{"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/nll-loss","entry":"nll_loss","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":29,"n_papers_ran":10,"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":20,"n_samples_ran":9,"n_samples_fingerprinted":1,"n_places":29,"n_places_pointer_only":10,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":2,"ran":5,"unverified":11},"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":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"szc19990412/TransMIL","path":"MyLoss/ND_Crossentropy.py","file_url":"https://github.com/szc19990412/TransMIL/blob/HEAD/MyLoss/ND_Crossentropy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2f6a7a4faec6cb11","mcp_get_code":{"code_sha256":"2f6a7a4faec6cb11"}},{"arxiv_id":"2506.20741","paper":"/paper/otsurv-a-novel-multiple-instance-learning","title":"OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transport","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"y-research-sbu/otsurv","path":"src/utils/losses.py","file_url":"https://github.com/y-research-sbu/otsurv/blob/HEAD/src/utils/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15821d5a95c321e7","mcp_get_code":{"code_sha256":"15821d5a95c321e7"}},{"arxiv_id":"2506.02408","paper":"/paper/revisiting-end-to-end-learning-with-slide","title":"Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dearcaat/e2e-wsi-abmilx","path":"train_utils.py","file_url":"https://github.com/dearcaat/e2e-wsi-abmilx/blob/HEAD/train_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"634cc658cc2e7e43","mcp_get_code":{"code_sha256":"634cc658cc2e7e43"}},{"arxiv_id":"2408.10419","paper":"/paper/second-order-forward-mode-automatic","title":"Second-Order Forward-Mode Automatic Differentiation for Optimization","date":"2024-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sri-csl/fomoh","path":"src/fomoh/nn.py","file_url":"https://github.com/sri-csl/fomoh/blob/HEAD/src/fomoh/nn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"f3958881d36885b5","mcp_get_code":{"code_sha256":"f3958881d36885b5"}},{"arxiv_id":"2407.15362","paper":"/paper/a-multimodal-knowledge-enhanced-whole-slide","title":"A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cassie07/pathomics","path":"PathOmics/model_and_training_utils/Customized_Loss.py","file_url":"https://github.com/cassie07/pathomics/blob/HEAD/PathOmics/model_and_training_utils/Customized_Loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62ede8fe77ab4913","mcp_get_code":{"code_sha256":"62ede8fe77ab4913"}},{"arxiv_id":"2407.00224","paper":"/paper/multimodal-prototyping-for-cancer-survival","title":"Multimodal Prototyping for cancer survival prediction","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/MMP","path":"src/mil_models/model_multimodal.py","file_url":"https://github.com/mahmoodlab/MMP/blob/HEAD/src/mil_models/model_multimodal.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"15821d5a95c321e7","mcp_get_code":{"code_sha256":"15821d5a95c321e7"}},{"arxiv_id":"2406.16708","paper":"/paper/causalformer-an-interpretable-transformer-for","title":"CausalFormer: An Interpretable Transformer for Temporal Causal Discovery","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lingbai-kong/causalformer","path":"model/loss.py","file_url":"https://github.com/lingbai-kong/causalformer/blob/HEAD/model/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d1be63c8c9a37d8b","mcp_get_code":{"code_sha256":"d1be63c8c9a37d8b"}},{"arxiv_id":"2404.02394","paper":"/paper/cohort-individual-cooperative-learning-for","title":"Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moothes/ccl-survival","path":"utils/loss_factory.py","file_url":"https://github.com/moothes/ccl-survival/blob/HEAD/utils/loss_factory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6da69690929061c7","mcp_get_code":{"code_sha256":"6da69690929061c7"}},{"arxiv_id":"2403.06800","paper":"/paper/mambamil-enhancing-long-sequence-modeling","title":"MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isyangshu/mambamil","path":"utils/survival_loss.py","file_url":"https://github.com/isyangshu/mambamil/blob/HEAD/utils/survival_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7acefd0931bba0fe","mcp_get_code":{"code_sha256":"7acefd0931bba0fe"}},{"arxiv_id":"2402.18846","paper":"/paper/multi-fidelity-residual-neural-processes-for","title":"Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rose-stl-lab/mfrnp","path":"model/loss.py","file_url":"https://github.com/rose-stl-lab/mfrnp/blob/HEAD/model/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1876fb7ce633ef5f","mcp_get_code":{"code_sha256":"1876fb7ce633ef5f"}},{"arxiv_id":"2311.09115","paper":"/paper/healnet-hybrid-multi-modal-fusion-for","title":"HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konst-int-i/mm-lego","path":"mm_lego/models/losses.py","file_url":"https://github.com/konst-int-i/mm-lego/blob/HEAD/mm_lego/models/losses.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":"8109ef4e167f0ad9","mcp_get_code":{"code_sha256":"8109ef4e167f0ad9"}},{"arxiv_id":"2306.08330","paper":"/paper/multimodal-optimal-transport-based-co","title":"Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JJ-ZHOU-Code/RobustMultiModel","path":"models/model_coattn.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_coattn.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62ede8fe77ab4913","mcp_get_code":{"code_sha256":"62ede8fe77ab4913"}},{"arxiv_id":"2305.03347","paper":"/paper/a-large-cross-modal-video-retrieval-dataset","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"callsys/textvr","path":"model/loss.py","file_url":"https://github.com/callsys/textvr/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2206.02659","paper":"/paper/robust-fine-tuning-of-deep-neural-networks","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","date":"2022-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VirtuosoResearch/Robust-fine-tuning","path":"exps_on_image_datasets/model/loss.py","file_url":"https://github.com/VirtuosoResearch/Robust-fine-tuning/blob/HEAD/exps_on_image_datasets/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2202.10553","paper":"/paper/guidelines-and-evaluation-for-clinical","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weinajin/multimodal_explanation","path":"code/model/loss.py","file_url":"https://github.com/weinajin/multimodal_explanation/blob/HEAD/code/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2109.04912","paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","date":"2021-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunlab-osu/reasonbert","path":"model/loss.py","file_url":"https://github.com/sunlab-osu/reasonbert/blob/HEAD/model/loss.