{"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/world-knowledge","name":"World Knowledge","slug":"world-knowledge","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":818,"papers_with_code":358,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1},{"url":"/dataset/mm-eval","name":"MM-Eval","full_name":"Modern Mongolian Evaluation","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":9,"rows_per_page":100,"shown":100,"of":818,"of_with_code":358,"tagged_in_all":818,"counts":{"archive_papers_tagged":818,"with_a_code_link":358,"where_syntology_ran_a_sample":142,"not_listed_spam_title":0,"listed":818,"listed_where_code_ran":142,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":117,"every_run_a_failure_of_syntologys_instrument":25,"listed_with_a_run_with_no_instrument_failure":117,"listed_every_run_a_failure_of_syntologys_instrument":25,"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/direct-preference-optimization-your-language","slug":"direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","arxiv_id":"2305.18290","repositories_listed":29,"syntology":{"n":31,"n_ran":25,"n_constructed":1,"n_ran_checked":21,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":2,"phrase":"25 ran (of which 1 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/direct-preference-optimization-your-language#ran","syntology_url":"https://syntology.ai/paper/2305.18290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18290"}},"official":null}},{"url":"/paper/measuring-massive-multitask-language","slug":"measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","date":"2020-09-07","arxiv_id":"2009.03300","repositories_listed":18,"syntology":{"n":26,"n_ran":19,"n_constructed":0,"n_ran_checked":10,"n_instrument":9,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/measuring-massive-multitask-language#ran","syntology_url":"https://syntology.ai/paper/2009.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.03300"}},"official":{"repos":["hendrycks/test"],"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/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","repositories_listed":18,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}},"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/realm-retrieval-augmented-language-model-pre","slug":"realm-retrieval-augmented-language-model-pre","title":"REALM: Retrieval-Augmented Language Model Pre-Training","date":"2020-02-10","arxiv_id":"2002.08909","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/realm-retrieval-augmented-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2002.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08909"}},"official":{"repos":["google-research/language"],"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/imagine-this-scripts-to-compositions-to","slug":"imagine-this-scripts-to-compositions-to","title":"Imagine This! Scripts to Compositions to Videos","date":"2018-04-10","arxiv_id":"1804.03608","repositories_listed":5,"syntology":null},{"url":"/paper/scaling-synthetic-data-creation-with","slug":"scaling-synthetic-data-creation-with","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","date":"2024-06-28","arxiv_id":"2406.20094","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-synthetic-data-creation-with#ran","syntology_url":"https://syntology.ai/paper/2406.20094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20094"}},"official":{"repos":["tencent-ailab/persona-hub"],"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/meim-multi-partition-embedding-interaction","slug":"meim-multi-partition-embedding-interaction","title":"MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction","date":"2022-09-30","arxiv_id":"2209.15597","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/meim-multi-partition-embedding-interaction#ran","syntology_url":"https://syntology.ai/paper/2209.15597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15597"}},"official":{"repos":["tranhungnghiep/meim-kge"],"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":["found_in_text"]}}},{"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/vila-on-pre-training-for-visual-language","slug":"vila-on-pre-training-for-visual-language","title":"VILA: On Pre-training for Visual Language Models","date":"2023-12-12","arxiv_id":"2312.07533","repositories_listed":3,"syntology":null},{"url":"/paper/dense-x-retrieval-what-retrieval-granularity","slug":"dense-x-retrieval-what-retrieval-granularity","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","date":"2023-12-11","arxiv_id":"2312.06648","repositories_listed":3,"syntology":null},{"url":"/paper/symbol-llm-towards-foundational-symbol","slug":"symbol-llm-towards-foundational-symbol","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","date":"2023-11-15","arxiv_id":"2311.09278","repositories_listed":3,"syntology":null},{"url":"/paper/aligning-ai-with-shared-human-values","slug":"aligning-ai-with-shared-human-values","title":"Aligning AI With Shared Human Values","date":"2020-08-05","arxiv_id":"2008.02275","repositories_listed":3,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/aligning-ai-with-shared-human-values#ran","syntology_url":"https://syntology.ai/paper/2008.