{"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/soft-cross-entropy","entry":"soft_cross_entropy","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":25,"n_papers_ran":16,"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":17,"n_samples_ran":8,"n_samples_fingerprinted":4,"n_places":26,"n_places_pointer_only":6,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":2,"ran":1,"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":"2512.15647","paper":"/paper/arxiv-2512-15647","title":"Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"Jiacheng8/HALD","path":"validate/train_fkd.py","file_url":"https://github.com/Jiacheng8/HALD/blob/HEAD/validate/train_fkd.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cef161c1e3365a6a","mcp_get_code":{"code_sha256":"cef161c1e3365a6a"}},{"arxiv_id":"2505.05868","paper":"/paper/open-set-label-shift-with-test-time-out-of","title":"Open Set Label Shift with Test Time Out-of-Distribution Reference","date":"2025-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChangkunYe/OpenSetLabelShift","path":"openood/losses/sce.py","file_url":"https://github.com/ChangkunYe/OpenSetLabelShift/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2411.10794","paper":"/paper/going-beyond-conventional-ood-detection","title":"Going Beyond Conventional OOD Detection","date":"2024-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sudarshanregmi/ascood","path":"openood/losses/sce.py","file_url":"https://github.com/sudarshanregmi/ascood/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2407.08966","paper":"/paper/lapt-label-driven-automated-prompt-tuning-for","title":"LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ybzh/openood-vlm","path":"openood/losses/sce.py","file_url":"https://github.com/ybzh/openood-vlm/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2312.10366","paper":"/paper/fusing-conditional-submodular-gan-and","title":"Fusing Conditional Submodular GAN and Programmatic Weak Supervision","date":"2023-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyrs/subpws-gan","path":"lightning_subset/module.py","file_url":"https://github.com/kyrs/subpws-gan/blob/HEAD/lightning_subset/module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"49e2f0c554d81ea3","mcp_get_code":{"code_sha256":"49e2f0c554d81ea3"}},{"arxiv_id":"2311.07052","paper":"/paper/towards-the-law-of-capacity-gap-in-distilling","title":"Towards the Law of Capacity Gap in Distilling Language Models","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"genezc/minima","path":"minima/run_distillation_llama_ds.py","file_url":"https://github.com/genezc/minima/blob/HEAD/minima/run_distillation_llama_ds.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5ea641b9e771d680","mcp_get_code":{"code_sha256":"5ea641b9e771d680"}},{"arxiv_id":"2310.07152","paper":"/paper/no-privacy-left-outside-on-the-in-security-of","title":"No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqi-zhang/teeslice-artifact","path":"membership-inference/knockoff_train.py","file_url":"https://github.com/ziqi-zhang/teeslice-artifact/blob/HEAD/membership-inference/knockoff_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20c1f5f89a49698b","mcp_get_code":{"code_sha256":"20c1f5f89a49698b"}},{"arxiv_id":"2309.11133","paper":"/paper/shape-anchor-guided-holistic-indoor-scene","title":"Shape Anchor Guided Holistic Indoor Scene Understanding","date":"2023-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Geo-Tell/AncRec","path":"models/loss.py","file_url":"https://github.com/Geo-Tell/AncRec/blob/HEAD/models/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e0c50b6f1b79889","mcp_get_code":{"code_sha256":"9e0c50b6f1b79889"}},{"arxiv_id":"2303.14531","paper":"/paper/sio-synthetic-in-distribution-data-benefits","title":"SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjysteven/sio","path":"openood/losses/sce.py","file_url":"https://github.com/zjysteven/sio/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2210.07795","paper":"/paper/efficientvlm-fast-and-accurate-vision","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"swaggy-tn/efficientvlm","path":"Eff_Captioning.py","file_url":"https://github.com/swaggy-tn/efficientvlm/blob/HEAD/Eff_Captioning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"e9a9fd7c33b84f9a","mcp_get_code":{"code_sha256":"e9a9fd7c33b84f9a"}},{"arxiv_id":"2210.07242","paper":"/paper/openood-benchmarking-generalized-out-of","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antoinedemathelin/openood","path":"openood/losses/sce.py","file_url":"https://github.com/antoinedemathelin/openood/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2210.01742","paper":"/paper/cadet-fully-self-supervised-anomaly-detection","title":"CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning","date":"2022-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charlesge/openood-cadet","path":"openood/losses/sce.py","file_url":"https://github.com/charlesge/openood-cadet/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2206.11251","paper":"/paper/behavior-transformers-cloning-k-modes-with","title":"Behavior Transformers: Cloning $k$ modes with one stone","date":"2022-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"notmahi/bet","path":"models/libraries/loss_fn.py","file_url":"https://github.com/notmahi/bet/blob/HEAD/models/libraries/loss_fn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c2032b53ba9edf4","mcp_get_code":{"code_sha256":"5c2032b53ba9edf4"}},{"arxiv_id":"2206.11251","paper":"/paper/behavior-transformers-cloning-k-modes-with","title":"Behavior Transformers: