{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/load-file","entry":"load_file","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":52,"n_papers_ran":20,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":56,"n_samples_ran":25,"n_samples_fingerprinted":2,"n_places":61,"n_places_pointer_only":13,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":0,"ran":19,"unverified":31},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.00845","paper":"/paper/arxiv-2609-00845","title":"Towards Generalizable Visually Grounded Exploration of Household Devices","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"BITHLP/VGEBench","path":"bench_close.py","file_url":"https://github.com/BITHLP/VGEBench/blob/HEAD/bench_close.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6307f0bd2bc005c3","mcp_get_code":{"code_sha256":"6307f0bd2bc005c3"}},{"arxiv_id":"2605.14888","paper":"/paper/arxiv-2605-14888","title":"PROCESS-2: A Benchmark Speech Corpus for Early Cognitive Impairment Detection","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CognoSpeak/PROCESS-2","path":"codes/PROCESS2_gen_ASR.py","file_url":"https://github.com/CognoSpeak/PROCESS-2/blob/HEAD/codes/PROCESS2_gen_ASR.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2781e9bddcced61d","mcp_get_code":{"code_sha256":"2781e9bddcced61d"}},{"arxiv_id":"2603.19532","paper":"/paper/arxiv-2603-19532","title":"EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Wizaaard/EvidenceRL","path":"plot_accuracy_vs_grounding.py","file_url":"https://github.com/Wizaaard/EvidenceRL/blob/HEAD/plot_accuracy_vs_grounding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b815bf26e194b0d1","mcp_get_code":{"code_sha256":"b815bf26e194b0d1"}},{"arxiv_id":"2512.03262","paper":"/paper/arxiv-2512-03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"LeiLiLab/susvibes","path":"susvibes/core/utils.py","file_url":"https://github.com/LeiLiLab/susvibes/blob/HEAD/susvibes/core/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"baf788c2a03567da","mcp_get_code":{"code_sha256":"baf788c2a03567da"}},{"arxiv_id":"2507.01299","paper":null,"title":"arXiv:2507.01299","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"alibaba/EfficientAI","path":"dcore/paper/cal_bfcl_lazy_reasoning.py","file_url":"https://github.com/alibaba/EfficientAI/blob/HEAD/dcore/paper/cal_bfcl_lazy_reasoning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"79c9821f6b80fb79","mcp_get_code":{"code_sha256":"79c9821f6b80fb79"}},{"arxiv_id":"2503.05244","paper":"/paper/writingbench-a-comprehensive-benchmark-for","title":"WritingBench: A Comprehensive Benchmark for Generative Writing","date":"2025-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"X-PLUG/WritingBench","path":"generate_response.py","file_url":"https://github.com/X-PLUG/WritingBench/blob/HEAD/generate_response.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1321e6d2e53e2bb3","mcp_get_code":{"code_sha256":"1321e6d2e53e2bb3"}},{"arxiv_id":"2411.04165","paper":"/paper/bio-xlstm-generative-modeling-representation","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/chem-xlstm","path":"chemxlstm/evaluate_cond_gen.py","file_url":"https://github.com/ml-jku/chem-xlstm/blob/HEAD/chemxlstm/evaluate_cond_gen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4208c567af7da5a8","mcp_get_code":{"code_sha256":"4208c567af7da5a8"}},{"arxiv_id":"2408.15126","paper":"/paper/force-guided-bridge-matching-for-full-atom","title":"Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaledeus/fbm","path":"simulation.py","file_url":"https://github.com/yaledeus/fbm/blob/HEAD/simulation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e702804326de3c90","mcp_get_code":{"code_sha256":"e702804326de3c90"}},{"arxiv_id":"2407.16434","paper":"/paper/enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/struxgpt","path":"src/utils/io.py","file_url":"https://github.com/alibaba/struxgpt/blob/HEAD/src/utils/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"899ae94e2516fc8c","mcp_get_code":{"code_sha256":"899ae94e2516fc8c"}},{"arxiv_id":"2405.06672","paper":"/paper/liouville-flow-importance-sampler","title":"Liouville Flow Importance Sampler","date":"2024-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lanl/lfis","path":"src/LFIS/util/util.py","file_url":"https://github.com/lanl/lfis/blob/HEAD/src/LFIS/util/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2ae8603411483e26","mcp_get_code":{"code_sha256":"2ae8603411483e26"}},{"arxiv_id":"2404.12753","paper":"/paper/autocrawler-a-progressive-understanding-web","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation","date":"2024-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EZ-hwh/AutoScraper","path":"crawler_count.