{"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/label-smoothed-nll-loss","entry":"label_smoothed_nll_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":43,"n_papers_ran":20,"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":22,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":47,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":1,"ran":0,"unverified":16},"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":"2502.19941","paper":"/paper/alleviating-distribution-shift-in-synthetic","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/njuqe","path":"njuqe/criterions/qe_loss.py","file_url":"https://github.com/NJUNLP/njuqe/blob/HEAD/njuqe/criterions/qe_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aeee078a872841dc","mcp_get_code":{"code_sha256":"aeee078a872841dc"}},{"arxiv_id":"2502.19870","paper":"/paper/mmke-bench-a-multimodal-editing-benchmark-for","title":"MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MMKE-Bench-ICLR/MMKE-Bench","path":"KE/src/utils.py","file_url":"https://github.com/MMKE-Bench-ICLR/MMKE-Bench/blob/HEAD/KE/src/utils.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2409.19872","paper":"/paper/towards-unified-multimodal-editing-with","title":"Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beepkh/unike","path":"easyeditor/models/unike/unike_main.py","file_url":"https://github.com/beepkh/unike/blob/HEAD/easyeditor/models/unike/unike_main.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2405.18906","paper":"/paper/language-generation-with-strictly-proper","title":"Language Generation with Strictly Proper Scoring Rules","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2404.00656","paper":"/paper/wavllm-towards-robust-and-adaptive-speech","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/speecht5","path":"SpeechT5/speecht5/criterions/speech_to_text_loss.py","file_url":"https://github.com/microsoft/speecht5/blob/HEAD/SpeechT5/speecht5/criterions/speech_to_text_loss.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2403.07350","paper":"/paper/kebench-a-benchmark-on-knowledge-editing-for","title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VLKEB/VLKEB","path":"KE/src/utils.py","file_url":"https://github.com/VLKEB/VLKEB/blob/HEAD/KE/src/utils.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2402.01404","paper":"/paper/on-measuring-context-utilization-in-document","title":"On Measuring Context Utilization in Document-Level MT Systems","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wafaa014/context-utilization","path":"contextual-mt/contextual_mt/attn_reg_loss.py","file_url":"https://github.com/Wafaa014/context-utilization/blob/HEAD/contextual-mt/contextual_mt/attn_reg_loss.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":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2306.02115","paper":"/paper/table-and-image-generation-for-investigating","title":"Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models","date":"2023-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OFA-Sys/OFA","path":"criterions/label_smoothed_encouraging_loss.py","file_url":"https://github.com/OFA-Sys/OFA/blob/HEAD/criterions/label_smoothed_encouraging_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"cbd8615e3eba731b","mcp_get_code":{"code_sha256":"cbd8615e3eba731b"}},{"arxiv_id":"2305.17100","paper":"/paper/biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taokz/biomedgpt","path":"criterions/label_smoothed_encouraging_loss.py","file_url":"https://github.com/taokz/biomedgpt/blob/HEAD/criterions/label_smoothed_encouraging_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"cbd8615e3eba731b","mcp_get_code":{"code_sha256":"cbd8615e3eba731b"}},{"arxiv_id":"2305.17100","paper":"/paper/biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taokz/biomedgpt","path":"criterions/label_smoothed_cross_entropy.py","file_url":"https://github.com/taokz/biomedgpt/blob/HEAD/criterions/label_smoothed_cross_entropy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"cdbc222d0057fb31","mcp_get_code":{"code_sha256":"cdbc222d0057fb31"}},{"arxiv_id":"2305.15387","paper":"/paper/peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aviclu/peekacross","path":"finetune_summarization.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/finetune_summarization.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e9a5fc2ab282ff2","mcp_get_code":{"code_sha256":"5e9a5fc2ab282ff2"}},{"arxiv_id":"2304.03548","paper":"/paper/gemini-controlling-the-sentence-level-writing","title":"GEMINI: Controlling the Sentence-level Writing Style for Abstractive Text Summarization","date":"2023-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baoguangsheng/gemini","path":"fairseq/criterions/label_smoothed_cross_entropy_gemini.py","file_url":"https://github.com/baoguangsheng/gemini/blob/HEAD/fairseq/criterions/label_smoothed_cross_entropy_gemini.