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02275"}},"official":{"repos":["hendrycks/ethics"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/aser-a-large-scale-eventuality-knowledge","slug":"aser-a-large-scale-eventuality-knowledge","title":"ASER: A Large-scale Eventuality Knowledge Graph","date":"2019-05-01","arxiv_id":"1905.00270","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/aser-a-large-scale-eventuality-knowledge#ran","syntology_url":"https://syntology.ai/paper/1905.00270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00270"}},"official":{"repos":["HKUST-KnowComp/ASER"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/bottlehumor-self-informed-humor-explanation","slug":"bottlehumor-self-informed-humor-explanation","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","date":"2025-02-22","arxiv_id":"2502.18331","repositories_listed":2,"syntology":null},{"url":"/paper/seallms-3-open-foundation-and-chat","slug":"seallms-3-open-foundation-and-chat","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","date":"2024-07-29","arxiv_id":"2407.19672","repositories_listed":2,"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":2,"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/seallms-3-open-foundation-and-chat#ran","syntology_url":"https://syntology.ai/paper/2407.19672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19672"}},"official":{"repos":["DAMO-NLP-SG/SeaExam"],"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/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}},"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-synthetic-dataset-for-personal-attribute","slug":"a-synthetic-dataset-for-personal-attribute","title":"A Synthetic Dataset for Personal Attribute Inference","date":"2024-06-11","arxiv_id":"2406.07217","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-synthetic-dataset-for-personal-attribute#ran","syntology_url":"https://syntology.ai/paper/2406.07217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07217"}},"official":{"repos":["eth-sri/synthpai"],"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":["listed","official"]}}},{"url":"/paper/elements-of-world-knowledge-ewok-a-cognition","slug":"elements-of-world-knowledge-ewok-a-cognition","title":"Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models","date":"2024-05-15","arxiv_id":"2405.09605","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elements-of-world-knowledge-ewok-a-cognition#ran","syntology_url":"https://syntology.ai/paper/2405.09605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09605"}},"official":{"repos":["ewok-core/ewok-paper","ewok-core/ewok"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mygo-discrete-modality-information-as-fine","slug":"mygo-discrete-modality-information-as-fine","title":"Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation","date":"2024-04-15","arxiv_id":"2404.09468","repositories_listed":2,"syntology":null},{"url":"/paper/can-llms-tuning-methods-work-in-medical","slug":"can-llms-tuning-methods-work-in-medical","title":"Can LLMs' Tuning Methods Work in Medical Multimodal Domain?","date":"2024-03-11","arxiv_id":"2403.06407","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-llms-tuning-methods-work-in-medical#ran","syntology_url":"https://syntology.ai/paper/2403.06407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06407"}},"official":{"repos":["timmy-chan/mile"],"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/grillbot-in-practice-lessons-and-tradeoffs","slug":"grillbot-in-practice-lessons-and-tradeoffs","title":"GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants","date":"2024-02-12","arxiv_id":"2402.07647","repositories_listed":2,"syntology":null},{"url":"/paper/bring-your-own-kg-self-supervised-program","slug":"bring-your-own-kg-self-supervised-program","title":"Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA","date":"2023-11-14","arxiv_id":"2311.07850","repositories_listed":2,"syntology":null},{"url":"/paper/freshllms-refreshing-large-language-models","slug":"freshllms-refreshing-large-language-models","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","date":"2023-10-05","arxiv_id":"2310.03214","repositories_listed":2,"syntology":null},{"url":"/paper/topical-chat-towards-knowledge-grounded-open-1","slug":"topical-chat-towards-knowledge-grounded-open-1","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","date":"2023-08-23","arxiv_id":"2308.11995","repositories_listed":2,"syntology":null},{"url":"/paper/expel-llm-agents-are-experiential-learners","slug":"expel-llm-agents-are-experiential-learners","title":"ExpeL: LLM Agents Are Experiential