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/crawler_count.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"94f6df3aa62d12ec","mcp_get_code":{"code_sha256":"94f6df3aa62d12ec"}},{"arxiv_id":"2404.12753","paper":"/paper/autocrawler-a-progressive-understanding-web","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation","date":"2024-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EZ-hwh/AutoScraper","path":"run_swde/evaluate.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/run_swde/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"93cc6e204a2d564e","mcp_get_code":{"code_sha256":"93cc6e204a2d564e"}},{"arxiv_id":"2404.04125","paper":"/paper/no-zero-shot-without-exponential-data","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bethgelab/frequency_determines_performance","path":"src/text_search_inverted_index_combine_dictionaries.py","file_url":"https://github.com/bethgelab/frequency_determines_performance/blob/HEAD/src/text_search_inverted_index_combine_dictionaries.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"426e1eb7406a069c","mcp_get_code":{"code_sha256":"426e1eb7406a069c"}},{"arxiv_id":"2404.00599","paper":"/paper/evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/evocodebench","path":"gpt_inference.py","file_url":"https://github.com/seketeam/evocodebench/blob/HEAD/gpt_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d6407246571e12e2","mcp_get_code":{"code_sha256":"d6407246571e12e2"}},{"arxiv_id":"2403.10967","paper":"/paper/dreaming-of-many-worlds-learning-contextual","title":"Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization","date":"2024-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sai-prasanna/dreaming_of_many_worlds","path":"eval_utils/eval_script.py","file_url":"https://github.com/sai-prasanna/dreaming_of_many_worlds/blob/HEAD/eval_utils/eval_script.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a93c90885a6fd3ec","mcp_get_code":{"code_sha256":"a93c90885a6fd3ec"}},{"arxiv_id":"2403.06845","paper":"/paper/drivedreamer-2-llm-enhanced-world-models-for","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"f1yfisher/drivedreamer2","path":"dreamer-train/dreamer_train/configs/config.py","file_url":"https://github.com/f1yfisher/drivedreamer2/blob/HEAD/dreamer-train/dreamer_train/configs/config.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2be7756925318d0b","mcp_get_code":{"code_sha256":"2be7756925318d0b"}},{"arxiv_id":"2402.12560","paper":"/paper/causalgym-benchmarking-causal","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aryamanarora/causalgym","path":"plot.py","file_url":"https://github.com/aryamanarora/causalgym/blob/HEAD/plot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42202b44c1ae3c17","mcp_get_code":{"code_sha256":"42202b44c1ae3c17"}},{"arxiv_id":"2401.17377","paper":"/paper/infini-gram-scaling-unbounded-n-gram-language","title":"Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens","date":"2024-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujch1998/infini-gram","path":"pkg/infini_gram/indexing.py","file_url":"https://github.com/liujch1998/infini-gram/blob/HEAD/pkg/infini_gram/indexing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2bbf95349db18608","mcp_get_code":{"code_sha256":"2bbf95349db18608"}},{"arxiv_id":"2401.17377","paper":"/paper/infini-gram-scaling-unbounded-n-gram-language","title":"Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens","date":"2024-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujch1998/infini-gram","path":"pkg/infini_gram/indexing_v6.py","file_url":"https://github.com/liujch1998/infini-gram/blob/HEAD/pkg/infini_gram/indexing_v6.