{"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/cross-entropy-loss","entry":"cross_entropy_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":58,"n_papers_ran":23,"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":21,"n_samples_fingerprinted":3,"n_places":58,"n_places_pointer_only":23,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":2,"ran":14,"unverified":28},"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":"2605.05838","paper":"/paper/arxiv-2605-05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","date":"2026-05-07","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"HuuYuLong/MomentumDeltaNet","path":"flame/torchtitan/components/loss.py","file_url":"https://github.com/HuuYuLong/MomentumDeltaNet/blob/HEAD/flame/torchtitan/components/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0b6e383f758e9a0","mcp_get_code":{"code_sha256":"e0b6e383f758e9a0"}},{"arxiv_id":"2602.18487","paper":"/paper/arxiv-2602-18487","title":"The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"urchade/GLiNER","path":"gliner/modeling/loss_functions.py","file_url":"https://github.com/urchade/GLiNER/blob/HEAD/gliner/modeling/loss_functions.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":"bb1f6cd5ab3e0c98","mcp_get_code":{"code_sha256":"bb1f6cd5ab3e0c98"}},{"arxiv_id":"2602.05234","paper":"/paper/arxiv-2602-05234","title":"Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"colored-dye/concept_das","path":"cdas/models/das_model.py","file_url":"https://github.com/colored-dye/concept_das/blob/HEAD/cdas/models/das_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7380c0f50e9f778c","mcp_get_code":{"code_sha256":"7380c0f50e9f778c"}},{"arxiv_id":"2512.00919","paper":"/paper/arxiv-2512-00919","title":"Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"Wornbard/AugSpecIV","path":"learning/losses.py","file_url":"https://github.com/Wornbard/AugSpecIV/blob/HEAD/learning/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c50540858bc7e459","mcp_get_code":{"code_sha256":"c50540858bc7e459"}},{"arxiv_id":"2507.11333","paper":"/paper/monomvsnet-monocular-priors-guided-multi-view","title":"MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JianfeiJ/MonoMVSNet","path":"models/monomvsnet.py","file_url":"https://github.com/JianfeiJ/MonoMVSNet/blob/HEAD/models/monomvsnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"41f59aee24980c21","mcp_get_code":{"code_sha256":"41f59aee24980c21"}},{"arxiv_id":"2506.14767","paper":"/paper/a-variational-framework-for-improving","title":"A Variational Framework for Improving Naturalness in Generative Spoken Language Models","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"b04901014/vae-gslm","path":"training_lib/losses.py","file_url":"https://github.com/b04901014/vae-gslm/blob/HEAD/training_lib/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bd9184f85f7e83d","mcp_get_code":{"code_sha256":"4bd9184f85f7e83d"}},{"arxiv_id":"2411.08460","paper":"/paper/trap-mid-trapdoor-based-defense-against-model","title":"Trap-MID: Trapdoor-based Defense against Model Inversion Attacks","date":"2024-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntuaislab/Trap-MID","path":"plgmi/losses.py","file_url":"https://github.com/ntuaislab/Trap-MID/blob/HEAD/plgmi/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c808ba0601a877e8","mcp_get_code":{"code_sha256":"c808ba0601a877e8"}},{"arxiv_id":"2410.16975","paper":"/paper/publishing-neural-networks-in-drug-discovery","title":"Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aidotse/leakpro","path":"leakpro/attacks/utils/gan_losses.py","file_url":"https://github.com/aidotse/leakpro/blob/HEAD/leakpro/attacks/utils/gan_losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"40e19414623504e2","mcp_get_code":{"code_sha256":"40e19414623504e2"}},{"arxiv_id":"2410.07163","paper":"/paper/simplicity-prevails-rethinking-negative","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/Unlearn-Simple","path":"synthetic/unlearn_utils.py","file_url":"https://github.com/OPTML-Group/Unlearn-Simple/blob/HEAD/synthetic/unlearn_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04d9dfc17842cf17","mcp_get_code":{"code_sha256":"04d9dfc17842cf17"}},{"arxiv_id":"2408.07507","paper":"/paper/decoder-ensembling-for-learned-latent","title":"Decoder