"url":"/dataset/liar2","name":"LIAR2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/stanceosaurus","name":"Stanceosaurus","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cfever","name":"CFEVER","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spiced","name":"Spiced","full_name":"","num_papers_in_archive":1},{"url":"/dataset/panacea","name":"PANACEA","full_name":"PANACEA dataset - Heterogeneous COVID-19 Claims","num_papers_in_archive":0},{"url":"/dataset/stvd-fc","name":"STVD-FC","full_name":"Fact-checking dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/fever-2-way","name":"FEVER (2-way)"},{"url":"/task/fever-3-way","name":"FEVER (3-way)"},{"url":"/task/known-unknowns","name":"Known Unknowns"},{"url":"/task/misconceptions","name":"Misconceptions"},{"url":"/task/sentence-ambiguity","name":"Sentence Ambiguity"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":7,"rows_per_page":100,"shown":100,"of":669,"of_with_code":297,"tagged_in_all":669,"counts":{"archive_papers_tagged":669,"with_a_code_link":297,"where_syntology_ran_a_sample":67,"not_listed_spam_title":0,"listed":669,"listed_where_code_ran":67,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":47,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":47,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/liar-liar-pants-on-fire-a-new-benchmark","slug":"liar-liar-pants-on-fire-a-new-benchmark","title":"\"Liar, Liar Pants on Fire\": A New Benchmark Dataset for Fake News Detection","date":"2017-05-01","arxiv_id":"1705.00648","repositories_listed":11,"syntology":null},{"url":"/paper/a-simple-but-tough-to-beat-baseline-for-the","slug":"a-simple-but-tough-to-beat-baseline-for-the","title":"A simple but tough-to-beat baseline for the Fake News Challenge stance detection task","date":"2017-07-11","arxiv_id":"1707.03264","repositories_listed":9,"syntology":null},{"url":"/paper/towards-unsupervised-dense-information","slug":"towards-unsupervised-dense-information","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.09118","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/towards-unsupervised-dense-information#ran","syntology_url":"https://syntology.ai/paper/2112.09118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09118"}},"official":{"repos":["facebookresearch/contriever"],"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/explainable-tsetlin-machine-framework-for","slug":"explainable-tsetlin-machine-framework-for","title":"Explainable Tsetlin Machine framework for fake news detection with credibility score assessment","date":"2021-05-19","arxiv_id":"2105.09114","repositories_listed":6,"syntology":null},{"url":"/paper/openfactcheck-a-unified-framework-for","slug":"openfactcheck-a-unified-framework-for","title":"OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs","date":"2024-05-09","arxiv_id":"2405.05583","repositories_listed":4,"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/openfactcheck-a-unified-framework-for#ran","syntology_url":"https://syntology.ai/paper/2405.05583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05583"}},"official":{"repos":["yuxiaw/openfactcheck"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-the-factual-consistency-of","slug":"evaluating-the-factual-consistency-of","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","date":"2019-10-28","arxiv_id":"1910.12840","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-the-factual-consistency-of#ran","syntology_url":"https://syntology.ai/paper/1910.12840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12840"}},"official":{"repos":["yuhui-zh15/FactCCX"],"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":["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/factool-factuality-detection-in-generative-ai","slug":"factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","arxiv_id":"2307.13528","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/factool-factuality-detection-in-generative-ai#ran","syntology_url":"https://syntology.ai/paper/2307.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13528"}},"official":{"repos":["gair-nlp/factool"],"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/averitec-a-dataset-for-real-world-claim-1","slug":"averitec-a-dataset-for-real-world-claim-1","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","date":"2023-05-22","arxiv_id":"2305.13117","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/averitec-a-dataset-for-real-world-claim-1#ran","syntology_url":"https://syntology.ai/paper/2305.13117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13117"}},"official":{"repos":["michschli/averitec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/longchecker-improving-scientific-claim","slug":"longchecker-improving-scientific-claim","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","date":"2021-12-02","arxiv_id":"2112.01640","repositories_listed":3,