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ef980fcf78d59ffe","mcp_get_code":{"code_sha256":"ef980fcf78d59ffe"}},{"arxiv_id":"2312.09536","paper":"/paper/riveter-measuring-power-and-social-dynamics","title":"Riveter: Measuring Power and Social Dynamics Between Entities","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/neuralcoref","path":"neuralcoref/train/conllparser.py","file_url":"https://github.com/huggingface/neuralcoref/blob/HEAD/neuralcoref/train/conllparser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7604c292d6409a3","mcp_get_code":{"code_sha256":"a7604c292d6409a3"}},{"arxiv_id":"2311.01734","paper":"/paper/mixcon3d-synergizing-multi-view-and-cross","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-vlaa/mixcon3d","path":"src/models/Minkowski_resnet.py","file_url":"https://github.com/ucsc-vlaa/mixcon3d/blob/HEAD/src/models/Minkowski_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"460808fbce44a8d8","mcp_get_code":{"code_sha256":"460808fbce44a8d8"}},{"arxiv_id":"2311.00288","paper":"/paper/active-instruction-tuning-improving-cross","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pluslabnlp/active-it","path":"ActiveIT/my_scripts/write_cls_split_into_tasks.py","file_url":"https://github.com/pluslabnlp/active-it/blob/HEAD/ActiveIT/my_scripts/write_cls_split_into_tasks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44fc237ca08b7b18","mcp_get_code":{"code_sha256":"44fc237ca08b7b18"}},{"arxiv_id":"2310.20329","paper":"/paper/instructcoder-empowering-language-models-for","title":"InstructCoder: Instruction Tuning Large Language Models for Code Editing","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qishenghu/CodeInstruct","path":"src/generate_instance.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/generate_instance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0bdcc7c326efa00","mcp_get_code":{"code_sha256":"c0bdcc7c326efa00"}},{"arxiv_id":"2310.18440","paper":"/paper/modeling-legal-reasoning-lm-annotation-at-the","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosthalken/legal-interpretation","path":"create_samples.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/create_samples.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a7eceaef502e02c","mcp_get_code":{"code_sha256":"6a7eceaef502e02c"}},{"arxiv_id":"2310.18440","paper":"/paper/modeling-legal-reasoning-lm-annotation-at-the","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosthalken/legal-interpretation","path":"prep_predictions.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/prep_predictions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ea6699b44cb0d86","mcp_get_code":{"code_sha256":"7ea6699b44cb0d86"}},{"arxiv_id":"2310.18349","paper":"/paper/a-boundary-offset-prediction-network-for","title":"A Boundary Offset Prediction Network for Named Entity Recognition","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mhtang1995/bopn","path":"src/utils.py","file_url":"https://github.com/mhtang1995/bopn/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8eb5a65e9cf29c87","mcp_get_code":{"code_sha256":"8eb5a65e9cf29c87"}},{"arxiv_id":"2310.14037","paper":"/paper/unlock-multi-modal-capability-of-dense","title":"MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/marvel","path":"ANCE/data.py","file_url":"https://github.com/openmatch/marvel/blob/HEAD/ANCE/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b334283bb59e66d0","mcp_get_code":{"code_sha256":"b334283bb59e66d0"}},{"arxiv_id":"2310.14037","paper":"/paper/unlock-multi-modal-capability-of-dense","title":"MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/marvel","path":"ANCE/retrieval.py","file_url":"https://github.com/openmatch/marvel/blob/HEAD/ANCE/retrieval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d71b15e3f71f7d11","mcp_get_code":{"code_sha256":"d71b15e3f71f7d11"}},{"arxiv_id":"2310.14037","paper":"/paper/unlock-multi-modal-capability-of-dense","title":"MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/marvel","path":"DPR/data.py","file_url":"https://github.com/openmatch/marvel/blob/HEAD/DPR/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc7b881120312440","mcp_get_code":{"code_sha256":"bc7b881120312440"}},{"arxiv_id":"2310.14037","paper":"/paper/unlock-multi-modal-capability-of-dense","title":"MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/marvel","path":"DPR/get_hard_negs_all.py","file_url":"https://github.com/openmatch/marvel/blob/HEAD/DPR/get_hard_negs_all.