ensembling for learned latent geometries","date":"2024-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mustass/ensertainty","path":"src/ensertainty/training/losses.py","file_url":"https://github.com/mustass/ensertainty/blob/HEAD/src/ensertainty/training/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"69df12e202c46837","mcp_get_code":{"code_sha256":"69df12e202c46837"}},{"arxiv_id":"2407.18899","paper":"/paper/learn-from-the-learnt-source-free-active","title":"Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence","date":"2024-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyumengyao/lftl","path":"mining/contrastive_sampling.py","file_url":"https://github.com/lyumengyao/lftl/blob/HEAD/mining/contrastive_sampling.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":"a84c8b8443596255","mcp_get_code":{"code_sha256":"a84c8b8443596255"}},{"arxiv_id":"2407.15549","paper":"/paper/targeted-latent-adversarial-training-improves","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aengusl/latent-adversarial-training","path":"latent_at/utils.py","file_url":"https://github.com/aengusl/latent-adversarial-training/blob/HEAD/latent_at/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d4f7e1c015733a4","mcp_get_code":{"code_sha256":"2d4f7e1c015733a4"}},{"arxiv_id":"2406.09405","paper":"/paper/why-warmup-the-learning-rate-underlying","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dayal-kalra/why-warmup","path":"vision/mechanisms/utils/loss_utils.py","file_url":"https://github.com/dayal-kalra/why-warmup/blob/HEAD/vision/mechanisms/utils/loss_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26d13d6c867ba7fa","mcp_get_code":{"code_sha256":"26d13d6c867ba7fa"}},{"arxiv_id":"2405.07987","paper":"/paper/the-platonic-representation-hypothesis","title":"The Platonic Representation Hypothesis","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minyoungg/platonic-rep","path":"utils.py","file_url":"https://github.com/minyoungg/platonic-rep/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7bd49b153fe597c","mcp_get_code":{"code_sha256":"a7bd49b153fe597c"}},{"arxiv_id":"2404.02973","paper":"/paper/scaling-laws-for-galaxy-images","title":"Scaling Laws for Galaxy Images","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"a68ecd1f369223b8","mcp_get_code":{"code_sha256":"a68ecd1f369223b8"}},{"arxiv_id":"2402.12789","paper":"/paper/fair-classifiers-without-fair-training-an","title":"Fairness Without Harm: An Influence-Guided Active Sampling Approach","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-real/fairnesswithoutharm","path":"src/metrics.py","file_url":"https://github.com/ucsc-real/fairnesswithoutharm/blob/HEAD/src/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bbab883e9f27b305","mcp_get_code":{"code_sha256":"bbab883e9f27b305"}},{"arxiv_id":"2402.10765","paper":"/paper/policy-learning-for-off-dynamics-rl-with","title":"Policy Learning for Off-Dynamics RL with Deficient Support","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linhlpv/DADS","path":"dads.py","file_url":"https://github.com/linhlpv/DADS/blob/HEAD/dads.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a359c6a7c05c7ea0","mcp_get_code":{"code_sha256":"a359c6a7c05c7ea0"}},{"arxiv_id":"2401.14168","paper":"/paper/vivim-a-video-vision-mamba-for-medical-video","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scott-yjyang/vivim","path":"loss.py","file_url":"https://github.com/scott-yjyang/vivim/blob/HEAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e4f26582292cf067","mcp_get_code":{"code_sha256":"e4f26582292cf067"}},{"arxiv_id":"2312.12222","paper":"/paper/earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Junjue-Wang/EarthVQA","path":"module/loss.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4133a26ae05f4dd9","mcp_get_code":{"code_sha256":"4133a26ae05f4dd9"}},{"arxiv_id":"2312.04021","paper":"/paper/a-study-on-the-calibration-of-in-context","title":"A Study on the Calibration of In-context Learning","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hlzhang109/icl-calibration","path":"calibrate/verified_calibration.py","file_url":"https://github.com/hlzhang109/icl-calibration/blob/HEAD/calibrate/verified_calibration.