Learners","date":"2023-08-20","arxiv_id":"2308.10144","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/expel-llm-agents-are-experiential-learners#ran","syntology_url":"https://syntology.ai/paper/2308.10144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10144"}},"official":{"repos":["LeapLabTHU/ExpeL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","repositories_listed":2,"syntology":null},{"url":"/paper/pk-chat-pointer-network-guided-knowledge","slug":"pk-chat-pointer-network-guided-knowledge","title":"PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model","date":"2023-04-02","arxiv_id":"2304.00592","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-autoregressive-models-for-content","slug":"scaling-autoregressive-models-for-content","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","date":"2022-06-22","arxiv_id":"2206.10789","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-autoregressive-models-for-content#ran","syntology_url":"https://syntology.ai/paper/2206.10789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10789"}},"official":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/style-hallucinated-dual-consistency-learning","slug":"style-hallucinated-dual-consistency-learning","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","date":"2022-04-06","arxiv_id":"2204.02548","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/style-hallucinated-dual-consistency-learning#ran","syntology_url":"https://syntology.ai/paper/2204.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02548"}},"official":{"repos":["helioszhao/shade"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/quantifying-adaptability-in-pre-trained","slug":"quantifying-adaptability-in-pre-trained","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","date":"2021-12-06","arxiv_id":"2112.03204","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quantifying-adaptability-in-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2112.03204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03204"}},"official":{"repos":["belindal/taskbench500","facebookresearch/task_bench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["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/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","repositories_listed":2,"syntology":null},{"url":"/paper/teaching-machine-comprehension-with","slug":"teaching-machine-comprehension-with","title":"Teaching Machine Comprehension with Compositional Explanations","date":"2020-05-02","arxiv_id":"2005.00806","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":1,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":4,"n_violates":1,"n_no_contract":1,"n_pointer_only":10,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-machine-comprehension-with#ran","syntology_url":"https://syntology.ai/paper/2005.00806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00806"}},"official":{"repos":["INK-USC/mrc-explanation","INK-USC/nl-explanation"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/breaking-nli-systems-with-sentences-that","slug":"breaking-nli-systems-with-sentences-that","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","date":"2018-05-06","arxiv_id":"1805.02266","repositories_listed":2,"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/breaking-nli-systems-with-sentences-that#ran","syntology_url":"https://syntology.ai/paper/1805.02266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.02266"}},"official":{"repos":["BIU-NLP/Breaking_NLI"],"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/dora-the-explorer-directed-outreaching","slug":"dora-the-explorer-directed-outreaching","title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","date":"2018-04-11","arxiv_id":"1804.04012","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/dora-the-explorer-directed-outreaching#ran","syntology_url":"https://syntology.ai/paper/1804.04012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04012"}},"official":{"repos":["borgr/DORA"],"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/dreamvla-a-vision-language-action-model-1","slug":"dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","date":"2025-07-06","arxiv_id":"2507.04447","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreamvla-a-vision-language-action-model-1#ran","syntology_url":"https://syntology.ai/paper/2507.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04447"}},"official":{"repos":["Zhangwenyao1/DreamVLA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mirage-a-benchmark-for-multimodal-information","slug":"mirage-a-benchmark-for-multimodal-information","title":"MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations","date":"2025-06-25","arxiv_id":"2506.20100","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":7,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":18,"phrase":"16 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; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mirage-a-benchmark-for-multimodal-information#ran","syntology_url":"https://syntology.ai/paper/2506.20100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20100"}},"official":{"repos":["mirage-benchmark/mirage-benchmark"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-preference-lambda-weighted-listwise-dpo","slug":"multi-preference-lambda-weighted-listwise-dpo","title":"Multi-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment","date":"2025-06-24","arxiv_id":"2506.19780","repositories_listed":1,"syntology":null},{"url":"/paper/impliret-benchmarking-the-implicit-fact","slug":"impliret-benchmarking-the-implicit-fact","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","date":"2025-06-17","arxiv_id":"2506.14407","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/impliret-benchmarking-the-implicit-fact#ran","syntology_url":"https://syntology.ai/paper/2506.14407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14407"}},"official":{"repos":["zeinabtaghavi/impliret"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autovla-a-vision-language-action-model-for","slug":"autovla-a-vision-language-action-model-for","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","date":"2025-06-16","arxiv_id":"2506.13757","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autovla-a-vision-language-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2506.13757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13757"}},"official":{"repos":["ucla-mobility/AutoVLA"],"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/contexttab-a-semantics-aware-tabular-in","slug":"contexttab-a-semantics-aware-tabular-in","title":"ConTextTab: