{"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/eval-model","entry":"eval_model","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":45,"n_papers_ran":17,"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":49,"n_samples_ran":17,"n_samples_fingerprinted":0,"n_places":50,"n_places_pointer_only":14,"by_status":{"ran_honours":8,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":6,"unverified":32},"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":"2605.13981","paper":"/paper/arxiv-2605-13981","title":"Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"StellarLuminosity/Energy","path":"distill_bench/pipelines/sft_main.py","file_url":"https://github.com/StellarLuminosity/Energy/blob/HEAD/distill_bench/pipelines/sft_main.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a3c4618734a7e045","mcp_get_code":{"code_sha256":"a3c4618734a7e045"}},{"arxiv_id":"2604.12479","paper":"/paper/arxiv-2604-12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"nrimsky/CAA","path":"finetune_llama.py","file_url":"https://github.com/nrimsky/CAA/blob/HEAD/finetune_llama.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88c6a4e2feade29f","mcp_get_code":{"code_sha256":"88c6a4e2feade29f"}},{"arxiv_id":"2602.17171","paper":"/paper/arxiv-2602-17171","title":"In-Context Learning in Linear vs. Quadratic Attention Models: An Empirical Study on Regression Tasks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Yushgoel/icl-benchmarking","path":"src/training/evaluator.py","file_url":"https://github.com/Yushgoel/icl-benchmarking/blob/HEAD/src/training/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2ca88cb8c3b44083","mcp_get_code":{"code_sha256":"2ca88cb8c3b44083"}},{"arxiv_id":"2601.16880","paper":"/paper/arxiv-2601-16880","title":"Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"evansbeth/backdoor_attack","path":"Backdoor/classifier_layer_bound_2.py","file_url":"https://github.com/evansbeth/backdoor_attack/blob/HEAD/Backdoor/classifier_layer_bound_2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b0e67531ca594321","mcp_get_code":{"code_sha256":"b0e67531ca594321"}},{"arxiv_id":"2601.12587","paper":"/paper/arxiv-2601-12587","title":"A theory of diversity for random matrices with applications to in-context learning of Schrödinger equations","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"LuGroupUMN/Diversity-of-random-matrices","path":"utils/train_utils.py","file_url":"https://github.com/LuGroupUMN/Diversity-of-random-matrices/blob/HEAD/utils/train_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd03e16bd418e81b","mcp_get_code":{"code_sha256":"dd03e16bd418e81b"}},{"arxiv_id":"2505.19932","paper":"/paper/logic-gate-neural-networks-are-good-for","title":"Logic Gate Neural Networks are Good for Verification","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HyberionBrew/difflogic_verify","path":"train_model.py","file_url":"https://github.com/HyberionBrew/difflogic_verify/blob/HEAD/train_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db7f2c73ccce434f","mcp_get_code":{"code_sha256":"db7f2c73ccce434f"}},{"arxiv_id":"2501.06252","paper":"/paper/text-transformer-2-self-adaptive-llms","title":"Transformer-Squared: Self-adaptive LLMs","date":"2025-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SakanaAI/self-adaptive-llms","path":"utils.py","file_url":"https://github.com/SakanaAI/self-adaptive-llms/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":"dde83d263378109c","mcp_get_code":{"code_sha256":"dde83d263378109c"}},{"arxiv_id":"2412.12359","paper":"/paper/visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bibisbar/LLaVA-Steering","path":"tinyllava/eval/model_vqa_halbench.py","file_url":"https://github.com/bibisbar/LLaVA-Steering/blob/HEAD/tinyllava/eval/model_vqa_halbench.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":"3289beb8d4bdf12b","mcp_get_code":{"code_sha256":"3289beb8d4bdf12b"}},{"arxiv_id":"2412.12359","paper":"/paper/visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bibisbar/LLaVA-Steering","path":"tinyllava/eval/model_vqa_mmhal.py","file_url":"https://github.com/bibisbar/LLaVA-Steering/blob/HEAD/tinyllava/eval/model_vqa_mmhal.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":"b449ac23f340f344","mcp_get_code":{"code_sha256":"b449ac23f340f344"}},{"arxiv_id":"2410.00485","paper":"/paper/a-hitchhikers-guide-to-fine-grained-face","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NickyFot/HitchhikersGuide","path":"train_utils.py","file_url":"https://github.com/NickyFot/HitchhikersGuide/blob/HEAD/train_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":"9270af9735eeeb5e","mcp_get_code":{"code_sha256":"9270af9735eeeb5e"}},{"arxiv_id":"2408.05446","paper":"/paper/ensemble-everything-everywhere-multi-scale","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ETH-DISCO/self-ensembling","path":"2-self-ensemble/self_ensemble.py","file_url":"https://github.com/ETH-DISCO/self-ensembling/blob/HEAD/2-self-ensemble/self_ensemble.