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longchecker-improving-scientific-claim#ran","syntology_url":"https://syntology.ai/paper/2112.01640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01640"}},"official":{"repos":["dwadden/longchecker","dwadden/multivers"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","slug":"beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","date":"2021-04-17","arxiv_id":"2104.08663","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/beir-a-heterogenous-benchmark-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2104.08663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08663"}},"official":{"repos":["UKPLab/beir"],"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/editing-factual-knowledge-in-language-models","slug":"editing-factual-knowledge-in-language-models","title":"Editing Factual Knowledge in Language Models","date":"2021-04-16","arxiv_id":"2104.08164","repositories_listed":3,"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":1,"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/editing-factual-knowledge-in-language-models#ran","syntology_url":"https://syntology.ai/paper/2104.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08164"}},"official":{"repos":["nicola-decao/KnowledgeEditor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/factual-error-correction-of-claims","slug":"factual-error-correction-of-claims","title":"Evidence-based Factual Error Correction","date":"2020-12-31","arxiv_id":"2012.15788","repositories_listed":3,"syntology":null},{"url":"/paper/team-alex-at-clef-checkthat-2020-identifying","slug":"team-alex-at-clef-checkthat-2020-identifying","title":"Team Alex at CLEF CheckThat! 2020: Identifying Check-Worthy Tweets With Transformer Models","date":"2020-09-07","arxiv_id":"2009.02931","repositories_listed":3,"syntology":null},{"url":"/paper/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}},"official":{"repos":["facebookresearch/KILT"],"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/coronavirus-on-social-media-analyzing","slug":"coronavirus-on-social-media-analyzing","title":"COVID-19 on Social Media: Analyzing Misinformation in Twitter Conversations","date":"2020-03-26","arxiv_id":"2003.12309","repositories_listed":3,"syntology":null},{"url":"/paper/checkthat-at-clef-2020-enabling-the-automatic","slug":"checkthat-at-clef-2020-enabling-the-automatic","title":"CheckThat! at CLEF 2020: Enabling the Automatic Identification and Verification of Claims in Social Media","date":"2020-01-21","arxiv_id":"2001.08546","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-fact-guided-sentence-modification","slug":"automatic-fact-guided-sentence-modification","title":"Automatic Fact-guided Sentence Modification","date":"2019-09-30","arxiv_id":"1909.13838","repositories_listed":3,"syntology":null},{"url":"/paper/fact-checking-in-community-forums","slug":"fact-checking-in-community-forums","title":"Fact Checking in Community Forums","date":"2018-03-08","arxiv_id":"1803.03178","repositories_listed":3,"syntology":null},{"url":"/paper/cove-context-and-veracity-prediction-for-out","slug":"cove-context-and-veracity-prediction-for-out","title":"COVE: COntext and VEracity prediction for out-of-context images","date":"2025-02-03","arxiv_id":"2502.01194","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cove-context-and-veracity-prediction-for-out#ran","syntology_url":"https://syntology.ai/paper/2502.01194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01194"}},"official":{"repos":["ukplab/naacl2025-cove"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openfactcheck-a-unified-framework-for-1","slug":"openfactcheck-a-unified-framework-for-1","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","date":"2024-08-06","arxiv_id":"2408.11832","repositories_listed":2,"syntology":null},{"url":"/paper/lotus-enabling-semantic-queries-with-llms","slug":"lotus-enabling-semantic-queries-with-llms","title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing","date":"2024-07-16","arxiv_id":"2407.11418","repositories_listed":2,"syntology":null},{"url":"/paper/missci-reconstructing-fallacies-in","slug":"missci-reconstructing-fallacies-in","title":"Missci: Reconstructing Fallacies in Misrepresented Science","date":"2024-06-05","arxiv_id":"2406.03181","repositories_listed":2,"syntology":null},{"url":"/paper/minicheck-efficient-fact-checking-of-llms-on","slug":"minicheck-efficient-fact-checking-of-llms-on","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","date":"2024-04-16","arxiv_id":"2404.10774","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/minicheck-efficient-fact-checking-of-llms-on#ran","syntology_url":"https://syntology.ai/paper/2404.10774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10774"}},"official":{"repos":["liyan06/minicheck"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cfever-a-chinese-fact-extraction-and","slug":"cfever-a-chinese-fact-extraction-and","title":"CFEVER: