{"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/loss-func","entry":"loss_func","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":26,"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":26,"n_samples_ran":17,"n_samples_fingerprinted":5,"n_places":28,"n_places_pointer_only":14,"by_status":{"ran_honours":2,"ran_violates":1,"ran_draft_wrong":3,"ran_fixture":3,"ran":8,"unverified":9},"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":"2608.20991","paper":"/paper/arxiv-2608-20991","title":"Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ventr1c/STAG","path":"graphclip/model/reconstruct.py","file_url":"https://github.com/ventr1c/STAG/blob/HEAD/graphclip/model/reconstruct.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":"8460148151bb97d8","mcp_get_code":{"code_sha256":"8460148151bb97d8"}},{"arxiv_id":"2411.02125","paper":"/paper/revisiting-k-mer-profile-for-effective-and","title":"Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abdcelikkanat/revisitingkmers","path":"src/nonlinear.py","file_url":"https://github.com/abdcelikkanat/revisitingkmers/blob/HEAD/src/nonlinear.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b8415a5ca4e28ff0","mcp_get_code":{"code_sha256":"b8415a5ca4e28ff0"}},{"arxiv_id":"2410.19123","paper":"/paper/read-me-refactorizing-llms-as-router","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/read-me","path":"moe_fication/train_red.py","file_url":"https://github.com/vita-group/read-me/blob/HEAD/moe_fication/train_red.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c2877c234b2d0e3f","mcp_get_code":{"code_sha256":"c2877c234b2d0e3f"}},{"arxiv_id":"2410.09112","paper":"/paper/hlm-cite-hybrid-language-model-workflow-for","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/H-LM","path":"code/model_train/functions.py","file_url":"https://github.com/tsinghua-fib-lab/H-LM/blob/HEAD/code/model_train/functions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df4f39f6cba1abae","mcp_get_code":{"code_sha256":"df4f39f6cba1abae"}},{"arxiv_id":"2410.07171","paper":"/paper/itercomp-iterative-composition-aware-feedback","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YangLing0818/IterComp","path":"train/train_reward_models.py","file_url":"https://github.com/YangLing0818/IterComp/blob/HEAD/train/train_reward_models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1164a205d991f3d8","mcp_get_code":{"code_sha256":"1164a205d991f3d8"}},{"arxiv_id":"2409.19872","paper":"/paper/towards-unified-multimodal-editing-with","title":"Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beepkh/unike","path":"easyeditor/models/unike/unike_main.py","file_url":"https://github.com/beepkh/unike/blob/HEAD/easyeditor/models/unike/unike_main.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ba48886f3a5f906","mcp_get_code":{"code_sha256":"7ba48886f3a5f906"}},{"arxiv_id":"2402.11887","paper":"/paper/generative-semi-supervised-graph-anomaly","title":"Generative Semi-supervised Graph Anomaly Detection","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mala-lab/GGAD","path":"ocgnn.py","file_url":"https://github.com/mala-lab/GGAD/blob/HEAD/ocgnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7290fd3be1378160","mcp_get_code":{"code_sha256":"7290fd3be1378160"}},{"arxiv_id":"2402.11283","paper":"/paper/deep-adaptive-sampling-for-surrogate-modeling","title":"Deep adaptive sampling for surrogate modeling without labeled data","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MJfadeaway/DAS-2","path":"Lid-driven_cavity_flow/das_train.py","file_url":"https://github.com/MJfadeaway/DAS-2/blob/HEAD/Lid-driven_cavity_flow/das_train.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":"c8171b470687f787","mcp_get_code":{"code_sha256":"c8171b470687f787"}},{"arxiv_id":"2402.11283","paper":"/paper/deep-adaptive-sampling-for-surrogate-modeling","title":"Deep adaptive sampling for surrogate modeling without labeled data","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MJfadeaway/DAS-2","path":"Operator_learning/das_oplearning.py","file_url":"https://github.com/MJfadeaway/DAS-2/blob/HEAD/Operator_learning/das_oplearning.