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"0d4c870ca9878659","mcp_get_code":{"code_sha256":"0d4c870ca9878659"}},{"arxiv_id":"2407.08762","paper":"/paper/commute-time-optimised-graphs-for-gnns","title":"Commute-Time-Optimised Graphs for GNNs","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"igorsterner/commute-opt-gnn","path":"src/train_synthetic.py","file_url":"https://github.com/igorsterner/commute-opt-gnn/blob/HEAD/src/train_synthetic.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":"7ea0be7474f38668","mcp_get_code":{"code_sha256":"7ea0be7474f38668"}},{"arxiv_id":"2407.07544","paper":"/paper/disentangling-masked-autoencoders-for","title":"Disentangling Masked Autoencoders for Unsupervised Domain Generalization","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rookiehb/dismae","path":"engine_finetune.py","file_url":"https://github.com/rookiehb/dismae/blob/HEAD/engine_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc0ab280ae31a4ab","mcp_get_code":{"code_sha256":"cc0ab280ae31a4ab"}},{"arxiv_id":"2406.06248","paper":"/paper/compute-better-spent-replacing-dense-layers","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shikaiqiu/compute-better-spent","path":"model/fns.py","file_url":"https://github.com/shikaiqiu/compute-better-spent/blob/HEAD/model/fns.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":"4e894cdc17d93f2c","mcp_get_code":{"code_sha256":"4e894cdc17d93f2c"}},{"arxiv_id":"2405.19707","paper":"/paper/demamba-ai-generated-video-detection-on","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenhaoxing/DeMamba","path":"util.py","file_url":"https://github.com/chenhaoxing/DeMamba/blob/HEAD/util.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":"93be1c3f4d74a140","mcp_get_code":{"code_sha256":"93be1c3f4d74a140"}},{"arxiv_id":"2312.06681","paper":"/paper/steering-llama-2-via-contrastive-activation","title":"Steering Llama 2 via Contrastive Activation Addition","date":"2023-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nrimsky/sycophancysteering","path":"finetune_llama.py","file_url":"https://github.com/nrimsky/sycophancysteering/blob/HEAD/finetune_llama.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88c6a4e2feade29f","mcp_get_code":{"code_sha256":"88c6a4e2feade29f"}},{"arxiv_id":"2312.00752","paper":"/paper/mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thearkaprava/ms-temba","path":"vim/MSTemba_main.py","file_url":"https://github.com/thearkaprava/ms-temba/blob/HEAD/vim/MSTemba_main.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":"ad88c39d5b497053","mcp_get_code":{"code_sha256":"ad88c39d5b497053"}},{"arxiv_id":"2312.00276","paper":"/paper/automating-continual-learning","title":"Automating Continual Learning","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idsia/automated-cl","path":"utils_few_shot.py","file_url":"https://github.com/idsia/automated-cl/blob/HEAD/utils_few_shot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c71a4a7bae9d5f3","mcp_get_code":{"code_sha256":"6c71a4a7bae9d5f3"}},{"arxiv_id":"2310.12490","paper":"/paper/co-2-pt-mitigating-bias-in-pre-trained","title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongxiangjue/co2pt","path":"eval_bios.py","file_url":"https://github.com/dongxiangjue/co2pt/blob/HEAD/eval_bios.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":"c59d7bc602a19b78","mcp_get_code":{"code_sha256":"c59d7bc602a19b78"}},{"arxiv_id":"2310.07579","paper":"/paper/in-context-unlearning-language-models-as-few","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martinpawel/openunlearn","path":"openunlearn/unlearners/catalog/neg_grad_plus/neg_grad_plus.py","file_url":"https://github.com/martinpawel/openunlearn/blob/HEAD/openunlearn/unlearners/catalog/neg_grad_plus/neg_grad_plus.