A Chinese Fact Extraction and VERification Dataset","date":"2024-02-20","arxiv_id":"2402.13025","repositories_listed":2,"syntology":null},{"url":"/paper/factcheck-gpt-end-to-end-fine-grained","slug":"factcheck-gpt-end-to-end-fine-grained","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","date":"2023-11-15","arxiv_id":"2311.09000","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/factcheck-gpt-end-to-end-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2311.09000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09000"}},"official":{"repos":["yuxiaw/factcheck-gpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bgglue-a-bulgarian-general-language","slug":"bgglue-a-bulgarian-general-language","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","date":"2023-06-04","arxiv_id":"2306.02349","repositories_listed":2,"syntology":null},{"url":"/paper/fact-checking-complex-claims-with-program","slug":"fact-checking-complex-claims-with-program","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","date":"2023-05-22","arxiv_id":"2305.12744","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":2,"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/fact-checking-complex-claims-with-program#ran","syntology_url":"https://syntology.ai/paper/2305.12744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12744"}},"official":{"repos":["mbzuai-nlp/programfc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-can-rate-news-outlet","slug":"large-language-models-can-rate-news-outlet","title":"Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models","date":"2023-04-01","arxiv_id":"2304.00228","repositories_listed":2,"syntology":null},{"url":"/paper/wice-real-world-entailment-for-claims-in","slug":"wice-real-world-entailment-for-claims-in","title":"WiCE: Real-World Entailment for Claims in Wikipedia","date":"2023-03-02","arxiv_id":"2303.01432","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wice-real-world-entailment-for-claims-in#ran","syntology_url":"https://syntology.ai/paper/2303.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01432"}},"official":{"repos":["ryokamoi/wice"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","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":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}},"official":{"repos":["facebookresearch/atlas"],"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/dialfact-a-benchmark-for-fact-checking-in","slug":"dialfact-a-benchmark-for-fact-checking-in","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","date":"2021-10-15","arxiv_id":"2110.08222","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialfact-a-benchmark-for-fact-checking-in#ran","syntology_url":"https://syntology.ai/paper/2110.08222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08222"}},"official":{"repos":["salesforce/dialfact"],"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/towards-continual-knowledge-learning-of","slug":"towards-continual-knowledge-learning-of","title":"Towards Continual Knowledge Learning of Language Models","date":"2021-10-07","arxiv_id":"2110.03215","repositories_listed":2,"syntology":null},{"url":"/paper/creak-a-dataset-for-commonsense-reasoning","slug":"creak-a-dataset-for-commonsense-reasoning","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","date":"2021-09-03","arxiv_id":"2109.01653","repositories_listed":2,"syntology":null},{"url":"/paper/faviq-fact-verification-from-information","slug":"faviq-fact-verification-from-information","title":"FaVIQ: FAct Verification from Information-seeking Questions","date":"2021-07-05","arxiv_id":"2107.02153","repositories_listed":2,"syntology":null},{"url":"/paper/a-multi-level-attention-model-for-evidence","slug":"a-multi-level-attention-model-for-evidence","title":"A Multi-Level Attention Model for Evidence-Based Fact Checking","date":"2021-06-02","arxiv_id":"2106.00950","repositories_listed":2,"syntology":null},{"url":"/paper/user-preference-aware-fake-news-detection","slug":"user-preference-aware-fake-news-detection","title":"User Preference-aware Fake News Detection","date":"2021-04-25","arxiv_id":"2104.12259","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/user-preference-aware-fake-news-detection#ran","syntology_url":"https://syntology.ai/paper/2104.12259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12259"}},"official":{"repos":["safe-graph/GNN-FakeNews"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/misinfo-belief-frames-a-case-study-on-covid","slug":"misinfo-belief-frames-a-case-study-on-covid","title":"Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines","date":"2021-04-18","arxiv_id":"2104.08790","repositories_listed":2,"syntology":null},{"url":"/paper/evidence-based-verification-for-real-world","slug":"evidence-based-verification-for-real-world","title":"AmbiFC: