{"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/log-sum-exp","entry":"log_sum_exp","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":51,"n_papers_ran":31,"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":36,"n_samples_ran":15,"n_samples_fingerprinted":8,"n_places":56,"n_places_pointer_only":11,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":9,"ran_fixture":0,"ran":4,"unverified":21},"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":"2605.00364","paper":"/paper/arxiv-2605-00364","title":"Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"nlp-uoregon/trankit","path":"trankit/layers/crf_layer.py","file_url":"https://github.com/nlp-uoregon/trankit/blob/HEAD/trankit/layers/crf_layer.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":"f9126d3e4828acad","mcp_get_code":{"code_sha256":"f9126d3e4828acad"}},{"arxiv_id":"2507.12075","paper":null,"title":"arXiv:2507.12075","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"booknlp/booknlp","path":"booknlp/common/crf.py","file_url":"https://github.com/booknlp/booknlp/blob/HEAD/booknlp/common/crf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"457e7ee196816a9e","mcp_get_code":{"code_sha256":"457e7ee196816a9e"}},{"arxiv_id":"2402.16302","paper":"/paper/graph-diffusion-policy-optimization","title":"Graph Diffusion Policy Optimization","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/gdpo","path":"model/infomax.py","file_url":"https://github.com/sail-sg/gdpo/blob/HEAD/model/infomax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c03feba6bc4986f6","mcp_get_code":{"code_sha256":"c03feba6bc4986f6"}},{"arxiv_id":"2402.15309","paper":"/paper/counterfactual-generation-with-1","title":"Counterfactual Generation with Identifiability Guarantees","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanqi-qi/matte","path":"models/flow_network.py","file_url":"https://github.com/hanqi-qi/matte/blob/HEAD/models/flow_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2a46cef5131cdc0","mcp_get_code":{"code_sha256":"e2a46cef5131cdc0"}},{"arxiv_id":"2311.01161","paper":"/paper/weakly-supervised-semantic-parsing-with-2","title":"Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"klee972/exec-filter","path":"wikitable/weaksp_em19/wikitable/model/baseline.py","file_url":"https://github.com/klee972/exec-filter/blob/HEAD/wikitable/weaksp_em19/wikitable/model/baseline.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":"3d7631fc6903e509","mcp_get_code":{"code_sha256":"3d7631fc6903e509"}},{"arxiv_id":"2311.01161","paper":"/paper/weakly-supervised-semantic-parsing-with-2","title":"Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"klee972/exec-filter","path":"wikitable/weaksp_em19/wikitable/module/lattice.py","file_url":"https://github.com/klee972/exec-filter/blob/HEAD/wikitable/weaksp_em19/wikitable/module/lattice.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":"c9cc0b6ea0723393","mcp_get_code":{"code_sha256":"c9cc0b6ea0723393"}},{"arxiv_id":"2310.10567","paper":"/paper/regavae-a-retrieval-augmented-gaussian","title":"RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustedllm/regavae","path":"Step1/train_utils.py","file_url":"https://github.com/trustedllm/regavae/blob/HEAD/Step1/train_utils.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":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"2310.01327","paper":"/paper/tactis-2-better-faster-simpler-attentional","title":"TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ServiceNow/TACTiS","path":"tactis/model/flow.py","file_url":"https://github.com/ServiceNow/TACTiS/blob/HEAD/tactis/model/flow.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":"3545580aca8bb732","mcp_get_code":{"code_sha256":"3545580aca8bb732"}},{"arxiv_id":"2309.02190","paper":"/paper/exchanging-based-multimodal-fusion-with","title":"Exchanging-based Multimodal Fusion with Transformer","date":"2023-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"recklessronan/muse","path":"code/models.py","file_url":"https://github.com/recklessronan/muse/blob/HEAD/code/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a42f23f7210ea856","mcp_get_code":{"code_sha256":"a42f23f7210ea856"}},{"arxiv_id":"2210.12582","paper":"/paper/language-model-pre-training-with-sparse","title":"Language Model Pre-Training with Sparse Latent