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3986ca46566273de","mcp_get_code":{"code_sha256":"3986ca46566273de"}},{"arxiv_id":"2302.05574","paper":"/paper/napss-paragraph-level-medical-text","title":"NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization","date":"2023-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LuJunru/NapSS","path":"modeling/utils.py","file_url":"https://github.com/LuJunru/NapSS/blob/HEAD/modeling/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2212.04231","paper":"/paper/harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-x/ofa-x","path":"OFA/criterions/label_smoothed_encouraging_loss.py","file_url":"https://github.com/ofa-x/ofa-x/blob/HEAD/OFA/criterions/label_smoothed_encouraging_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cbd8615e3eba731b","mcp_get_code":{"code_sha256":"cbd8615e3eba731b"}},{"arxiv_id":"2212.04231","paper":"/paper/harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-x/ofa-x","path":"OFA/criterions/label_smoothed_cross_entropy.py","file_url":"https://github.com/ofa-x/ofa-x/blob/HEAD/OFA/criterions/label_smoothed_cross_entropy.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":"cdbc222d0057fb31","mcp_get_code":{"code_sha256":"cdbc222d0057fb31"}},{"arxiv_id":"2212.04231","paper":"/paper/harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-x/ofa-x","path":"OFA/criterions/label_smoothed_cross_entropy_expl.py","file_url":"https://github.com/ofa-x/ofa-x/blob/HEAD/OFA/criterions/label_smoothed_cross_entropy_expl.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":"3a3448cb08438214","mcp_get_code":{"code_sha256":"3a3448cb08438214"}},{"arxiv_id":"2210.12357","paper":"/paper/information-transport-based-policy-for","title":"Information-Transport-based Policy for Simultaneous Translation","date":"2022-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictnlp/itst","path":"fairseq/criterions/label_smoothed_cross_entropy_with_itst_s2t_flexible_predecision.py","file_url":"https://github.com/ictnlp/itst/blob/HEAD/fairseq/criterions/label_smoothed_cross_entropy_with_itst_s2t_flexible_predecision.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2210.05144","paper":"/paper/mixture-of-attention-heads-selecting","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","date":"2022-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yikangshen/moa","path":"moa_loss.py","file_url":"https://github.com/yikangshen/moa/blob/HEAD/moa_loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2210.00312","paper":"/paper/multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/MKGformer","path":"MKG/models/utils.py","file_url":"https://github.com/zjunlp/MKGformer/blob/HEAD/MKG/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fadc10fc2c451c92","mcp_get_code":{"code_sha256":"fadc10fc2c451c92"}},{"arxiv_id":"2208.06073","paper":"/paper/conditional-antibody-design-as-3d-equivariant","title":"Conditional Antibody Design as 3D Equivariant Graph Translation","date":"2022-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lkny123/agn","path":"src/modules/cross_entropy.py","file_url":"https://github.com/lkny123/agn/blob/HEAD/src/modules/cross_entropy.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":"64b95cd94f34f39e","mcp_get_code":{"code_sha256":"64b95cd94f34f39e"}},{"arxiv_id":"2205.13401","paper":"/paper/your-transformer-may-not-be-as-powerful-as","title":"Your Transformer May Not be as Powerful as You Expect","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lsj2408/urpe","path":"fairseq/criterions/label_smoothed_cross_entropy.py","file_url":"https://github.com/lsj2408/urpe/blob/HEAD/fairseq/criterions/label_smoothed_cross_entropy.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":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2204.07937","paper":"/paper/unsupervised-cross-task-generalization-via","title":"Unsupervised Cross-Task Generalization via Retrieval Augmentation","date":"2022-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"INK-USC/ReCross","path":"metax/models/utils.py","file_url":"https://github.com/INK-USC/ReCross/blob/HEAD/metax/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9d63f8ce1c64098","mcp_get_code":{"code_sha256":"e9d63f8ce1c64098"}},{"arxiv_id":"2203.07836","paper":"/paper/graph-pre-training-for-amr-parsing-and-1","title":"Graph Pre-training for AMR Parsing and Generation","date":"2022-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"muyeby/AMRBART","path":"fine-tune/seq2seq_trainer.py","file_url":"https://github.com/muyeby/AMRBART/blob/HEAD/fine-tune/seq2seq_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fadc10fc2c451c92","mcp_get_code":{"code_sha256":"fadc10fc2c451c92"}},{"arxiv_id":"2110.08499","paper":"/paper/primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/primer","path":"script/primer_main.py","file_url":"https://github.com/allenai/primer/blob/HEAD/script/primer_main.