Fact-Checking Ambiguous Claims with Evidence","date":"2021-04-01","arxiv_id":"2104.00640","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"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, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evidence-based-verification-for-real-world#ran","syntology_url":"https://syntology.ai/paper/2104.00640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00640"}},"official":{"repos":["CambridgeNLIP/verification-real-world-info-needs"],"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/eating-garlic-prevents-covid-19-infection","slug":"eating-garlic-prevents-covid-19-infection","title":"Eating Garlic Prevents COVID-19 Infection: Detecting Misinformation on the Arabic Content of Twitter","date":"2021-01-09","arxiv_id":"2101.05626","repositories_listed":2,"syntology":null},{"url":"/paper/explainable-automated-fact-checking-for","slug":"explainable-automated-fact-checking-for","title":"Explainable Automated Fact-Checking for Public Health Claims","date":"2020-10-19","arxiv_id":"2010.09926","repositories_listed":2,"syntology":null},{"url":"/paper/where-are-the-facts-searching-for-fact","slug":"where-are-the-facts-searching-for-fact","title":"Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News","date":"2020-10-07","arxiv_id":"2010.03159","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/where-are-the-facts-searching-for-fact#ran","syntology_url":"https://syntology.ai/paper/2010.03159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03159"}},"official":{"repos":["nguyenvo09/EMNLP2020"],"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":["official"]}}},{"url":"/paper/graph-neural-networks-with-continual-learning","slug":"graph-neural-networks-with-continual-learning","title":"Graph Neural Networks with Continual Learning for Fake News Detection from Social Media","date":"2020-07-07","arxiv_id":"2007.03316","repositories_listed":2,"syntology":null},{"url":"/paper/that-is-a-known-lie-detecting-previously-fact","slug":"that-is-a-known-lie-detecting-previously-fact","title":"That is a Known Lie: Detecting Previously Fact-Checked Claims","date":"2020-05-12","arxiv_id":"2005.06058","repositories_listed":2,"syntology":null},{"url":"/paper/fact-or-fiction-verifying-scientific-claims","slug":"fact-or-fiction-verifying-scientific-claims","title":"Fact or Fiction: Verifying Scientific Claims","date":"2020-04-30","arxiv_id":"2004.14974","repositories_listed":2,"syntology":null},{"url":"/paper/a-richly-annotated-corpus-for-different-tasks-1","slug":"a-richly-annotated-corpus-for-different-tasks-1","title":"A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking","date":"2019-10-29","arxiv_id":"1911.01214","repositories_listed":2,"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":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) · 3 unverified","sample_list":"/paper/a-richly-annotated-corpus-for-different-tasks-1#ran","syntology_url":"https://syntology.ai/paper/1911.01214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01214"}},"official":{"repos":["UKPLab/conll2019-snopes-crawling","UKPLab/conll2019-snopes-experiments"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-fact-extraction-and-verification","slug":"combining-fact-extraction-and-verification","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","date":"2018-11-16","arxiv_id":"1811.07039","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/combining-fact-extraction-and-verification#ran","syntology_url":"https://syntology.ai/paper/1811.07039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07039"}},"official":{"repos":["easonnie/combine-FEVER-NSMN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/where-is-your-evidence-improving-fact","slug":"where-is-your-evidence-improving-fact","title":"Where is Your Evidence: Improving Fact-checking by Justification Modeling","date":"2018-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/predicting-factuality-of-reporting-and-bias","slug":"predicting-factuality-of-reporting-and-bias","title":"Predicting Factuality of Reporting and Bias of News Media Sources","date":"2018-10-02","arxiv_id":"1810.01765","repositories_listed":2,"syntology":null},{"url":"/paper/declare-debunking-fake-news-and-false-claims","slug":"declare-debunking-fake-news-and-false-claims","title":"DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning","date":"2018-09-17","arxiv_id":"1809.06416","repositories_listed":2,"syntology":null},{"url":"/paper/ti-cnn-convolutional-neural-networks-for-fake","slug":"ti-cnn-convolutional-neural-networks-for-fake","title":"TI-CNN: Convolutional Neural Networks for Fake News Detection","date":"2018-06-03","arxiv_id":"1806.00749","repositories_listed":2,"syntology":null},{"url":"/paper/liar-liar-pants-on-fire-a-new-benchmark-1","slug":"liar-liar-pants-on-fire-a-new-benchmark-1","title":"``Liar, Liar Pants on Fire'': A New Benchmark