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"70926fb8a521dab4","mcp_get_code":{"code_sha256":"70926fb8a521dab4"}},{"arxiv_id":"2310.03780","paper":"/paper/automating-human-tutor-style-programming","title":"Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"machine-teaching-group/lak2024_gpt4-hints-gpt3.5val","path":"src/utils/IO_utils.py","file_url":"https://github.com/machine-teaching-group/lak2024_gpt4-hints-gpt3.5val/blob/HEAD/src/utils/IO_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb40912c4c110ea2","mcp_get_code":{"code_sha256":"fb40912c4c110ea2"}},{"arxiv_id":"2308.10855","paper":"/paper/lateval-an-interactive-llms-evaluation","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thukelab/lateval","path":"src/game.py","file_url":"https://github.com/thukelab/lateval/blob/HEAD/src/game.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d9140c3ef7f275d4","mcp_get_code":{"code_sha256":"d9140c3ef7f275d4"}},{"arxiv_id":"2308.07286","paper":"/paper/the-devil-is-in-the-errors-leveraging-large","title":"The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuuhuang/lost_in_the_src","path":"automqm/llm_ppl.py","file_url":"https://github.com/xuuhuang/lost_in_the_src/blob/HEAD/automqm/llm_ppl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fa0d7896f0984c2","mcp_get_code":{"code_sha256":"4fa0d7896f0984c2"}},{"arxiv_id":"2307.03067","paper":"/paper/deeponto-a-python-package-for-ontology","title":"DeepOnto: A Python Package for Ontology Engineering with Deep Learning","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KRR-Oxford/DeepOnto","path":"src/deeponto/utils/file_utils.py","file_url":"https://github.com/KRR-Oxford/DeepOnto/blob/HEAD/src/deeponto/utils/file_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"307b5ecd9046ae51","mcp_get_code":{"code_sha256":"307b5ecd9046ae51"}},{"arxiv_id":"2306.16324","paper":"/paper/dosediff-distance-aware-diffusion-model-for","title":"DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy","date":"2023-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whisney/dosediff","path":"csv2nii.py","file_url":"https://github.com/whisney/dosediff/blob/HEAD/csv2nii.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"98a36741b705a3e9","mcp_get_code":{"code_sha256":"98a36741b705a3e9"}},{"arxiv_id":"2305.10764","paper":"/paper/openshape-scaling-up-3d-shape-representation-1","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Colin97/OpenShape_code","path":"src/models/Minkowski_resnet.py","file_url":"https://github.com/Colin97/OpenShape_code/blob/HEAD/src/models/Minkowski_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"460808fbce44a8d8","mcp_get_code":{"code_sha256":"460808fbce44a8d8"}},{"arxiv_id":"2305.03510","paper":"/paper/parameter-efficient-cross-lingual-transfer-of","title":"Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment","date":"2023-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/pectvlm","path":"align_from_to_en/load_datasets.py","file_url":"https://github.com/eric-ai-lab/pectvlm/blob/HEAD/align_from_to_en/load_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ff52d229e19a87e","mcp_get_code":{"code_sha256":"8ff52d229e19a87e"}},{"arxiv_id":"2210.12553","paper":"/paper/understanding-domain-learning-in-language","title":"Understanding Domain Learning in Language Models Through Subpopulation Analysis","date":"2022-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zsquaredz/subpopulation_analysis","path":"code/preprocess/utils.py","file_url":"https://github.com/zsquaredz/subpopulation_analysis/blob/HEAD/code/preprocess/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"41bedd34dd92f3bb","mcp_get_code":{"code_sha256":"41bedd34dd92f3bb"}},{"arxiv_id":"2209.00179","paper":"/paper/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/univl-dr","path":"UniVL-DR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"657a1b13e0907d5f","mcp_get_code":{"code_sha256":"657a1b13e0907d5f"}},{"arxiv_id":"2209.00179","paper":"/paper/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/univl-dr","path":"UniVL-DR/retrieval.