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19422cfbfee41729","mcp_get_code":{"code_sha256":"19422cfbfee41729"}},{"arxiv_id":"2311.17539","paper":"/paper/the-effects-of-overparameterization-on","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"log-postech/sam-overparam","path":"train_utils.py","file_url":"https://github.com/log-postech/sam-overparam/blob/HEAD/train_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f369ebdcbe5c0a3","mcp_get_code":{"code_sha256":"6f369ebdcbe5c0a3"}},{"arxiv_id":"2310.19342","paper":"/paper/label-only-model-inversion-attacks-via-1","title":"Label-Only Model Inversion Attacks via Knowledge Transfer","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ngoc-nguyen-0/LOKT_neurips2023","path":"plg_tacgan.py","file_url":"https://github.com/ngoc-nguyen-0/LOKT_neurips2023/blob/HEAD/plg_tacgan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c808ba0601a877e8","mcp_get_code":{"code_sha256":"c808ba0601a877e8"}},{"arxiv_id":"2310.13892","paper":"/paper/specify-robust-causal-representation-from","title":"Specify Robust Causal Representation from Mixed Observations","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymy4323460/cari","path":"utils.py","file_url":"https://github.com/ymy4323460/cari/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bfc467eb2d2b427","mcp_get_code":{"code_sha256":"6bfc467eb2d2b427"}},{"arxiv_id":"2309.17218","paper":"/paper/when-epipolar-constraint-meets-non-local-1","title":"When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tqtqliu/et-mvsnet","path":"models/MVS4Net.py","file_url":"https://github.com/tqtqliu/et-mvsnet/blob/HEAD/models/MVS4Net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"41f59aee24980c21","mcp_get_code":{"code_sha256":"41f59aee24980c21"}},{"arxiv_id":"2309.11425","paper":"/paper/galaxy-zoo-desi-detailed-morphology","title":"Galaxy Zoo DESI: Detailed Morphology Measurements for 8.7M Galaxies in the DESI Legacy Imaging Surveys","date":null,"month_inferred_from_arxiv_id":"2023-09","title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"a68ecd1f369223b8","mcp_get_code":{"code_sha256":"a68ecd1f369223b8"}},{"arxiv_id":"2309.11160","paper":"/paper/multi-grained-temporal-prototype-learning-for","title":"Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation","date":"2023-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nankepan/VIPMT","path":"libs/utils/loss.py","file_url":"https://github.com/nankepan/VIPMT/blob/HEAD/libs/utils/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2d13347de310a810","mcp_get_code":{"code_sha256":"2d13347de310a810"}},{"arxiv_id":"2308.04016","paper":"/paper/hierarchical-visual-primitive-experts-for","title":"Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanjaekim98/cot","path":"models/cot.py","file_url":"https://github.com/hanjaekim98/cot/blob/HEAD/models/cot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"86116ff1c363bbaf","mcp_get_code":{"code_sha256":"86116ff1c363bbaf"}},{"arxiv_id":"2307.00631","paper":"/paper/bidirectional-looking-with-a-novel-double","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","date":"2023-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chernyn/admeta-optimizer","path":"admeta-code/admeta-cifar/pytorch_image_classification/losses/label_smoothing.py","file_url":"https://github.com/chernyn/admeta-optimizer/blob/HEAD/admeta-code/admeta-cifar/pytorch_image_classification/losses/label_smoothing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"bc8c7f73dc3f1039","mcp_get_code":{"code_sha256":"bc8c7f73dc3f1039"}},{"arxiv_id":"2305.19534","paper":"/paper/recasting-self-attention-with-holographic","title":"Recasting Self-Attention with Holographic Reduced Representations","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neuromorphiccomputationresearchprogram/hrrformer","path":"image/hrrformer_mgpu.py","file_url":"https://github.com/neuromorphiccomputationresearchprogram/hrrformer/blob/HEAD/image/hrrformer_mgpu.