Dataset for Fake News Detection","date":"2017-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/proje-embedding-projection-for-knowledge","slug":"proje-embedding-projection-for-knowledge","title":"ProjE: Embedding Projection for Knowledge Graph Completion","date":"2016-11-16","arxiv_id":"1611.05425","repositories_listed":2,"syntology":null},{"url":"/paper/ds-gt-at-checkthat-2025-evaluating-context","slug":"ds-gt-at-checkthat-2025-evaluating-context","title":"DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification","date":"2025-07-08","arxiv_id":"2507.06195","repositories_listed":1,"syntology":null},{"url":"/paper/decide-less-communicate-more-on-the-construct","slug":"decide-less-communicate-more-on-the-construct","title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine","date":"2025-06-25","arxiv_id":"2506.20876","repositories_listed":1,"syntology":null},{"url":"/paper/verifying-the-verifiers-unveiling-pitfalls","slug":"verifying-the-verifiers-unveiling-pitfalls","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","date":"2025-06-16","arxiv_id":"2506.13342","repositories_listed":1,"syntology":null},{"url":"/paper/realfactbench-a-benchmark-for-evaluating","slug":"realfactbench-a-benchmark-for-evaluating","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","date":"2025-06-14","arxiv_id":"2506.12538","repositories_listed":1,"syntology":null},{"url":"/paper/climateviz-a-benchmark-for-statistical","slug":"climateviz-a-benchmark-for-statistical","title":"ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts","date":"2025-06-10","arxiv_id":"2506.08700","repositories_listed":1,"syntology":null},{"url":"/paper/search-arena-analyzing-search-augmented-llms","slug":"search-arena-analyzing-search-augmented-llms","title":"Search Arena: Analyzing Search-Augmented LLMs","date":"2025-06-05","arxiv_id":"2506.05334","repositories_listed":1,"syntology":null},{"url":"/paper/sucea-reasoning-intensive-retrieval-for","slug":"sucea-reasoning-intensive-retrieval-for","title":"SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing","date":"2025-06-05","arxiv_id":"2506.04583","repositories_listed":1,"syntology":null},{"url":"/paper/resolving-conflicting-evidence-in-automated","slug":"resolving-conflicting-evidence-in-automated","title":"Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs","date":"2025-05-23","arxiv_id":"2505.17762","repositories_listed":1,"syntology":null},{"url":"/paper/emulate-a-multi-agent-framework-for","slug":"emulate-a-multi-agent-framework-for","title":"EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions","date":"2025-05-22","arxiv_id":"2505.16576","repositories_listed":1,"syntology":null},{"url":"/paper/urdufactcheck-an-agentic-fact-checking","slug":"urdufactcheck-an-agentic-fact-checking","title":"UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking","date":"2025-05-21","arxiv_id":"2505.15063","repositories_listed":1,"syntology":null},{"url":"/paper/multihal-multilingual-dataset-for-knowledge","slug":"multihal-multilingual-dataset-for-knowledge","title":"MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations","date":"2025-05-20","arxiv_id":"2505.14101","repositories_listed":1,"syntology":null},{"url":"/paper/factors-a-new-dataset-for-studying-the-fact","slug":"factors-a-new-dataset-for-studying-the-fact","title":"FACTors: A New Dataset for Studying the Fact-checking Ecosystem","date":"2025-05-14","arxiv_id":"2505.09414","repositories_listed":1,"syntology":null},{"url":"/paper/judging-the-judges-can-large-vision-language","slug":"judging-the-judges-can-large-vision-language","title":"Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?","date":"2025-05-13","arxiv_id":"2505.08468","repositories_listed":1,"syntology":null},{"url":"/paper/chronocept-instilling-a-sense-of-time-in","slug":"chronocept-instilling-a-sense-of-time-in","title":"Chronocept: Instilling a Sense of Time in Machines","date":"2025-05-12","arxiv_id":"2505.07637","repositories_listed":1,"syntology":null},{"url":"/paper/a-generative-ai-driven-claim-retrieval-system","slug":"a-generative-ai-driven-claim-retrieval-system","title":"A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages","date":"2025-04-29","arxiv_id":"2504.20668","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-manipulated-contents-using","slug":"detecting-manipulated-contents-using","title":"Detecting Manipulated Contents Using Knowledge-Grounded Inference","date":"2025-04-29","arxiv_id":"2504.21165","repositories_listed":1,"syntology":null},{"url":"/paper/entity-aware-cross-lingual-claim-detection","slug":"entity-aware-cross-lingual-claim-detection","title":"Entity-aware Cross-lingual Claim Detection for Automated