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/UniVL-DR/retrieval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab52e35a4aeb0fdd","mcp_get_code":{"code_sha256":"ab52e35a4aeb0fdd"}},{"arxiv_id":"2209.00179","paper":"/paper/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/univl-dr","path":"CLIP-DPR/data.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/CLIP-DPR/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03524f1126e7841f","mcp_get_code":{"code_sha256":"03524f1126e7841f"}},{"arxiv_id":"2209.00179","paper":"/paper/universal-multi-modality-retrieval-with-one","title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/univl-dr","path":"CLIP-DPR/get_hard_negs.py","file_url":"https://github.com/openmatch/univl-dr/blob/HEAD/CLIP-DPR/get_hard_negs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10874e9329daa92e","mcp_get_code":{"code_sha256":"10874e9329daa92e"}},{"arxiv_id":"2205.14895","paper":"/paper/from-representation-to-reasoning-towards-both","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","date":"2022-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcmi/Causal-VidQA","path":"utils.py","file_url":"https://github.com/bcmi/Causal-VidQA/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e649c25c10f968ce","mcp_get_code":{"code_sha256":"e649c25c10f968ce"}},{"arxiv_id":"2205.10400","paper":"/paper/multi2woz-a-robust-multilingual-dataset-and-1","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","date":"2022-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umanlp/Multi2WOZ","path":"LangOpenSubtitles/concat_files.py","file_url":"https://github.com/umanlp/Multi2WOZ/blob/HEAD/LangOpenSubtitles/concat_files.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d33955d7249e9bc","mcp_get_code":{"code_sha256":"0d33955d7249e9bc"}},{"arxiv_id":"2202.08303","paper":"/paper/openkbp-opt-an-international-and-reproducible","title":"OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ababier/open-kbp-opt","path":"provided_code/general_functions.py","file_url":"https://github.com/ababier/open-kbp-opt/blob/HEAD/provided_code/general_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aff645c77a21ad8","mcp_get_code":{"code_sha256":"6aff645c77a21ad8"}},{"arxiv_id":"2202.07282","paper":"/paper/adaptive-conformal-predictions-for-time","title":"Adaptive Conformal Predictions for Time Series","date":"2022-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mzaffran/adaptiveconformalpredictionstimeseries","path":"files.py","file_url":"https://github.com/mzaffran/adaptiveconformalpredictionstimeseries/blob/HEAD/files.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87829a399740dc06","mcp_get_code":{"code_sha256":"87829a399740dc06"}},{"arxiv_id":"2112.06197","paper":"/paper/video-as-conditional-graph-hierarchy-for","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","date":"2021-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"doc-doc/hqga","path":"utils.py","file_url":"https://github.com/doc-doc/hqga/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e649c25c10f968ce","mcp_get_code":{"code_sha256":"e649c25c10f968ce"}},{"arxiv_id":"2105.08276","paper":"/paper/next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","date":"2021-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"doc-doc/NExT-QA","path":"utils.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e649c25c10f968ce","mcp_get_code":{"code_sha256":"e649c25c10f968ce"}},{"arxiv_id":"2008.07298","paper":"/paper/waffle-watermarking-in-federated-learning","title":"WAFFLE: Watermarking in Federated Learning","date":"2020-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssg-research/WAFFLE","path":"src/plot.py","file_url":"https://github.com/ssg-research/WAFFLE/blob/HEAD/src/plot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"716eed9846e231f8","mcp_get_code":{"code_sha256":"716eed9846e231f8"}},{"arxiv_id":"1910.13321","paper":"/paper/191013321","title":"Semantic Object Accuracy for Generative Text-to-Image Synthesis","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","path":"SOA/util.