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":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2104.00650","paper":"/paper/frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"m-bain/frozen-in-time","path":"model/loss.py","file_url":"https://github.com/m-bain/frozen-in-time/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2008.10546","paper":"/paper/sde-net-equipping-deep-neural-networks-with","title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","date":"2020-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lingkai-Kong/SDE-Net","path":"YearMSD/SDE_regression.py","file_url":"https://github.com/Lingkai-Kong/SDE-Net/blob/HEAD/YearMSD/SDE_regression.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"90e12c93d2ca890b","mcp_get_code":{"code_sha256":"90e12c93d2ca890b"}},{"arxiv_id":"2006.12204","paper":"/paper/telescoping-density-ratio-estimation","title":"Telescoping Density-Ratio Estimation","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benrhodes26/tre_code","path":"representation_learning_evaluation.py","file_url":"https://github.com/benrhodes26/tre_code/blob/HEAD/representation_learning_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc6b7cfb69c9976e","mcp_get_code":{"code_sha256":"bc6b7cfb69c9976e"}},{"arxiv_id":"2003.01941","paper":"/paper/gaussianization-flows","title":"Gaussianization Flows","date":"2020-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IPL-UV/rbig_jax","path":"rbig_jax/stopping.py","file_url":"https://github.com/IPL-UV/rbig_jax/blob/HEAD/rbig_jax/stopping.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36a600d9e04a706d","mcp_get_code":{"code_sha256":"36a600d9e04a706d"}},{"arxiv_id":"2001.01941","paper":"/paper/paraphrase-generation-with-latent-bag-of-1","title":"Paraphrase Generation with Latent Bag of Words","date":"2020-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FranxYao/dgm_latent_bow","path":"src/bow_seq2seq.py","file_url":"https://github.com/FranxYao/dgm_latent_bow/blob/HEAD/src/bow_seq2seq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a8e1721a125fdd2","mcp_get_code":{"code_sha256":"9a8e1721a125fdd2"}},{"arxiv_id":"1908.11523","paper":"/paper/conditional-density-estimation-tools-in","title":"Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference","date":"2019-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tpospisi/DeepCDE","path":"deepcde/deepcde_tensorflow.py","file_url":"https://github.com/tpospisi/DeepCDE/blob/HEAD/deepcde/deepcde_tensorflow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e952a89a011eab1e","mcp_get_code":{"code_sha256":"e952a89a011eab1e"}},{"arxiv_id":"1908.03971","paper":"/paper/taper-time-aware-patient-ehr-representation","title":"TAPER: Time-Aware Patient EHR Representation","date":"2019-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sajaddarabi/TAPER","path":"model/loss.py","file_url":"https://github.com/sajaddarabi/TAPER/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ee89582184d0fd2","mcp_get_code":{"code_sha256":"8ee89582184d0fd2"}},{"arxiv_id":"1905.05928","paper":"/paper/rethinking-the-usage-of-batch-normalization","title":"Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks","date":"2019-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tae898/age-gender","path":"model/loss.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/loss.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":"f733c7f26bd8c1dc","mcp_get_code":{"code_sha256":"f733c7f26bd8c1dc"}},{"arxiv_id":"1609.09869","paper":"/paper/structured-inference-networks-for-nonlinear","title":"Structured Inference Networks for Nonlinear State Space Models","date":"2016-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjlolo/pytorch-deep-markov-model","path":"model/loss.py","file_url":"https://github.com/yjlolo/pytorch-deep-markov-model/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5351f56bbfd3e22","mcp_get_code":{"code_sha256":"b5351f56bbfd3e22"}},{"arxiv_id":"1409.2329","paper":"/paper/recurrent-neural-network-regularization","title":"Recurrent Neural Network Regularization","date":"2014-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Goodideax/lstm-negtive","path":"ensemble.py","file_url":"https://github.com/Goodideax/lstm-negtive/blob/HEAD/ensemble.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd2e42e616936d7a","mcp_get_code":{"code_sha256":"dd2e42e616936d7a"}},{"arxiv_id":"2023.emnlp-main.979","paper":null,"title":"arXiv:2023.emnlp-main.979","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cyclexu/TacoPrompt","path":"TacoPrompt/model/loss.py","file_url":"https://github.com/cyclexu/TacoPrompt/blob/HEAD/TacoPrompt/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2022.findings-emnlp.24","paper":null,"title":"arXiv:2022.findings-emnlp.24","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"StanLei52/TQVSR","path":"models/loss.py","file_url":"https://github.com/StanLei52/TQVSR/blob/HEAD/models/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}},{"arxiv_id":"2022.findings-acl.116","paper":null,"title":"arXiv:2022.findings-acl.116","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"vistec-AI/Thai-NNER","path":"model/loss.py","file_url":"https://github.com/vistec-AI/Thai-NNER/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c2db3d4435816c0","mcp_get_code":{"code_sha256":"8c2db3d4435816c0"}}]}