Typing","date":"2022-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renll/sparselt","path":"evaluations/supervised-ie/model.py","file_url":"https://github.com/renll/sparselt/blob/HEAD/evaluations/supervised-ie/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bd9ad74746bdeace","mcp_get_code":{"code_sha256":"bd9ad74746bdeace"}},{"arxiv_id":"2209.02970","paper":"/paper/fengshenbang-1-0-being-the-foundation-of","title":"Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence","date":"2022-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-ccnl/fengshenbang-lm","path":"fengshen/models/DAVAE/DAVAEModel.py","file_url":"https://github.com/idea-ccnl/fengshenbang-lm/blob/HEAD/fengshen/models/DAVAE/DAVAEModel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"2207.06130","paper":"/paper/fuse-it-more-deeply-a-variational-transformer-1","title":"Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation","date":"2022-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenVLG/DELLA","path":"train_utils.py","file_url":"https://github.com/OpenVLG/DELLA/blob/HEAD/train_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"2205.12585","paper":"/paper/a-simple-and-unified-tagging-model-with","title":"TAGPRIME: A Unified Framework for Relational Structure Extraction","date":"2022-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PlusLabNLP/TagPrime","path":"src/model.py","file_url":"https://github.com/PlusLabNLP/TagPrime/blob/HEAD/src/model.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":"bd9ad74746bdeace","mcp_get_code":{"code_sha256":"bd9ad74746bdeace"}},{"arxiv_id":"2201.12179","paper":"/paper/plug-play-attacks-towards-robust-and-flexible","title":"Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SCccc21/Knowledge-Enriched-DMI","path":"attack.py","file_url":"https://github.com/SCccc21/Knowledge-Enriched-DMI/blob/HEAD/attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"265774c3878176e5","mcp_get_code":{"code_sha256":"265774c3878176e5"}},{"arxiv_id":"2110.12381","paper":"/paper/regularizing-variational-autoencoder-with","title":"Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness","date":"2021-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smilesdzgk/du-vae","path":"modules/vae.py","file_url":"https://github.com/smilesdzgk/du-vae/blob/HEAD/modules/vae.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"2108.10612","paper":"/paper/protomil-multiple-instance-learning-with","title":"ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification","date":"2021-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apardyl/protomil","path":"weight_loss.py","file_url":"https://github.com/apardyl/protomil/blob/HEAD/weight_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d90a16e645700743","mcp_get_code":{"code_sha256":"d90a16e645700743"}},{"arxiv_id":"2105.14083","paper":"/paper/rethinking-noisy-label-models-labeler","title":"Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wohlert/semi-supervised-pytorch","path":"semi-supervised/utils.py","file_url":"https://github.com/wohlert/semi-supervised-pytorch/blob/HEAD/semi-supervised/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c96d37e6f13ff9af","mcp_get_code":{"code_sha256":"c96d37e6f13ff9af"}},{"arxiv_id":"2105.06247","paper":"/paper/video-corpus-moment-retrieval-with","title":"Video Corpus Moment Retrieval with Contrastive Learning","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IsaacChanghau/ReLoCLNet","path":"method_tvr/contrastive.py","file_url":"https://github.com/IsaacChanghau/ReLoCLNet/blob/HEAD/method_tvr/contrastive.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"80b5572ac3d22dd3","mcp_get_code":{"code_sha256":"80b5572ac3d22dd3"}},{"arxiv_id":"2103.16130","paper":"/paper/active-learning-for-deep-object-detection-via","title":"Active Learning for Deep Object Detection via Probabilistic Modeling","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/AL-MDN","path":"layers/modules/multibox_loss_gmm.py","file_url":"https://github.com/NVlabs/AL-MDN/blob/HEAD/layers/modules/multibox_loss_gmm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"99c65fd4e843a6a0","mcp_get_code":{"code_sha256":"99c65fd4e843a6a0"}},{"arxiv_id":"2010.04592","paper":"/paper/contrastive-learning-with-hard-negative-1","title":"Contrastive Learning with Hard Negative Samples","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshr17/HCL","path":"graph/cortex_DIM/functions/gan_losses.py","file_url":"https://github.com/joshr17/HCL/blob/HEAD/graph/cortex_DIM/functions/gan_losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c03feba6bc4986f6","mcp_get_code":{"code_sha256":"c03feba6bc4986f6"}},{"arxiv_id":"2010.04092","paper":"/paper/improved-techniques-for-model-inversion-1","title":"Knowledge-Enriched Distributional Model Inversion Attacks","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scccc21/knowledge-enriched-dmi","path":"k+1_gan.py","file_url":"https://github.com/scccc21/knowledge-enriched-dmi/blob/HEAD/k%2B1_gan.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed2c8f941b766ebb","mcp_get_code":{"code_sha256":"ed2c8f941b766ebb"}},{"arxiv_id":"2010.00633","paper":"/paper/discontinuous-constituent-parsing-as-sequence","title":"Discontinuous Constituent Parsing as Sequence Labeling","date":"2020-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aghie/disco2labels","path":"NCRF/model/crf.py","file_url":"https://github.com/aghie/disco2labels/blob/HEAD/NCRF/model/crf.