Cloning $k$ modes with one stone","date":"2022-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skandermoalla/bet-reproduction","path":"models/libraries/loss_fn.py","file_url":"https://github.com/skandermoalla/bet-reproduction/blob/HEAD/models/libraries/loss_fn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e05fa1b88b3794c","mcp_get_code":{"code_sha256":"9e05fa1b88b3794c"}},{"arxiv_id":"2205.09148","paper":"/paper/ddxplus-a-new-dataset-for-medical-automatic","title":"DDXPlus: A New Dataset For Automatic Medical Diagnosis","date":"2022-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mila-iqia/ddxplus","path":"code/aarlc/ddxplus_code/agent.py","file_url":"https://github.com/mila-iqia/ddxplus/blob/HEAD/code/aarlc/ddxplus_code/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e67d80a6128cc3d","mcp_get_code":{"code_sha256":"4e67d80a6128cc3d"}},{"arxiv_id":"2203.12023","paper":"/paper/generative-modeling-helps-weak-supervision","title":"Generative Modeling Helps Weak Supervision (and Vice Versa)","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"49e2f0c554d81ea3","mcp_get_code":{"code_sha256":"49e2f0c554d81ea3"}},{"arxiv_id":"2109.06304","paper":"/paper/phrase-bert-improved-phrase-embeddings-from","title":"Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration","date":"2021-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"memray/llm_phrase_semantics","path":"phrase-topic-model/model_utils.py","file_url":"https://github.com/memray/llm_phrase_semantics/blob/HEAD/phrase-topic-model/model_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":"f26677a468445f39","mcp_get_code":{"code_sha256":"f26677a468445f39"}},{"arxiv_id":"2108.11941","paper":"/paper/semantically-coherent-out-of-distribution","title":"Semantically Coherent Out-of-Distribution Detection","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jingkang50/ICCV21_SCOOD","path":"scood/trainers/udg_trainer.py","file_url":"https://github.com/Jingkang50/ICCV21_SCOOD/blob/HEAD/scood/trainers/udg_trainer.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2007.03317","paper":"/paper/efficient-learning-of-generative-models-via","title":"Efficient Learning of Generative Models via Finite-Difference Score Matching","date":"2020-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taufikxu/FD-ScoreMatching","path":"DeepEBM/Torture/loss_function.py","file_url":"https://github.com/taufikxu/FD-ScoreMatching/blob/HEAD/DeepEBM/Torture/loss_function.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fbd5704657ae5a16","mcp_get_code":{"code_sha256":"fbd5704657ae5a16"}},{"arxiv_id":"2006.08572","paper":"/paper/flexible-dataset-distillation-learn-labels","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","date":"2020-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ondrejbohdal/label-distillation","path":"label_distillation_or2.py","file_url":"https://github.com/ondrejbohdal/label-distillation/blob/HEAD/label_distillation_or2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b40608d582dc51b","mcp_get_code":{"code_sha256":"7b40608d582dc51b"}},{"arxiv_id":"2005.10481","paper":"/paper/aows-adaptive-and-optimal-network-width","title":"AOWS: Adaptive and optimal network width search with latency constraints","date":"2020-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bermanmaxim/AOWS","path":"misc.py","file_url":"https://github.com/bermanmaxim/AOWS/blob/HEAD/misc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"49afece34f1fc351","mcp_get_code":{"code_sha256":"49afece34f1fc351"}},{"arxiv_id":"2004.04037","paper":"/paper/dynabert-dynamic-bert-with-adaptive-width-and","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/pretrained-language-model","path":"DynaBERT/run_glue.py","file_url":"https://github.com/huawei-noah/pretrained-language-model/blob/HEAD/DynaBERT/run_glue.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":"32fee35165e8a309","mcp_get_code":{"code_sha256":"32fee35165e8a309"}},{"arxiv_id":"1911.03809","paper":"/paper/meta-label-correction-for-learning-with-weak-1","title":"Meta Label Correction for Noisy Label Learning","date":"2019-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/mlc","path":"mlc_utils.py","file_url":"https://github.com/microsoft/mlc/blob/HEAD/mlc_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8cf974088fe695e","mcp_get_code":{"code_sha256":"d8cf974088fe695e"}},{"arxiv_id":"Liu_Detecting_Out-of-Distribution_Through_the_Lens_of_Neural_Collapse_CVPR_2025_paper","paper":null,"title":"arXiv:Liu_Detecting_Out-of-Distribution_Through_the_Lens_of_Neural_Collapse_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"litianliu/NCI-OOD","path":"openood/losses/sce.py","file_url":"https://github.com/litianliu/NCI-OOD/blob/HEAD/openood/losses/sce.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":"61492b343324d2ea","mcp_get_code":{"code_sha256":"61492b343324d2ea"}},{"arxiv_id":"2023.findings-acl.810","paper":null,"title":"arXiv:2023.findings-acl.810","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yoyo-yun/DG_RRR","path":"models/KD_zoo.py","file_url":"https://github.com/yoyo-yun/DG_RRR/blob/HEAD/models/KD_zoo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7b18a6f569a07bb","mcp_get_code":{"code_sha256":"d7b18a6f569a07bb"}},{"arxiv_id":"2022.naacl-main.64","paper":null,"title":"arXiv:2022.naacl-main.64","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/MLC","path":"mlc_utils.py","file_url":"https://github.com/microsoft/MLC/blob/HEAD/mlc_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8cf974088fe695e","mcp_get_code":{"code_sha256":"d8cf974088fe695e"}}]}