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":"11b73c012ece44e7","mcp_get_code":{"code_sha256":"11b73c012ece44e7"}},{"arxiv_id":"2303.17132","paper":"/paper/c-sfda-a-curriculum-learning-aided-self","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation","path":"target_csfda.py","file_url":"https://github.com/nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/blob/HEAD/target_csfda.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1d0329a2deb6eac4","mcp_get_code":{"code_sha256":"1d0329a2deb6eac4"}},{"arxiv_id":"2302.01190","paper":"/paper/on-the-efficacy-of-differentially-private-few","title":"On the Efficacy of Differentially Private Few-shot Image Classification","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridge-mlg/dp-few-shot","path":"src/utils.py","file_url":"https://github.com/cambridge-mlg/dp-few-shot/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a521b8c61c81ecdd","mcp_get_code":{"code_sha256":"a521b8c61c81ecdd"}},{"arxiv_id":"2302.00194","paper":"/paper/free-lunch-for-domain-adversarial-training-1","title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","date":"2023-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yfzhang114/Environment-Label-Smoothing","path":"Domain_Generalization/domainbed/algorithms.py","file_url":"https://github.com/yfzhang114/Environment-Label-Smoothing/blob/HEAD/Domain_Generalization/domainbed/algorithms.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":"f0b9793b30a672e0","mcp_get_code":{"code_sha256":"f0b9793b30a672e0"}},{"arxiv_id":"2204.10377","paper":"/paper/contrastive-test-time-adaptation","title":"Contrastive Test-Time Adaptation","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DianCh/AdaContrast","path":"target.py","file_url":"https://github.com/DianCh/AdaContrast/blob/HEAD/target.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":"7f2f33aeb9dd8ed3","mcp_get_code":{"code_sha256":"7f2f33aeb9dd8ed3"}},{"arxiv_id":"2111.14893","paper":"/paper/learning-multiple-dense-prediction-tasks-from","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","date":"2021-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vico-uoe/mtpsl","path":"model/mapfns.py","file_url":"https://github.com/vico-uoe/mtpsl/blob/HEAD/model/mapfns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae00279e3bc33623","mcp_get_code":{"code_sha256":"ae00279e3bc33623"}},{"arxiv_id":"2110.12735","paper":"/paper/practical-galaxy-morphology-tools-from-deep","title":"Practical Galaxy Morphology Tools from Deep Supervised Representation Learning","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"a68ecd1f369223b8","mcp_get_code":{"code_sha256":"a68ecd1f369223b8"}},{"arxiv_id":"2109.05940","paper":"/paper/cross-domain-robot-imitation-with-invariant","title":"Cross Domain Robot Imitation with Invariant Representation","date":"2021-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaohengyin/irgail_example","path":"imitation_learning/network/utils.py","file_url":"https://github.com/zhaohengyin/irgail_example/blob/HEAD/imitation_learning/network/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4cee438c3091f1c","mcp_get_code":{"code_sha256":"b4cee438c3091f1c"}},{"arxiv_id":"2107.07075","paper":"/paper/deep-learning-on-a-data-diet-finding","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","date":"2021-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mansheej/data_diet","path":"data_diet/metrics.py","file_url":"https://github.com/mansheej/data_diet/blob/HEAD/data_diet/metrics.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":"b9fe6d146beff6d7","mcp_get_code":{"code_sha256":"b9fe6d146beff6d7"}},{"arxiv_id":"2107.05802","paper":"/paper/how-many-degrees-of-freedom-do-we-need-to","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","date":"2021-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganguli-lab/degrees-of-freedom","path":"lottery_subspace.py","file_url":"https://github.com/ganguli-lab/degrees-of-freedom/blob/HEAD/lottery_subspace.