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":"5e9a5fc2ab282ff2","mcp_get_code":{"code_sha256":"5e9a5fc2ab282ff2"}},{"arxiv_id":"2109.04096","paper":"/paper/a-three-stage-learning-framework-for-low","title":"A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neukg/kat-tslf","path":"dial/utils.py","file_url":"https://github.com/neukg/kat-tslf/blob/HEAD/dial/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2109.03792","paper":"/paper/highly-parallel-autoregressive-entity-linking","title":"Highly Parallel Autoregressive Entity Linking with Discriminative Correction","date":"2021-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicola-decao/efficient-autoregressive-EL","path":"src/utils.py","file_url":"https://github.com/nicola-decao/efficient-autoregressive-EL/blob/HEAD/src/utils.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2108.11846","paper":"/paper/alleviating-exposure-bias-via-contrastive","title":"Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shichaosun/conabssum","path":"src/utils.py","file_url":"https://github.com/shichaosun/conabssum/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":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2106.02208","paper":"/paper/berttune-fine-tuning-neural-machine","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ijauregiCMCRC/fairseq-bert-loss","path":"fairseq/criterions/lsce_with_bert_regularization.py","file_url":"https://github.com/ijauregiCMCRC/fairseq-bert-loss/blob/HEAD/fairseq/criterions/lsce_with_bert_regularization.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":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2105.11269","paper":"/paper/neural-machine-translation-with-monolingual","title":"Neural Machine Translation with Monolingual Translation Memory","date":"2021-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jcyk/copyisallyouneed","path":"generator.py","file_url":"https://github.com/jcyk/copyisallyouneed/blob/HEAD/generator.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":"6ee29e1e1f56a934","mcp_get_code":{"code_sha256":"6ee29e1e1f56a934"}},{"arxiv_id":"2105.11174","paper":"/paper/retrieval-enhanced-model-for-commonsense","title":"Retrieval Enhanced Model for Commonsense Generation","date":"2021-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HanNight/RE-T5","path":"code/RE-T5/utils.py","file_url":"https://github.com/HanNight/RE-T5/blob/HEAD/code/RE-T5/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":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2105.04779","paper":"/paper/el-attention-memory-efficient-lossless","title":"EL-Attention: Memory Efficient Lossless Attention for Generation","date":"2021-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/fastseq","path":"fastseq_cli/transformers_utils.py","file_url":"https://github.com/microsoft/fastseq/blob/HEAD/fastseq_cli/transformers_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2104.08691","paper":"/paper/the-power-of-scale-for-parameter-efficient","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","date":"2021-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"exelents/soft-prompt-tuning","path":"utils1.py","file_url":"https://github.com/exelents/soft-prompt-tuning/blob/HEAD/utils1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2104.08400","paper":"/paper/structure-aware-abstractive-conversation","title":"Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GT-SALT/Structure-Aware-BART","path":"src/utils.py","file_url":"https://github.com/GT-SALT/Structure-Aware-BART/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":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2104.08164","paper":"/paper/editing-factual-knowledge-in-language-models","title":"Editing Factual Knowledge in Language Models","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicola-decao/KnowledgeEditor","path":"src/utils.py","file_url":"https://github.com/nicola-decao/KnowledgeEditor/blob/HEAD/src/utils.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2010.08014","paper":"/paper/gsum-a-general-framework-for-guided-neural","title":"GSum: A General Framework for Guided Neural Abstractive Summarization","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neulab/guided_summarization","path":"bart/fairseq/criterions/guided_label_smoothed_cross_entropy.py","file_url":"https://github.com/neulab/guided_summarization/blob/HEAD/bart/fairseq/criterions/guided_label_smoothed_cross_entropy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b796617355839eb2","mcp_get_code":{"code_sha256":"b796617355839eb2"}},{"arxiv_id":"2008.07772","paper":"/paper/very-deep-transformers-for-neural-machine","title":"Very Deep Transformers for Neural Machine Translation","date":"2020-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/deepnmt","path":"deepnmt/adv_label_smoothed_cross_entropy.