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce73ac36a39a4b99","mcp_get_code":{"code_sha256":"ce73ac36a39a4b99"}},{"arxiv_id":"1910.02527","paper":"/paper/3d-scene-graph-a-structure-for-unified","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","date":"2019-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StanfordVL/3DSceneGraph","path":"tools/load.py","file_url":"https://github.com/StanfordVL/3DSceneGraph/blob/HEAD/tools/load.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2d6a8cfe58a578bc","mcp_get_code":{"code_sha256":"2d6a8cfe58a578bc"}},{"arxiv_id":"1906.00830","paper":"/paper/190600830","title":"DAWN: Dynamic Adversarial Watermarking of Neural Networks","date":"2019-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ssg-research/dawn-dynamic-adversarial-watermarking-of-neural-networks","path":"noisy_verification.py","file_url":"https://github.com/ssg-research/dawn-dynamic-adversarial-watermarking-of-neural-networks/blob/HEAD/noisy_verification.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"de2fdb2904611ccb","mcp_get_code":{"code_sha256":"de2fdb2904611ccb"}},{"arxiv_id":"1904.08755","paper":"/paper/4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/MinkowskiEngine","path":"examples/indoor.py","file_url":"https://github.com/NVIDIA/MinkowskiEngine/blob/HEAD/examples/indoor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"460808fbce44a8d8","mcp_get_code":{"code_sha256":"460808fbce44a8d8"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benywon/ComQA","path":"utils.py","file_url":"https://github.com/benywon/ComQA/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"30636ab752ebf9b0","mcp_get_code":{"code_sha256":"30636ab752ebf9b0"}},{"arxiv_id":"1805.10966","paper":"/paper/lifelong-learning-of-spatiotemporal","title":"Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization","date":"2018-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giparisi/GDM","path":"gtls.py","file_url":"https://github.com/giparisi/GDM/blob/HEAD/gtls.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bcff111584386fc","mcp_get_code":{"code_sha256":"7bcff111584386fc"}},{"arxiv_id":"aaai_5584","paper":null,"title":"arXiv:aaai_5584","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"martinlackner/perpetual","path":"file_loader.py","file_url":"https://github.com/martinlackner/perpetual/blob/HEAD/file_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6bf102558ef6ab5","mcp_get_code":{"code_sha256":"e6bf102558ef6ab5"}},{"arxiv_id":"2025.findings-acl.949","paper":null,"title":"arXiv:2025.findings-acl.949","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"renjie3/GRUN","path":"grun_wdmp_eval_mcq.py","file_url":"https://github.com/renjie3/GRUN/blob/HEAD/grun_wdmp_eval_mcq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b96c2e4b55fd5a75","mcp_get_code":{"code_sha256":"b96c2e4b55fd5a75"}},{"arxiv_id":"2025.emnlp-main.192","paper":null,"title":"arXiv:2025.emnlp-main.192","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"FreedomIntelligence/RAG-Instruct","path":"eval/eval_sglang.py","file_url":"https://github.com/FreedomIntelligence/RAG-Instruct/blob/HEAD/eval/eval_sglang.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cc9d641ec0d314e8","mcp_get_code":{"code_sha256":"cc9d641ec0d314e8"}},{"arxiv_id":"2025.acl-long.1425","paper":null,"title":"arXiv:2025.acl-long.1425","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"D2I-ai/struxgpt","path":"src/utils/io.py","file_url":"https://github.com/D2I-ai/struxgpt/blob/HEAD/src/utils/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"899ae94e2516fc8c","mcp_get_code":{"code_sha256":"899ae94e2516fc8c"}},{"arxiv_id":"2024.naacl-long.343","paper":null,"title":"arXiv:2024.naacl-long.343","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"king-yyf/CMeKG_tools","path":"utils.py","file_url":"https://github.com/king-yyf/CMeKG_tools/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"938b3e3386bd747d","mcp_get_code":{"code_sha256":"938b3e3386bd747d"}},{"arxiv_id":"2023.acl-long.139","paper":null,"title":"arXiv:2023.acl-long.139","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TIAN-viola/DynRT","path":"clean_dataset.py","file_url":"https://github.com/TIAN-viola/DynRT/blob/HEAD/clean_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0d49e997726edd6","mcp_get_code":{"code_sha256":"c0d49e997726edd6"}}]}