Fact-checking","date":"2025-03-19","arxiv_id":"2503.15220","repositories_listed":1,"syntology":null},{"url":"/paper/when-claims-evolve-evaluating-and-enhancing","slug":"when-claims-evolve-evaluating-and-enhancing","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","date":"2025-03-05","arxiv_id":"2503.03417","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00955","slug":"2503-00955","title":"SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking","date":"2025-03-02","arxiv_id":"2503.00955","repositories_listed":1,"syntology":null},{"url":"/paper/graphcheck-multi-path-fact-checking-with","slug":"graphcheck-multi-path-fact-checking-with","title":"GraphCheck: Multi-Path Fact-Checking with Entity-Relationship Graphs","date":"2025-02-28","arxiv_id":"2502.20785","repositories_listed":1,"syntology":null},{"url":"/paper/fact-audit-an-adaptive-multi-agent-framework","slug":"fact-audit-an-adaptive-multi-agent-framework","title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","date":"2025-02-25","arxiv_id":"2502.17924","repositories_listed":1,"syntology":null},{"url":"/paper/verdict-a-library-for-scaling-judge-time","slug":"verdict-a-library-for-scaling-judge-time","title":"Verdict: A Library for Scaling Judge-Time Compute","date":"2025-02-25","arxiv_id":"2502.18018","repositories_listed":1,"syntology":null},{"url":"/paper/bidev-bilateral-defusing-verification-for","slug":"bidev-bilateral-defusing-verification-for","title":"BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking","date":"2025-02-22","arxiv_id":"2502.16181","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-translation-llm-based-data-generation","slug":"beyond-translation-llm-based-data-generation","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","date":"2025-02-21","arxiv_id":"2502.15419","repositories_listed":1,"syntology":null},{"url":"/paper/step-by-step-fact-verification-system-for","slug":"step-by-step-fact-verification-system-for","title":"Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning","date":"2025-02-20","arxiv_id":"2502.14765","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-density-based-uncertainty","slug":"token-level-density-based-uncertainty","title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","date":"2025-02-20","arxiv_id":"2502.14427","repositories_listed":1,"syntology":null},{"url":"/paper/hintsoftruth-a-multimodal-checkworthiness","slug":"hintsoftruth-a-multimodal-checkworthiness","title":"HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims","date":"2025-02-17","arxiv_id":"2502.11753","repositories_listed":1,"syntology":null},{"url":"/paper/correct-context-and-reference-augmented","slug":"correct-context-and-reference-augmented","title":"CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking","date":"2025-02-09","arxiv_id":"2502.09635","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/correct-context-and-reference-augmented#ran","syntology_url":"https://syntology.ai/paper/2502.09635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09635"}},"official":{"repos":["cezhang01/correct"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/flashcheck-exploration-of-efficient-evidence","slug":"flashcheck-exploration-of-efficient-evidence","title":"FlashCheck: Exploration of Efficient Evidence Retrieval for Fast Fact-Checking","date":"2025-02-09","arxiv_id":"2502.05803","repositories_listed":1,"syntology":null},{"url":"/paper/self-rationalization-in-the-wild-a-large","slug":"self-rationalization-in-the-wild-a-large","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","date":"2025-02-07","arxiv_id":"2502.04797","repositories_listed":1,"syntology":null},{"url":"/paper/from-scarcity-to-capability-empowering-fake","slug":"from-scarcity-to-capability-empowering-fake","title":"From Scarcity to Capability: Empowering Fake News Detection in Low-Resource Languages with LLMs","date":"2025-01-16","arxiv_id":"2501.09604","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-the-takes-and-trajectories-of","slug":"tracking-the-takes-and-trajectories-of","title":"Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome Websites","date":"2025-01-15","arxiv_id":"2501.09102","repositories_listed":1,"syntology":null},{"url":"/paper/face-the-facts-evaluating-rag-based-fact","slug":"face-the-facts-evaluating-rag-based-fact","title":"Face the Facts! Evaluating RAG-based Fact-checking Pipelines in Realistic