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"67b0cd2c25da8b69","mcp_get_code":{"code_sha256":"67b0cd2c25da8b69"}},{"arxiv_id":"2310.02093","paper":"/paper/stochastic-gradient-descent-with","title":"Stochastic Gradient Descent with Preconditioned Polyak Step-size","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fxrshed/scaledsps","path":"run_nn.py","file_url":"https://github.com/fxrshed/scaledsps/blob/HEAD/run_nn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bf9abf72409d634","mcp_get_code":{"code_sha256":"7bf9abf72409d634"}},{"arxiv_id":"2308.15673","paper":"/paper/mdtd-a-multi-domain-trojan-detector-for-deep","title":"MDTD: A Multi Domain Trojan Detector for Deep Neural Networks","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajabia/mdtd","path":"trainmodels.py","file_url":"https://github.com/rajabia/mdtd/blob/HEAD/trainmodels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f04f58d8c4d5473","mcp_get_code":{"code_sha256":"6f04f58d8c4d5473"}},{"arxiv_id":"2307.15700","paper":"/paper/memotr-long-term-memory-augmented-transformer","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mcg-nju/memotr","path":"eval_engine.py","file_url":"https://github.com/mcg-nju/memotr/blob/HEAD/eval_engine.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"871c3d5d01b0c75a","mcp_get_code":{"code_sha256":"871c3d5d01b0c75a"}},{"arxiv_id":"2307.09423","paper":"/paper/scaling-laws-for-imitation-learning-in","title":"Scaling Laws for Imitation Learning in Single-Agent Games","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/il-scaling-in-games","path":"il_scale/atari/eval_game.py","file_url":"https://github.com/princeton-nlp/il-scaling-in-games/blob/HEAD/il_scale/atari/eval_game.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5a77a04ba19bba16","mcp_get_code":{"code_sha256":"5a77a04ba19bba16"}},{"arxiv_id":"2212.10876","paper":"/paper/hyperparameters-in-contextual-rl-are-highly","title":"Hyperparameters in Contextual RL are Highly Situational","date":"2022-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"automl-private/crl_hpo","path":"cRL_HPO/run_pb2.py","file_url":"https://github.com/automl-private/crl_hpo/blob/HEAD/cRL_HPO/run_pb2.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"258d6c5cdb4f0623","mcp_get_code":{"code_sha256":"258d6c5cdb4f0623"}},{"arxiv_id":"2212.10876","paper":"/paper/hyperparameters-in-contextual-rl-are-highly","title":"Hyperparameters in Contextual RL are Highly Situational","date":"2022-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"automl-private/crl_hpo","path":"cRL_HPO/play_pb2.py","file_url":"https://github.com/automl-private/crl_hpo/blob/HEAD/cRL_HPO/play_pb2.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c73e6161af97557b","mcp_get_code":{"code_sha256":"c73e6161af97557b"}},{"arxiv_id":"2210.12918","paper":"/paper/unsupervised-object-representation-learning","title":"Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE","date":"2022-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smlc-nysbc/target-vae","path":"train_dsprites.py","file_url":"https://github.com/smlc-nysbc/target-vae/blob/HEAD/train_dsprites.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a0c4d1584fb072d5","mcp_get_code":{"code_sha256":"a0c4d1584fb072d5"}},{"arxiv_id":"2210.12918","paper":"/paper/unsupervised-object-representation-learning","title":"Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE","date":"2022-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smlc-nysbc/target-vae","path":"train_galaxy.py","file_url":"https://github.com/smlc-nysbc/target-vae/blob/HEAD/train_galaxy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9769b6fef90de4d5","mcp_get_code":{"code_sha256":"9769b6fef90de4d5"}},{"arxiv_id":"2207.04771","paper":"/paper/functional-generalized-empirical-likelihood","title":"Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions","date":"2022-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heinerkremer/functional-gel","path":"experiments/exp_heteroskedastic.py","file_url":"https://github.com/heinerkremer/functional-gel/blob/HEAD/experiments/exp_heteroskedastic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f20aede6409c0bb5","mcp_get_code":{"code_sha256":"f20aede6409c0bb5"}},{"arxiv_id":"2204.12632","paper":"/paper/testing-the-ability-of-language-models-to-1","title":"Testing the Ability of Language Models to Interpret Figurative Language","date":"2022-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simran-khanuja/multilingual-fig-qa","path":"run_baselines.py","file_url":"https://github.com/simran-khanuja/multilingual-fig-qa/blob/HEAD/run_baselines.