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":"82620ac387a3de49","mcp_get_code":{"code_sha256":"82620ac387a3de49"}},{"arxiv_id":"2107.01105","paper":"/paper/memory-efficient-meta-learning-with-large","title":"Memory Efficient Meta-Learning with Large Images","date":"2021-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridge-mlg/LITE","path":"src/utils.py","file_url":"https://github.com/cambridge-mlg/LITE/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a521b8c61c81ecdd","mcp_get_code":{"code_sha256":"a521b8c61c81ecdd"}},{"arxiv_id":"2103.13841","paper":"/paper/universal-representation-learning-from","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/CoPA","path":"models/pa.py","file_url":"https://github.com/tmlr-group/CoPA/blob/HEAD/models/pa.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab00127e0e9d1905","mcp_get_code":{"code_sha256":"ab00127e0e9d1905"}},{"arxiv_id":"2102.08414","paper":"/paper/galaxy-zoo-decals-detailed-visual-morphology","title":"Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies","date":"2021-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mwalmsley/zoobot","path":"zoobot/pytorch/training/finetune.py","file_url":"https://github.com/mwalmsley/zoobot/blob/HEAD/zoobot/pytorch/training/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"a68ecd1f369223b8","mcp_get_code":{"code_sha256":"a68ecd1f369223b8"}},{"arxiv_id":"2012.02943","paper":"/paper/cross-domain-sentiment-classification-with-in","title":"Cross-Domain Sentiment Classification with In-Domain Contrastive Learning","date":"2020-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CasparSwift/CLIM","path":"loss.py","file_url":"https://github.com/CasparSwift/CLIM/blob/HEAD/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bffe7f13e375927e","mcp_get_code":{"code_sha256":"bffe7f13e375927e"}},{"arxiv_id":"2010.16010","paper":"/paper/loss-rescaling-vqa-revisiting-language-prior","title":"Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View","date":"2020-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guoyang9/class-imbalance-VQA","path":"utils/losses.py","file_url":"https://github.com/guoyang9/class-imbalance-VQA/blob/HEAD/utils/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":"bd13bf1e7cf15819","mcp_get_code":{"code_sha256":"bd13bf1e7cf15819"}},{"arxiv_id":"2007.12107","paper":"/paper/few-shot-object-detection-and-viewpoint","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","date":"2020-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YoungXIAO13/PoseContrast","path":"src/model/model_utils.py","file_url":"https://github.com/YoungXIAO13/PoseContrast/blob/HEAD/src/model/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af5785faecdf4e41","mcp_get_code":{"code_sha256":"af5785faecdf4e41"}},{"arxiv_id":"2005.11041","paper":"/paper/a-survey-of-information-cascade-analysis","title":"A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances","date":"2020-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xovee/hdgnn","path":"codes/gnn_train/tools.py","file_url":"https://github.com/Xovee/hdgnn/blob/HEAD/codes/gnn_train/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6dab6885871344ad","mcp_get_code":{"code_sha256":"6dab6885871344ad"}},{"arxiv_id":"2003.09338","paper":"/paper/selecting-relevant-features-from-a-universal","title":"Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification","date":"2020-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvornikita/SUR","path":"models/losses.py","file_url":"https://github.com/dvornikita/SUR/blob/HEAD/models/losses.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab00127e0e9d1905","mcp_get_code":{"code_sha256":"ab00127e0e9d1905"}},{"arxiv_id":"2001.07685","paper":"/paper/fixmatch-simplifying-semi-supervised-learning","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","date":"2020-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gomezzz/distmsmatch","path":"MSMatch/models/fixmatch/FixMatch.py","file_url":"https://github.com/gomezzz/distmsmatch/blob/HEAD/MSMatch/models/fixmatch/FixMatch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"774112e52d064668","mcp_get_code":{"code_sha256":"774112e52d064668"}},{"arxiv_id":"2001.06570","paper":"/paper/harmonic-convolutional-networks-based-on","title":"Harmonic Convolutional Networks based on Discrete Cosine Transform","date":"2020-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matej-ulicny/harmonic-networks","path":"bsds/functions.py","file_url":"https://github.com/matej-ulicny/harmonic-networks/blob/HEAD/bsds/functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"508c627527d31817","mcp_get_code":{"code_sha256":"508c627527d31817"}},{"arxiv_id":"1906.08230","paper":"/paper/evaluating-protein-transfer-learning-with","title":"Evaluating Protein Transfer Learning with TAPE","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"googleinterns/protein-embedding-retrieval","path":"contextual_lenses/loss_fns.py","file_url":"https://github.com/googleinterns/protein-embedding-retrieval/blob/HEAD/contextual_lenses/loss_fns.