A Semantics-Aware Tabular In-Context Learner","date":"2025-06-12","arxiv_id":"2506.10707","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/contexttab-a-semantics-aware-tabular-in#ran","syntology_url":"https://syntology.ai/paper/2506.10707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10707"}},"official":{"repos":["sap-samples/contexttab"],"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":["found_in_text","official"]}}},{"url":"/paper/probing-the-geometry-of-truth-consistency-and","slug":"probing-the-geometry-of-truth-consistency-and","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","date":"2025-06-01","arxiv_id":"2506.00823","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probing-the-geometry-of-truth-consistency-and#ran","syntology_url":"https://syntology.ai/paper/2506.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00823"}},"official":{"repos":["colored-dye/truthfulness_probe_generalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/augment-or-not-a-comparative-study-of-pure","slug":"augment-or-not-a-comparative-study-of-pure","title":"Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders","date":"2025-05-29","arxiv_id":"2505.23053","repositories_listed":1,"syntology":null},{"url":"/paper/align-beyond-prompts-evaluating-world","slug":"align-beyond-prompts-evaluating-world","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","date":"2025-05-24","arxiv_id":"2505.18730","repositories_listed":1,"syntology":null},{"url":"/paper/gre-suite-geo-localization-inference-via-fine","slug":"gre-suite-geo-localization-inference-via-fine","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","date":"2025-05-24","arxiv_id":"2505.18700","repositories_listed":1,"syntology":null},{"url":"/paper/o-2-searcher-a-searching-based-agent-model","slug":"o-2-searcher-a-searching-based-agent-model","title":"O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering","date":"2025-05-22","arxiv_id":"2505.16582","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/o-2-searcher-a-searching-based-agent-model#ran","syntology_url":"https://syntology.ai/paper/2505.16582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16582"}},"official":{"repos":["acade-mate/o2-searcher"],"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/timecausality-evaluating-the-causal-ability","slug":"timecausality-evaluating-the-causal-ability","title":"TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models","date":"2025-05-21","arxiv_id":"2505.15435","repositories_listed":1,"syntology":null},{"url":"/paper/unierase-unlearning-token-as-a-universal","slug":"unierase-unlearning-token-as-a-universal","title":"UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models","date":"2025-05-21","arxiv_id":"2505.15674","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-lms-are-better-knowledge","slug":"bidirectional-lms-are-better-knowledge","title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","date":"2025-05-18","arxiv_id":"2505.12306","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-spatiotemporal-reasoning-in-llms","slug":"benchmarking-spatiotemporal-reasoning-in-llms","title":"Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges","date":"2025-05-16","arxiv_id":"2505.11618","repositories_listed":1,"syntology":null},{"url":"/paper/llm4cd-leveraging-large-language-models-for","slug":"llm4cd-leveraging-large-language-models-for","title":"LLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis","date":"2025-05-14","arxiv_id":"2505.13492","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-and-benchmarking-personalized-tool","slug":"advancing-and-benchmarking-personalized-tool","title":"Advancing and Benchmarking Personalized Tool Invocation for LLMs","date":"2025-05-07","arxiv_id":"2505.04072","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-contrastive-feedback-for-effective","slug":"evaluating-contrastive-feedback-for-effective","title":"Evaluating Contrastive Feedback for Effective User Simulations","date":"2025-05-05","arxiv_id":"2505.02560","repositories_listed":1,"syntology":null},{"url":"/paper/weathergen-a-unified-diverse-weather","slug":"weathergen-a-unified-diverse-weather","title":"WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion","date":"2025-04-18","arxiv_id":"2504.13561","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weathergen-a-unified-diverse-weather#ran","syntology_url":"https://syntology.ai/paper/2504.13561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13561"}},"official":{"repos":["wuyang98/weathergen"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-modular-classification-learning-to","slug":"memory-modular-classification-learning-to","title":"Memory-Modular