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":"feabd500549c048c","mcp_get_code":{"code_sha256":"feabd500549c048c"}},{"arxiv_id":"2402.11283","paper":"/paper/deep-adaptive-sampling-for-surrogate-modeling","title":"Deep adaptive sampling for surrogate modeling without labeled data","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MJfadeaway/DAS-2","path":"Lid-driven_cavity_flow/das_fixed.py","file_url":"https://github.com/MJfadeaway/DAS-2/blob/HEAD/Lid-driven_cavity_flow/das_fixed.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":"2767233d06d2a32a","mcp_get_code":{"code_sha256":"2767233d06d2a32a"}},{"arxiv_id":"2402.08573","paper":"/paper/two-tales-of-single-phase-contrastive-hebbian","title":"Two Tales of Single-Phase Contrastive Hebbian Learning","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rasmuskh/dualprop_icml_2024","path":"config/cli_config.py","file_url":"https://github.com/Rasmuskh/dualprop_icml_2024/blob/HEAD/config/cli_config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a9389d40f435482","mcp_get_code":{"code_sha256":"8a9389d40f435482"}},{"arxiv_id":"2402.03220","paper":"/paper/the-benefits-of-reusing-batches-for-gradient","title":"The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idephics/benefit-reusing-batch","path":"simulations_PyTorch.py","file_url":"https://github.com/idephics/benefit-reusing-batch/blob/HEAD/simulations_PyTorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f257a6a2b02c83f","mcp_get_code":{"code_sha256":"7f257a6a2b02c83f"}},{"arxiv_id":"2312.10102","paper":"/paper/robust-estimation-of-causal-heteroscedastic","title":"Robust Estimation of Causal Heteroscedastic Noise Models","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"quangdzuytran/ROCHE","path":"causa/roche.py","file_url":"https://github.com/quangdzuytran/ROCHE/blob/HEAD/causa/roche.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a43f04570f2e3bd","mcp_get_code":{"code_sha256":"4a43f04570f2e3bd"}},{"arxiv_id":"2308.10918","paper":"/paper/deep-semi-supervised-anomaly-detection-with","title":"Label-based Graph Augmentation with Metapath for Graph Anomaly Detection","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"missinghwan/MSAD","path":"random_search.py","file_url":"https://github.com/missinghwan/MSAD/blob/HEAD/random_search.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"461ba2662d434a33","mcp_get_code":{"code_sha256":"461ba2662d434a33"}},{"arxiv_id":"2307.02129","paper":"/paper/how-deep-neural-networks-learn-compositional","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pcsl-epfl/hierarchy-learning","path":"optim_loss.py","file_url":"https://github.com/pcsl-epfl/hierarchy-learning/blob/HEAD/optim_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c23da6206919edb5","mcp_get_code":{"code_sha256":"c23da6206919edb5"}},{"arxiv_id":"2307.01951","paper":"/paper/a-neural-collapse-perspective-on-feature-1","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kvignesh1420/gnn_collapse","path":"gufm.py","file_url":"https://github.com/kvignesh1420/gnn_collapse/blob/HEAD/gufm.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":"16d68f9aa5f47c6b","mcp_get_code":{"code_sha256":"16d68f9aa5f47c6b"}},{"arxiv_id":"2307.00755","paper":"/paper/graph-level-anomaly-detection-via","title":"Graph-level Anomaly Detection via Hierarchical Memory Networks","date":"2023-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niuchx/himnet","path":"loss.py","file_url":"https://github.com/niuchx/himnet/blob/HEAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00f227f6ee7015cb","mcp_get_code":{"code_sha256":"00f227f6ee7015cb"}},{"arxiv_id":"2301.09785","paper":"/paper/transformer-patcher-one-mistake-worth-one","title":"Transformer-Patcher: One Mistake worth One Neuron","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZeroYuHuang/Transformer-Patcher","path":"src/models/patch.py","file_url":"https://github.com/ZeroYuHuang/Transformer-Patcher/blob/HEAD/src/models/patch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ef32b5700dabe8c","mcp_get_code":{"code_sha256":"3ef32b5700dabe8c"}},{"arxiv_id":"2210.11464","paper":"/paper/self-supervised-learning-via-maximum-entropy","title":"Self-Supervised Learning via Maximum Entropy Coding","date":"2022-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinliu20/mec","path":"main_pretrain.py","file_url":"https://github.com/xinliu20/mec/blob/HEAD/main_pretrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d6e7120fd354e50","mcp_get_code":{"code_sha256":"2d6e7120fd354e50"}},{"arxiv_id":"2206.07050","paper":"/paper/near-exact-recovery-for-tomographic-inverse","title":"Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jmaces/aapm-ct-challenge","path":"aapm-ct/script_train_ddnet_inv.py","file_url":"https://github.com/jmaces/aapm-ct-challenge/blob/HEAD/aapm-ct/script_train_ddnet_inv.