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31e5d4061c0165ee","mcp_get_code":{"code_sha256":"31e5d4061c0165ee"}},{"arxiv_id":"2203.14434","paper":"/paper/risk-regularization-through-bidirectional","title":"Flexible risk design using bi-directional dispersion","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feedbackward/bdd","path":"bdd/setup_eval.py","file_url":"https://github.com/feedbackward/bdd/blob/HEAD/bdd/setup_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c481ddacab52025c","mcp_get_code":{"code_sha256":"c481ddacab52025c"}},{"arxiv_id":"2112.00652","paper":"/paper/graph-neural-networks-for-fast-electron","title":"Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids","date":"2021-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"peterbjorgensen/DeepDFT","path":"runner.py","file_url":"https://github.com/peterbjorgensen/DeepDFT/blob/HEAD/runner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"afa2f819f2fb255a","mcp_get_code":{"code_sha256":"afa2f819f2fb255a"}},{"arxiv_id":"2106.08283","paper":"/paper/crfl-certifiably-robust-federated-learning","title":"CRFL: Certifiably Robust Federated Learning against Backdoor Attacks","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI-secure/CRFL","path":"smooth_mnist.py","file_url":"https://github.com/AI-secure/CRFL/blob/HEAD/smooth_mnist.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":"4d7f485df31b3c02","mcp_get_code":{"code_sha256":"4d7f485df31b3c02"}},{"arxiv_id":"2105.04544","paper":"/paper/proximal-causal-learning-with-kernels-two","title":"Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction","date":"2021-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchen-zhu/kernel_proxies","path":"baselines_scripts/run_zoo_experiments_more_baselines.py","file_url":"https://github.com/yuchen-zhu/kernel_proxies/blob/HEAD/baselines_scripts/run_zoo_experiments_more_baselines.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"163994b7dab0dc19","mcp_get_code":{"code_sha256":"163994b7dab0dc19"}},{"arxiv_id":"2103.12242","paper":"/paper/f-siol-310-a-robotic-dataset-and-benchmark","title":"F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning","date":"2021-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aliayub7/cbcl-pr","path":"training_functions.py","file_url":"https://github.com/aliayub7/cbcl-pr/blob/HEAD/training_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c00ad285b324bd8","mcp_get_code":{"code_sha256":"3c00ad285b324bd8"}},{"arxiv_id":"2103.05091","paper":"/paper/learning-connectivity-for-data-distribution","title":"Learning Connectivity for Data Distribution in Robot Teams","date":"2021-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"landonbutler/Learning-Connectivity","path":"test_all.py","file_url":"https://github.com/landonbutler/Learning-Connectivity/blob/HEAD/test_all.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":"2b4b61da529b5231","mcp_get_code":{"code_sha256":"2b4b61da529b5231"}},{"arxiv_id":"2101.11214","paper":"/paper/towards-robustness-to-label-noise-in-text","title":"Towards Robustness to Label Noise in Text Classification via Noise Modeling","date":"2021-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thumbe3/label-noise-nlp","path":"train_classifier.py","file_url":"https://github.com/thumbe3/label-noise-nlp/blob/HEAD/train_classifier.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e0740f9258c4c0c","mcp_get_code":{"code_sha256":"2e0740f9258c4c0c"}},{"arxiv_id":"2007.13971","paper":"/paper/accurate-low-latency-visual-perception-for","title":"Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions","date":"2020-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cv-core/MIT-Driverless-CV-TrainingInfra","path":"RektNet/keypoint_tutorial_util.py","file_url":"https://github.com/cv-core/MIT-Driverless-CV-TrainingInfra/blob/HEAD/RektNet/keypoint_tutorial_util.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":"651a7b6fa2ae8d29","mcp_get_code":{"code_sha256":"651a7b6fa2ae8d29"}},{"arxiv_id":"2007.11142","paper":"/paper/flot-scene-flow-on-point-clouds-guided-by","title":"FLOT: Scene Flow on Point Clouds Guided by Optimal Transport","date":"2020-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/FLOT","path":"flot/scripts/val_test.py","file_url":"https://github.com/valeoai/FLOT/blob/HEAD/flot/scripts/val_test.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5c7237bcc1e3ea85","mcp_get_code":{"code_sha256":"5c7237bcc1e3ea85"}},{"arxiv_id":"2006.15408","paper":"/paper/learning-optimal-tree-models-under-beam","title":"Learning Optimal Tree Models Under Beam Search","date":"2020-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/x-deeplearning","path":"xdl-algorithm-solution/DIEN/script/model.py","file_url":"https://github.com/alibaba/x-deeplearning/blob/HEAD/xdl-algorithm-solution/DIEN/script/model.