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":"af86e14bcdd0eee9","mcp_get_code":{"code_sha256":"af86e14bcdd0eee9"}},{"arxiv_id":"1906.05105","paper":"/paper/pose-from-shape-deep-pose-estimation-for","title":"Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YoungXIAO13/PoseFromShape","path":"auxiliary/loss.py","file_url":"https://github.com/YoungXIAO13/PoseFromShape/blob/HEAD/auxiliary/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af5785faecdf4e41","mcp_get_code":{"code_sha256":"af5785faecdf4e41"}},{"arxiv_id":"1905.03246","paper":"/paper/190503246","title":"End-to-End Wireframe Parsing","date":"2019-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhou13/lcnn","path":"lcnn/models/multitask_learner.py","file_url":"https://github.com/zhou13/lcnn/blob/HEAD/lcnn/models/multitask_learner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d148fed48dc7e0f","mcp_get_code":{"code_sha256":"0d148fed48dc7e0f"}},{"arxiv_id":"1810.02309","paper":"/paper/learning-compressed-transforms-with-low","title":"Learning Compressed Transforms with Low Displacement Rank","date":"2018-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HazyResearch/structured-nets","path":"pytorch/utils.py","file_url":"https://github.com/HazyResearch/structured-nets/blob/HEAD/pytorch/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":"8ef54cdb8384cbab","mcp_get_code":{"code_sha256":"8ef54cdb8384cbab"}},{"arxiv_id":"1706.04599","paper":"/paper/on-calibration-of-modern-neural-networks","title":"On Calibration of Modern Neural Networks","date":"2017-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saurabhgarg1996/calibration","path":"calibration/calibrators.py","file_url":"https://github.com/saurabhgarg1996/calibration/blob/HEAD/calibration/calibrators.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"155f63d9cf89a950","mcp_get_code":{"code_sha256":"155f63d9cf89a950"}},{"arxiv_id":"1609.01775","paper":"/paper/performance-measures-and-a-data-set-for-multi","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","date":"2016-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hh23333/tsd","path":"loss/parsing_loss.py","file_url":"https://github.com/hh23333/tsd/blob/HEAD/loss/parsing_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89da1a43b987162b","mcp_get_code":{"code_sha256":"89da1a43b987162b"}},{"arxiv_id":"1505.05770","paper":"/paper/variational-inference-with-normalizing-flows","title":"Variational Inference with Normalizing Flows","date":"2015-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Aditya-kiran/ResNet-VAE","path":"code/losses.py","file_url":"https://github.com/Aditya-kiran/ResNet-VAE/blob/HEAD/code/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"70fc47d8442de3fe","mcp_get_code":{"code_sha256":"70fc47d8442de3fe"}},{"arxiv_id":"1504.06375","paper":"/paper/holistically-nested-edge-detection","title":"Holistically-Nested Edge Detection","date":"2015-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meteorshowers/hed-pytorch","path":"functions.py","file_url":"https://github.com/meteorshowers/hed-pytorch/blob/HEAD/functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"508c627527d31817","mcp_get_code":{"code_sha256":"508c627527d31817"}},{"arxiv_id":"aaai_5479","paper":null,"title":"arXiv:aaai_5479","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thunlp/QAjudge","path":"model/loss.py","file_url":"https://github.com/thunlp/QAjudge/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":"d0e9f4c84e69fbf5","mcp_get_code":{"code_sha256":"d0e9f4c84e69fbf5"}},{"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":"fc13a6fe4c6c8129","mcp_get_code":{"code_sha256":"fc13a6fe4c6c8129"}}]}