Settings","date":"2024-12-19","arxiv_id":"2412.15189","repositories_listed":1,"syntology":null},{"url":"/paper/defame-dynamic-evidence-based-fact-checking","slug":"defame-dynamic-evidence-based-fact-checking","title":"DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts","date":"2024-12-13","arxiv_id":"2412.10510","repositories_listed":1,"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/defame-dynamic-evidence-based-fact-checking#ran","syntology_url":"https://syntology.ai/paper/2412.10510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10510"}},"official":{"repos":["multimodal-ai-lab/defame"],"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"]}}},{"url":"/paper/llms-as-debate-partners-utilizing-genetic","slug":"llms-as-debate-partners-utilizing-genetic","title":"LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments","date":"2024-12-09","arxiv_id":"2412.06229","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/llms-as-debate-partners-utilizing-genetic#ran","syntology_url":"https://syntology.ai/paper/2412.06229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06229"}},"official":{"repos":["prakash-aryan/debatebrawl-app"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-fact-checking-with-vision-language","slug":"multimodal-fact-checking-with-vision-language","title":"Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies","date":"2024-12-06","arxiv_id":"2412.05155","repositories_listed":1,"syntology":null},{"url":"/paper/truth-or-mirage-towards-end-to-end-factuality","slug":"truth-or-mirage-towards-end-to-end-factuality","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","date":"2024-11-29","arxiv_id":"2411.19655","repositories_listed":1,"syntology":null},{"url":"/paper/zefav-boosting-large-language-models-for-zero","slug":"zefav-boosting-large-language-models-for-zero","title":"ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification","date":"2024-11-18","arxiv_id":"2411.11247","repositories_listed":1,"syntology":null},{"url":"/paper/belief-in-the-machine-investigating","slug":"belief-in-the-machine-investigating","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","date":"2024-10-28","arxiv_id":"2410.21195","repositories_listed":1,"syntology":null},{"url":"/paper/subjective-qa-measuring-subjectivity-in","slug":"subjective-qa-measuring-subjectivity-in","title":"SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis","date":"2024-10-28","arxiv_id":"2410.20651","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/subjective-qa-measuring-subjectivity-in#ran","syntology_url":"https://syntology.ai/paper/2410.20651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20651"}},"official":{"repos":["gtfintechlab/subjective-qa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-fake-news-from-adversarial-feedback","slug":"real-time-fake-news-from-adversarial-feedback","title":"Real-time Fake News from Adversarial Feedback","date":"2024-10-18","arxiv_id":"2410.14651","repositories_listed":1,"syntology":null},{"url":"/paper/fire-fact-checking-with-iterative-retrieval","slug":"fire-fact-checking-with-iterative-retrieval","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","date":"2024-10-17","arxiv_id":"2411.00784","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fire-fact-checking-with-iterative-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.00784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00784"}},"official":{"repos":["mbzuai-nlp/fire"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hero-at-averitec-the-herd-of-open-large","slug":"hero-at-averitec-the-herd-of-open-large","title":"HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims","date":"2024-10-16","arxiv_id":"2410.12377","repositories_listed":1,"syntology":null},{"url":"/paper/aic-ctu-system-at-averitec-re-framing","slug":"aic-ctu-system-at-averitec-re-framing","title":"AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task","date":"2024-10-15","arxiv_id":"2410.11446","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-translation-bias-and","slug":"a-comparative-study-of-translation-bias-and","title":"A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification","date":"2024-10-14","arxiv_id":"2410.10303","repositories_listed":1,"syntology":null}],"syntology_records":28,"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":6,"papers_placed":1,"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/fact-checking-on-scifact-beir","since_archive":"/sota/fact-checking-on-scifact-beir#since-judged","papers_judged":6,"placed":1}]},"papers_where_code_ran":67,"papers_where_code_ran_first_page":"/task/fact-checking/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":7,"url":"/task/fact-checking/papers/2","json":"/task/fact-checking/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/fact-checking/papers/3","json":"/task/fact-checking/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/fact-checking/papers/4","json":"/task/fact-checking/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/fact-checking/papers/5","json":"/task/fact-checking/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/fact-checking/papers/6","json":"/task/fact-checking/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/fact-checking/papers/7","json":"/task/fact-checking/papers/7.json","rows":69},{"order":"ran","page":1,"of":1,"url":"/task/fact-checking/papers/ran/1","json":"/task/fact-checking/papers/ran/1.json","rows":67}],"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":"d38125473f0591cec597f42c0fd31544e4d8f599a82438a19b62b6c9fe8f3463","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}