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd9b4f62ae1d8205","mcp_get_code":{"code_sha256":"bd9b4f62ae1d8205"}},{"arxiv_id":"2106.04781","paper":"/paper/embedding-physics-to-learn-spatiotemporal","title":"Encoding physics to learn reaction-diffusion processes","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Raocp/PeRCNN","path":"3d_gs_rd/train_3drd.py","file_url":"https://github.com/Raocp/PeRCNN/blob/HEAD/3d_gs_rd/train_3drd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32af45a8240c8744","mcp_get_code":{"code_sha256":"32af45a8240c8744"}},{"arxiv_id":"2102.07988","paper":"/paper/terapipe-token-level-pipeline-parallelism-for","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","date":"2021-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuohan123/terapipe","path":"terapipe.py","file_url":"https://github.com/zhuohan123/terapipe/blob/HEAD/terapipe.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"49e2a4eb90f7b049","mcp_get_code":{"code_sha256":"49e2a4eb90f7b049"}},{"arxiv_id":"2001.01258","paper":"/paper/the-troublesome-kernel-why-deep-learning-for","title":"The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems","date":"2020-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vegarant/troublesome_kernel","path":"ellipses/script_train_fourier_unet_it_jit-nojit.py","file_url":"https://github.com/vegarant/troublesome_kernel/blob/HEAD/ellipses/script_train_fourier_unet_it_jit-nojit.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd9b4f62ae1d8205","mcp_get_code":{"code_sha256":"bd9b4f62ae1d8205"}},{"arxiv_id":"1909.10837","paper":"/paper/direct-training-based-spiking-convolutional","title":"Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zbs881314/Temporal-Coded-Deep-SNN","path":"MNIST/SNN.py","file_url":"https://github.com/zbs881314/Temporal-Coded-Deep-SNN/blob/HEAD/MNIST/SNN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d997d1e25178db8","mcp_get_code":{"code_sha256":"5d997d1e25178db8"}},{"arxiv_id":"1905.11954","paper":"/paper/unsupervised-learning-from-video-with-deep","title":"Unsupervised Learning from Video with Deep Neural Embeddings","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neuroailab/VIE","path":"tf_model/train_vie.py","file_url":"https://github.com/neuroailab/VIE/blob/HEAD/tf_model/train_vie.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":"56be0c434fce98a7","mcp_get_code":{"code_sha256":"56be0c434fce98a7"}},{"arxiv_id":"1612.02806","paper":"/paper/quantum-autoencoders-for-efficient","title":"Quantum autoencoders for efficient compression of quantum data","date":null,"month_inferred_from_arxiv_id":"2016-12","title_source":"archive","repo":"theodoradragan/QuantumAutoencoder","path":"utils.py","file_url":"https://github.com/theodoradragan/QuantumAutoencoder/blob/HEAD/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0cb57b5b394f6f4","mcp_get_code":{"code_sha256":"a0cb57b5b394f6f4"}},{"arxiv_id":"1606.08165","paper":"/paper/supervised-learning-based-on-temporal-coding","title":"Supervised learning based on temporal coding in spiking neural networks","date":"2016-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TianjianCai/SNN","path":"SNN.py","file_url":"https://github.com/TianjianCai/SNN/blob/HEAD/SNN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d997d1e25178db8","mcp_get_code":{"code_sha256":"5d997d1e25178db8"}},{"arxiv_id":"Yu_SSHNet_Unsupervised_Cross-modal_Homography_Estimation_via_Problem_Reformulation_and_Split_CVPR_2025_paper","paper":null,"title":"arXiv:Yu_SSHNet_Unsupervised_Cross-modal_Homography_Estimation_via_Problem_Reformulation_and_Split_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Junchen-Yu/SSHNet","path":"utils/loss.py","file_url":"https://github.com/Junchen-Yu/SSHNet/blob/HEAD/utils/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":"cbc8d3baf37188e5","mcp_get_code":{"code_sha256":"cbc8d3baf37188e5"}}]}