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":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"2008.03736","paper":"/paper/fast-and-accurate-neural-crf-constituency-1","title":"Fast and Accurate Neural CRF Constituency Parsing","date":"2020-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiesutd/NCRFpp","path":"model/crf.py","file_url":"https://github.com/jiesutd/NCRFpp/blob/HEAD/model/crf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"2006.12013","paper":"/paper/club-a-contrastive-log-ratio-upper-bound-of","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Linear95/CLUB","path":"mi_estimators.py","file_url":"https://github.com/Linear95/CLUB/blob/HEAD/mi_estimators.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":"a1572564f4e423a2","mcp_get_code":{"code_sha256":"a1572564f4e423a2"}},{"arxiv_id":"2004.13590","paper":"/paper/maven-a-massive-general-domain-event","title":"MAVEN: A Massive General Domain Event Detection Dataset","date":"2020-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-KEG/MAVEN-dataset","path":"baselines/BERT+CRF/BERT-CRF-MAVEN/crf.py","file_url":"https://github.com/THU-KEG/MAVEN-dataset/blob/HEAD/baselines/BERT%2BCRF/BERT-CRF-MAVEN/crf.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":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"2004.12585","paper":"/paper/a-batch-normalized-inference-network-keeps","title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","date":"2020-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valdersoul/bn-vae","path":"modules/utils.py","file_url":"https://github.com/valdersoul/bn-vae/blob/HEAD/modules/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"2002.11879","paper":"/paper/state-only-imitation-with-transition-dynamics-1","title":"State-only Imitation with Transition Dynamics Mismatch","date":"2020-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tgangwani/RL-Indirect-imitation","path":"i2l/networks/discriminator_model.py","file_url":"https://github.com/tgangwani/RL-Indirect-imitation/blob/HEAD/i2l/networks/discriminator_model.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":"5e0544169ee07211","mcp_get_code":{"code_sha256":"5e0544169ee07211"}},{"arxiv_id":"2002.01685","paper":"/paper/parsing-as-pretraining","title":"Parsing as Pretraining","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aghie/parsing-as-pretraining","path":"NCRFpp/model/crf.py","file_url":"https://github.com/aghie/parsing-as-pretraining/blob/HEAD/NCRFpp/model/crf.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":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"1911.02257","paper":"/paper/hierarchical-contextualized-representation","title":"Hierarchical Contextualized Representation for Named Entity Recognition","date":"2019-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cslydia/Hire-NER","path":"model/crf.py","file_url":"https://github.com/cslydia/Hire-NER/blob/HEAD/model/crf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"1906.01378","paper":"/paper/distantly-supervised-named-entity-recognition","title":"Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"v-mipeng/LexiconNER","path":"sub_model.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/sub_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"390527929922fd01","mcp_get_code":{"code_sha256":"390527929922fd01"}},{"arxiv_id":"1904.02399","paper":"/paper/riemannian-normalizing-flow-on-variational","title":"Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling","date":"2019-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kingofspace0wzz/wae-rnf-lm","path":"model.py","file_url":"https://github.com/kingofspace0wzz/wae-rnf-lm/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b95c648cb0fb5f2","mcp_get_code":{"code_sha256":"7b95c648cb0fb5f2"}},{"arxiv_id":"1902.08605","paper":"/paper/centroid-networks-for-few-shot-clustering-and","title":"Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time","date":"2019-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gabrielhuang/centroid-networks","path":"protonets/models/wasserstein.py","file_url":"https://github.com/gabrielhuang/centroid-networks/blob/HEAD/protonets/models/wasserstein.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62fa5972227f4654","mcp_get_code":{"code_sha256":"62fa5972227f4654"}},{"arxiv_id":"1902.04999","paper":"/paper/wasserstein-barycenter-model-ensembling-1","title":"Wasserstein Barycenter Model Ensembling","date":"2019-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/wasserstein-barycenters","path":"barycenter.py","file_url":"https://github.com/IBM/wasserstein-barycenters/blob/HEAD/barycenter.