Classification: Learning to Generalize with Memory Replacement","date":"2025-04-08","arxiv_id":"2504.06021","repositories_listed":1,"syntology":null},{"url":"/paper/f-vita-foundation-model-guided-visible-to","slug":"f-vita-foundation-model-guided-visible-to","title":"F-ViTA: Foundation Model Guided Visible to Thermal Translation","date":"2025-04-03","arxiv_id":"2504.02801","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-imgeval-a-comprehensive-benchmark-for","slug":"gpt-imgeval-a-comprehensive-benchmark-for","title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","date":"2025-04-03","arxiv_id":"2504.02782","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graph-completion-with-mixed","slug":"knowledge-graph-completion-with-mixed","title":"Knowledge Graph Completion with Mixed Geometry Tensor Factorization","date":"2025-04-03","arxiv_id":"2504.02589","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-to-real-self-supervised-robust","slug":"synthetic-to-real-self-supervised-robust","title":"Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors","date":"2025-03-26","arxiv_id":"2503.20211","repositories_listed":1,"syntology":null},{"url":"/paper/llm-based-agent-simulation-for-maternal","slug":"llm-based-agent-simulation-for-maternal","title":"LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation","date":"2025-03-25","arxiv_id":"2503.22719","repositories_listed":1,"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":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-based-agent-simulation-for-maternal#ran","syntology_url":"https://syntology.ai/paper/2503.22719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22719"}},"official":{"repos":["sarahmart/llm-abs-armman-prediction"],"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/exploiting-diffusion-prior-for-real-world-1","slug":"exploiting-diffusion-prior-for-real-world-1","title":"Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training","date":"2025-03-19","arxiv_id":"2503.15017","repositories_listed":1,"syntology":null},{"url":"/paper/fusdreamer-label-efficient-remote-sensing","slug":"fusdreamer-label-efficient-remote-sensing","title":"FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification","date":"2025-03-18","arxiv_id":"2503.13814","repositories_listed":1,"syntology":null},{"url":"/paper/free-form-language-based-robotic-reasoning","slug":"free-form-language-based-robotic-reasoning","title":"Free-form language-based robotic reasoning and grasping","date":"2025-03-17","arxiv_id":"2503.13082","repositories_listed":1,"syntology":null},{"url":"/paper/who-relies-more-on-world-knowledge-and-bias","slug":"who-relies-more-on-world-knowledge-and-bias","title":"Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?","date":"2025-03-13","arxiv_id":"2503.10838","repositories_listed":1,"syntology":null},{"url":"/paper/pointvla-injecting-the-3d-world-into-vision","slug":"pointvla-injecting-the-3d-world-into-vision","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","date":"2025-03-10","arxiv_id":"2503.07511","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pointvla-injecting-the-3d-world-into-vision#ran","syntology_url":"https://syntology.ai/paper/2503.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07511"}},"official":null}},{"url":"/paper/fact-or-fair-a-checklist-for-behavioral","slug":"fact-or-fair-a-checklist-for-behavioral","title":"Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries","date":"2025-02-09","arxiv_id":"2502.05849","repositories_listed":1,"syntology":null},{"url":"/paper/hermes-a-unified-self-driving-world-model-for","slug":"hermes-a-unified-self-driving-world-model-for","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","date":"2025-01-24","arxiv_id":"2501.14729","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/hermes-a-unified-self-driving-world-model-for#ran","syntology_url":"https://syntology.ai/paper/2501.14729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14729"}},"official":{"repos":["lmd0311/hermes"],"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/condor-enhance-llm-alignment-with-knowledge","slug":"condor-enhance-llm-alignment-with-knowledge","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","date":"2025-01-21","arxiv_id":"2501.12273","repositories_listed":1,"syntology":null},{"url":"/paper/voxeval-benchmarking-the-knowledge","slug":"voxeval-benchmarking-the-knowledge","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","date":"2025-01-09","arxiv_id":"2501.04962","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voxeval-benchmarking-the-knowledge#ran","syntology_url":"https://syntology.ai/paper/2501.04962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04962"}},"official":{"repos":["dreamtheater123/voxeval"],"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/cold-start-recommendation-towards-the-era-of","slug":"cold-start-recommendation-towards-the-era-of","title":"Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap","date":"2025-01-03","arxiv_id":"2501.01945","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-hybrid-segmentation-assistant-with","slug":"hyperseg-hybrid-segmentation-assistant-with","title":"HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-automatic-graph-construction-framework","slug":"an-automatic-graph-construction-framework","title":"An