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":"88e3effeb58e908b","mcp_get_code":{"code_sha256":"88e3effeb58e908b"}},{"arxiv_id":"2006.03677","paper":"/paper/visual-transformers-token-based-image","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","date":"2020-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aws-samples/amazon-sagemaker-visual-transformer","path":"image-classification/code/vt-resnet-34.py","file_url":"https://github.com/aws-samples/amazon-sagemaker-visual-transformer/blob/HEAD/image-classification/code/vt-resnet-34.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"code_sha256_prefix":"4a3aa44eded8d09b","mcp_get_code":{"code_sha256":"4a3aa44eded8d09b"}},{"arxiv_id":"2002.04289","paper":"/paper/to-share-or-not-to-share-a-comprehensive","title":"To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing","date":"2020-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apourchot/to_share_or_not_to_share","path":"training.py","file_url":"https://github.com/apourchot/to_share_or_not_to_share/blob/HEAD/training.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf07dd413f297eb9","mcp_get_code":{"code_sha256":"cf07dd413f297eb9"}},{"arxiv_id":"1909.11663","paper":"/paper/explicitly-disentangling-image-content-from","title":"Explicitly disentangling image content from translation and rotation with spatial-VAE","date":"2019-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tbepler/spatial-VAE","path":"train_mnist.py","file_url":"https://github.com/tbepler/spatial-VAE/blob/HEAD/train_mnist.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"574e22e6718a6402","mcp_get_code":{"code_sha256":"574e22e6718a6402"}},{"arxiv_id":"1909.11663","paper":"/paper/explicitly-disentangling-image-content-from","title":"Explicitly disentangling image content from translation and rotation with spatial-VAE","date":"2019-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tbepler/spatial-VAE","path":"train_particles.py","file_url":"https://github.com/tbepler/spatial-VAE/blob/HEAD/train_particles.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ebc30d59ffdabf83","mcp_get_code":{"code_sha256":"ebc30d59ffdabf83"}},{"arxiv_id":"1909.11663","paper":"/paper/explicitly-disentangling-image-content-from","title":"Explicitly disentangling image content from translation and rotation with spatial-VAE","date":"2019-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tbepler/spatial-VAE","path":"train_galaxy.py","file_url":"https://github.com/tbepler/spatial-VAE/blob/HEAD/train_galaxy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ec7b29d649004d3","mcp_get_code":{"code_sha256":"3ec7b29d649004d3"}},{"arxiv_id":"1811.07039","paper":"/paper/combining-fact-extraction-and-verification","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","date":"2018-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"easonnie/combine-FEVER-NSMN","path":"src/nli/mesim_wn_simi_v1_3.py","file_url":"https://github.com/easonnie/combine-FEVER-NSMN/blob/HEAD/src/nli/mesim_wn_simi_v1_3.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75be915616e6844d","mcp_get_code":{"code_sha256":"75be915616e6844d"}},{"arxiv_id":"1808.09357","paper":"/paper/rational-recurrences","title":"Rational Recurrences","date":"2018-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Noahs-ARK/rational-recurrences","path":"classification/train_classifier.py","file_url":"https://github.com/Noahs-ARK/rational-recurrences/blob/HEAD/classification/train_classifier.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffb793bae7c75c69","mcp_get_code":{"code_sha256":"ffb793bae7c75c69"}},{"arxiv_id":"2023.findings-emnlp.384","paper":null,"title":"arXiv:2023.findings-emnlp.384","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"JHL-HUST/SparseMA","path":"train_classifier.py","file_url":"https://github.com/JHL-HUST/SparseMA/blob/HEAD/train_classifier.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":"b8714aa8b5678221","mcp_get_code":{"code_sha256":"b8714aa8b5678221"}},{"arxiv_id":"2023.findings-acl.765","paper":null,"title":"arXiv:2023.findings-acl.765","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qtli/EIB","path":"code/BottleSum/finetune_BottleSelf.py","file_url":"https://github.com/qtli/EIB/blob/HEAD/code/BottleSum/finetune_BottleSelf.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":"3f8c02eb208fc9e7","mcp_get_code":{"code_sha256":"3f8c02eb208fc9e7"}},{"arxiv_id":"2023.acl-short.31","paper":null,"title":"arXiv:2023.acl-short.31","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"JFChi/PLUE","path":"pretraining/BERT/run_mlm_no_trainer.py","file_url":"https://github.com/JFChi/PLUE/blob/HEAD/pretraining/BERT/run_mlm_no_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3a6621055683d86","mcp_get_code":{"code_sha256":"f3a6621055683d86"}}]}