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":"961877103f86fea9","mcp_get_code":{"code_sha256":"961877103f86fea9"}},{"arxiv_id":"1902.00640","paper":"/paper/meta-particle-flow-for-sequential-bayesian","title":"Particle Flow Bayes' Rule","date":"2019-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinshi-chen/MetaParticleFlow","path":"pfbayes/common/torch_utils.py","file_url":"https://github.com/xinshi-chen/MetaParticleFlow/blob/HEAD/pfbayes/common/torch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c56e632880df4e3","mcp_get_code":{"code_sha256":"4c56e632880df4e3"}},{"arxiv_id":"1901.05534","paper":"/paper/lagging-inference-networks-and-posterior","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","date":"2019-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxhe/vae-lagging-encoder","path":"modules/utils.py","file_url":"https://github.com/jxhe/vae-lagging-encoder/blob/HEAD/modules/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5efe6eb2209f6591","mcp_get_code":{"code_sha256":"5efe6eb2209f6591"}},{"arxiv_id":"1811.11212","paper":"/paper/self-supervised-generative-adversarial","title":"Self-Supervised GANs via Auxiliary Rotation Loss","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vandit15/Self-Supervised-Gans-Pytorch","path":"ops.py","file_url":"https://github.com/vandit15/Self-Supervised-Gans-Pytorch/blob/HEAD/ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a0d455dcdcf2ec5","mcp_get_code":{"code_sha256":"6a0d455dcdcf2ec5"}},{"arxiv_id":"1811.11212","paper":"/paper/self-supervised-generative-adversarial","title":"Self-Supervised GANs via Auxiliary Rotation Loss","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangqianhui/Self-Supervised-GANs","path":"ops.py","file_url":"https://github.com/zhangqianhui/Self-Supervised-GANs/blob/HEAD/ops.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":"dffe333c7a3624a0","mcp_get_code":{"code_sha256":"dffe333c7a3624a0"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sberbank-ai/ner-bert","path":"modules/layers/ncrf.py","file_url":"https://github.com/sberbank-ai/ner-bert/blob/HEAD/modules/layers/ncrf.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":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sberbank-ai/ner-bert","path":"modules/layers/crf.py","file_url":"https://github.com/sberbank-ai/ner-bert/blob/HEAD/modules/layers/crf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"913ba2502c2a2780","mcp_get_code":{"code_sha256":"913ba2502c2a2780"}},{"arxiv_id":"1807.10589","paper":"/paper/diverse-feature-visualizations-reveal","title":"Diverse feature visualizations reveal invariances in early layers of deep neural networks","date":"2018-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacadena/diverse_feature_vis","path":"pixel-cnn/pixel_cnn_pp/nn.py","file_url":"https://github.com/sacadena/diverse_feature_vis/blob/HEAD/pixel-cnn/pixel_cnn_pp/nn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba937f5383eb9016","mcp_get_code":{"code_sha256":"ba937f5383eb9016"}},{"arxiv_id":"1807.07281","paper":"/paper/clarinet-parallel-wave-generation-in-end-to","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","date":"2018-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiberiu44/TTS-Cube","path":"cube/networks/loss.py","file_url":"https://github.com/tiberiu44/TTS-Cube/blob/HEAD/cube/networks/loss.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":"a42f23f7210ea856","mcp_get_code":{"code_sha256":"a42f23f7210ea856"}},{"arxiv_id":"1806.05626","paper":"/paper/ncrf-an-open-source-neural-sequence-labeling","title":"NCRF++: An Open-source Neural Sequence Labeling Toolkit","date":"2018-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiesutd/PyTorchSeqLabel","path":"model/crf.py","file_url":"https://github.com/jiesutd/PyTorchSeqLabel/blob/HEAD/model/crf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"1806.00271","paper":"/paper/learning-neural-random-fields-with-inclusive","title":"Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection","date":"2018-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-spmi/Inclusive-NRF","path":"pytorch_generation/CIFAR_NRF_supervised.py","file_url":"https://github.com/thu-spmi/Inclusive-NRF/blob/HEAD/pytorch_generation/CIFAR_NRF_supervised.