Automatic Graph Construction Framework based on Large Language Models for Recommendation","date":"2024-12-24","arxiv_id":"2412.18241","repositories_listed":1,"syntology":null},{"url":"/paper/interweaving-memories-of-a-siamese-large","slug":"interweaving-memories-of-a-siamese-large","title":"Interweaving Memories of a Siamese Large Language Model","date":"2024-12-23","arxiv_id":"2412.17383","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-editing-through-chain-of-thought","slug":"knowledge-editing-through-chain-of-thought","title":"Knowledge Editing through Chain-of-Thought","date":"2024-12-23","arxiv_id":"2412.17727","repositories_listed":1,"syntology":null},{"url":"/paper/fietje-an-open-efficient-llm-for-dutch","slug":"fietje-an-open-efficient-llm-for-dutch","title":"Fietje: An open, efficient LLM for Dutch","date":"2024-12-19","arxiv_id":"2412.15450","repositories_listed":1,"syntology":null},{"url":"/paper/mmlu-cf-a-contamination-free-multi-task","slug":"mmlu-cf-a-contamination-free-multi-task","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","date":"2024-12-19","arxiv_id":"2412.15194","repositories_listed":1,"syntology":null},{"url":"/paper/antileak-bench-preventing-data-contamination","slug":"antileak-bench-preventing-data-contamination","title":"AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge","date":"2024-12-18","arxiv_id":"2412.13670","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"12 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/antileak-bench-preventing-data-contamination#ran","syntology_url":"https://syntology.ai/paper/2412.13670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13670"}},"official":{"repos":["bobxwu/antileak-bench"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-user-side-knowledge-gap-in","slug":"bridging-the-user-side-knowledge-gap-in","title":"Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models","date":"2024-12-18","arxiv_id":"2412.13544","repositories_listed":1,"syntology":null},{"url":"/paper/quench-measuring-the-gap-between-indic-and","slug":"quench-measuring-the-gap-between-indic-and","title":"QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs","date":"2024-12-16","arxiv_id":"2412.11763","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-to-non-stationary-environments-multi","slug":"adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","date":"2024-12-10","arxiv_id":"2412.07618","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adapting-to-non-stationary-environments-multi#ran","syntology_url":"https://syntology.ai/paper/2412.07618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07618"}},"official":{"repos":["futureeeeee/dynamic-rag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/i-don-t-know-explicit-modeling-of-uncertainty","slug":"i-don-t-know-explicit-modeling-of-uncertainty","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","date":"2024-12-09","arxiv_id":"2412.06676","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/i-don-t-know-explicit-modeling-of-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2412.06676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06676"}},"official":{"repos":["roi-hpi/IDK-token-tuning"],"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/retrieval-augmented-machine-translation-with","slug":"retrieval-augmented-machine-translation-with","title":"Retrieval-Augmented Machine Translation with Unstructured Knowledge","date":"2024-12-05","arxiv_id":"2412.04342","repositories_listed":1,"syntology":null},{"url":"/paper/a-surprisal-oracle-for-when-every-layer","slug":"a-surprisal-oracle-for-when-every-layer","title":"A surprisal oracle for when every layer counts","date":"2024-12-04","arxiv_id":"2412.03098","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm2clip-powerful-language-model-unlock","slug":"llm2clip-powerful-language-model-unlock","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation","date":"2024-11-07","arxiv_id":"2411.04997","repositories_listed":1,"syntology":null},{"url":"/paper/chatsearch-a-dataset-and-a-generative","slug":"chatsearch-a-dataset-and-a-generative","title":"ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval","date":"2024-10-24","arxiv_id":"2410.18715","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/chatsearch-a-dataset-and-a-generative#ran","syntology_url":"https://syntology.ai/paper/2410.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18715"}},"official":{"repos":["joez17/chatsearch"],"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/understanding-the-role-of-llms-in-multimodal","slug":"understanding-the-role-of-llms-in-multimodal","title":"Understanding the Role of LLMs in Multimodal Evaluation Benchmarks","date":"2024-10-16","arxiv_id":"2410.12329","repositories_listed":1,"syntology":null},{"url":"/paper/livexiv-a-multi-modal-live-benchmark-based-on","slug":"livexiv-a-multi-modal-live-benchmark-based-on","title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","date":"2024-10-14","arxiv_id":"2410.10783","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":4,"n_instrument":13,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"17 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; 13 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/livexiv-a-multi-modal-live-benchmark-based-on#ran","syntology_url":"https://syntology.ai/paper/2410.10783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10783"}},"official":{"repos":["nimrodshabtay/livexiv"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dyvo-dynamic-vocabularies-for-learned-sparse","slug":"dyvo-dynamic-vocabularies-for-learned-sparse","title":"DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities","date":"2024-10-10","arxiv_id":"2410.07722","repositories_listed":1,"syntology":null},{"url":"/paper/llm-embeddings-improve-test-time-adaptation","slug":"llm-embeddings-improve-test-time-adaptation","title":"LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts","date":"2024-10-09","arxiv_id":"2410.07395","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-embeddings-improve-test-time-adaptation#ran","syntology_url":"https://syntology.ai/paper/2410.07395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07395"}},"official":{"repos":["namkoong-lab/llm-tabular-shifts"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/which-programming-language-and-what-features","slug":"which-programming-language-and-what-features","title":"Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?","date":"2024-10-09","arxiv_id":"2410.06735","repositories_listed":1,"syntology":null},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 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; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/curricullm-automatic-task-curricula-design","slug":"curricullm-automatic-task-curricula-design","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models","date":"2024-09-27","arxiv_id":"2409.18382","repositories_listed":1,"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":2,"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/curricullm-automatic-task-curricula-design#ran","syntology_url":"https://syntology.ai/paper/2409.18382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18382"}},"official":{"repos":["labicon/curricullm"],"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/pioneering-reliable-assessment-in-text-to","slug":"pioneering-reliable-assessment-in-text-to","title":"Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion","date":"2024-09-26","arxiv_id":"2409.17928","repositories_listed":1,"syntology":null},{"url":"/paper/style-over-substance-failure-modes-of-llm","slug":"style-over-substance-failure-modes-of-llm","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","date":"2024-09-23","arxiv_id":"2409.15268","repositories_listed":1,"syntology":null},{"url":"/paper/hllm-enhancing-sequential-recommendations-via","slug":"hllm-enhancing-sequential-recommendations-via","title":"HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling","date":"2024-09-19","arxiv_id":"2409.12740","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hllm-enhancing-sequential-recommendations-via#ran","syntology_url":"https://syntology.ai/paper/2409.12740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12740"}},"official":{"repos":["bytedance/hllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diversify-and-conquer-diversity-centric-data","slug":"diversify-and-conquer-diversity-centric-data","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement","date":"2024-09-17","arxiv_id":"2409.11378","repositories_listed":1,"syntology":null}],"syntology_records":45,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":142,"papers_where_code_ran_first_page":"/task/world-knowledge/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":9,"url":"/task/world-knowledge/papers/2","json":"/task/world-knowledge/papers/2.json","rows":100},{"order":"archive","page":3,"of":9,"url":"/task/world-knowledge/papers/3","json":"/task/world-knowledge/papers/3.json","rows":100},{"order":"archive","page":4,"of":9,"url":"/task/world-knowledge/papers/4","json":"/task/world-knowledge/papers/4.json","rows":100},{"order":"archive","page":5,"of":9,"url":"/task/world-knowledge/papers/5","json":"/task/world-knowledge/papers/5.json","rows":100},{"order":"archive","page":6,"of":9,"url":"/task/world-knowledge/papers/6","json":"/task/world-knowledge/papers/6.json","rows":100},{"order":"archive","page":7,"of":9,"url":"/task/world-knowledge/papers/7","json":"/task/world-knowledge/papers/7.json","rows":100},{"order":"archive","page":8,"of":9,"url":"/task/world-knowledge/papers/8","json":"/task/world-knowledge/papers/8.json","rows":100},{"order":"archive","page":9,"of":9,"url":"/task/world-knowledge/papers/9","json":"/task/world-knowledge/papers/9.json","rows":18},{"order":"ran","page":1,"of":2,"url":"/task/world-knowledge/papers/ran/1","json":"/task/world-knowledge/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/world-knowledge/papers/ran/2","json":"/task/world-knowledge/papers/ran/2.json","rows":42}],"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":"7f7d2dff4d759c242dfdebb8add4a63fcd942dbec75d527a62eff090bdb5ca85","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}