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"79526833a41be6f5","mcp_get_code":{"code_sha256":"79526833a41be6f5"}},{"arxiv_id":"1802.07595","paper":"/paper/smooth-loss-functions-for-deep-top-k","title":"Smooth Loss Functions for Deep Top-k Classification","date":"2018-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oval-group/smooth-topk","path":"topk/polynomial/sp.py","file_url":"https://github.com/oval-group/smooth-topk/blob/HEAD/topk/polynomial/sp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17dff13c779067fd","mcp_get_code":{"code_sha256":"17dff13c779067fd"}},{"arxiv_id":"1702.08658","paper":"/paper/towards-deeper-understanding-of-variational","title":"Towards Deeper Understanding of Variational Autoencoding Models","date":"2017-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShengjiaZhao/Generalized-PixelVAE","path":"pixel_cnn_pp/nn.py","file_url":"https://github.com/ShengjiaZhao/Generalized-PixelVAE/blob/HEAD/pixel_cnn_pp/nn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad066f5de5f84073","mcp_get_code":{"code_sha256":"ad066f5de5f84073"}},{"arxiv_id":"1603.01360","paper":"/paper/neural-architectures-for-named-entity","title":"Neural Architectures for Named Entity Recognition","date":"2016-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZubinGou/NER-BiLSTM-CRF-PyTorch","path":"src/model.py","file_url":"https://github.com/ZubinGou/NER-BiLSTM-CRF-PyTorch/blob/HEAD/src/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4329236872658c9","mcp_get_code":{"code_sha256":"d4329236872658c9"}},{"arxiv_id":"1603.01360","paper":"/paper/neural-architectures-for-named-entity","title":"Neural Architectures for Named Entity Recognition","date":"2016-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyHaker/NamedEntityRecognition","path":"src/LSTM-CNNs-CRF/model.py","file_url":"https://github.com/yyHaker/NamedEntityRecognition/blob/HEAD/src/LSTM-CNNs-CRF/model.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":"ca4d0de367bcc625","mcp_get_code":{"code_sha256":"ca4d0de367bcc625"}},{"arxiv_id":"1603.01354","paper":"/paper/end-to-end-sequence-labeling-via-bi","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","date":"2016-03-04","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":"d4329236872658c9","mcp_get_code":{"code_sha256":"d4329236872658c9"}},{"arxiv_id":"1511.08308","paper":"/paper/named-entity-recognition-with-bidirectional","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","date":"2015-11-26","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":"d4329236872658c9","mcp_get_code":{"code_sha256":"d4329236872658c9"}},{"arxiv_id":"1508.01991","paper":"/paper/bidirectional-lstm-crf-models-for-sequence","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","date":"2015-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jidasheng/bi-lstm-crf","path":"bi_lstm_crf/model/crf.py","file_url":"https://github.com/jidasheng/bi-lstm-crf/blob/HEAD/bi_lstm_crf/model/crf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"270d6bd48a51f2ae","mcp_get_code":{"code_sha256":"270d6bd48a51f2ae"}},{"arxiv_id":"1505.08075","paper":"/paper/transition-based-dependency-parsing-with-2","title":"Transition-Based Dependency Parsing with Stack Long Short-Term Memory","date":"2015-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mstrise/dep2label","path":"model/crf.py","file_url":"https://github.com/mstrise/dep2label/blob/HEAD/model/crf.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":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}},{"arxiv_id":"2024.naacl-long.343","paper":null,"title":"arXiv:2024.naacl-long.343","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"king-yyf/CMeKG_tools","path":"model_cws/crf.py","file_url":"https://github.com/king-yyf/CMeKG_tools/blob/HEAD/model_cws/crf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"390527929922fd01","mcp_get_code":{"code_sha256":"390527929922fd01"}},{"arxiv_id":"2024.naacl-long.343","paper":null,"title":"arXiv:2024.naacl-long.343","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"king-yyf/CMeKG_tools","path":"model_ner/crf.py","file_url":"https://github.com/king-yyf/CMeKG_tools/blob/HEAD/model_ner/crf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c72bb90ead60151","mcp_get_code":{"code_sha256":"8c72bb90ead60151"}},{"arxiv_id":"2024.naacl-long.241","paper":null,"title":"arXiv:2024.naacl-long.241","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jiadongzh/iacos","path":"modelx/rnnx.py","file_url":"https://github.com/jiadongzh/iacos/blob/HEAD/modelx/rnnx.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":"05c860970db7fdc1","mcp_get_code":{"code_sha256":"05c860970db7fdc1"}},{"arxiv_id":"2024.findings-acl.760","paper":null,"title":"arXiv:2024.findings-acl.760","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ej0cl6/TextEE","path":"TextEE/models/AMRIE/E2Emodel.py","file_url":"https://github.com/ej0cl6/TextEE/blob/HEAD/TextEE/models/AMRIE/E2Emodel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bd9ad74746bdeace","mcp_get_code":{"code_sha256":"bd9ad74746bdeace"}},{"arxiv_id":"2023.emnlp-demo.11","paper":null,"title":"arXiv:2023.emnlp-demo.11","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jiesutd/YATO","path":"model/crf.py","file_url":"https://github.com/jiesutd/YATO/blob/HEAD/model/crf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e960fbb64668568","mcp_get_code":{"code_sha256":"8e960fbb64668568"}}]}