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/deepnmt/adv_label_smoothed_cross_entropy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0084024f3f3086ec","mcp_get_code":{"code_sha256":"0084024f3f3086ec"}},{"arxiv_id":"2007.08426","paper":"/paper/investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UKPLab/plms-graph2text","path":"agenda/utils.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/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":"e386d3a24af4d168","mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"arxiv_id":"2006.16336","paper":"/paper/learning-sparse-prototypes-for-text","title":"Learning Sparse Prototypes for Text Generation","date":"2020-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxhe/sparse-text-prototype","path":"sparse_prototype/guu_criterion.py","file_url":"https://github.com/jxhe/sparse-text-prototype/blob/HEAD/sparse_prototype/guu_criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c3cce785199ac95","mcp_get_code":{"code_sha256":"2c3cce785199ac95"}},{"arxiv_id":"2006.16336","paper":"/paper/learning-sparse-prototypes-for-text","title":"Learning Sparse Prototypes for Text Generation","date":"2020-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxhe/sparse-text-prototype","path":"sparse_prototype/lm_criterion.py","file_url":"https://github.com/jxhe/sparse-text-prototype/blob/HEAD/sparse_prototype/lm_criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33456d398c6c40ab","mcp_get_code":{"code_sha256":"33456d398c6c40ab"}},{"arxiv_id":"2005.01107","paper":"/paper/transformer-based-end-to-end-question","title":"Simplifying Paragraph-level Question Generation via Transformer Language Models","date":"2020-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AndreasInk/Quiz-APIv2","path":"utils.py","file_url":"https://github.com/AndreasInk/Quiz-APIv2/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e8522233e82d5b1","mcp_get_code":{"code_sha256":"2e8522233e82d5b1"}},{"arxiv_id":"2004.05572","paper":"/paper/amr-parsing-via-graph-sequence-iterative","title":"AMR Parsing via Graph-Sequence Iterative Inference","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjascob/amrlib","path":"amrlib/models/parse_gsii/modules/parser.py","file_url":"https://github.com/bjascob/amrlib/blob/HEAD/amrlib/models/parse_gsii/modules/parser.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":"2746494f3bbf25b3","mcp_get_code":{"code_sha256":"2746494f3bbf25b3"}},{"arxiv_id":"2004.05150","paper":"/paper/longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"a-rios/ats-models","path":"ats_models/metrics.py","file_url":"https://github.com/a-rios/ats-models/blob/HEAD/ats_models/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":"9c78ceb4210479cf","mcp_get_code":{"code_sha256":"9c78ceb4210479cf"}},{"arxiv_id":"2002.06714","paper":"/paper/multi-layer-representation-fusion-for-neural-2","title":"Multi-layer Representation Fusion for Neural Machine Translation","date":"2020-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"1908.04319","paper":"/paper/neural-text-generation-with-unlikelihood","title":"Neural Text Generation with Unlikelihood Training","date":"2019-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"griff4692/calibrating-summaries","path":"model/contrast_utils.py","file_url":"https://github.com/griff4692/calibrating-summaries/blob/HEAD/model/contrast_utils.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":"a261ba0741e044d7","mcp_get_code":{"code_sha256":"a261ba0741e044d7"}},{"arxiv_id":"1610.02424","paper":"/paper/diverse-beam-search-decoding-diverse","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","date":"2016-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"26da4f92ba56e785","mcp_get_code":{"code_sha256":"26da4f92ba56e785"}},{"arxiv_id":"2023.findings-emnlp.978","paper":null,"title":"arXiv:2023.findings-emnlp.978","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"libeineu/MMT-VQA","path":"fairseq/criterions/label_smoothed_cross_entropy_mmt_vqa.py","file_url":"https://github.com/libeineu/MMT-VQA/blob/HEAD/fairseq/criterions/label_smoothed_cross_entropy_mmt_vqa.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":"96b6713ff1c322ca","mcp_get_code":{"code_sha256":"96b6713ff1c322ca"}},{"arxiv_id":"2022.naacl-main.342","paper":null,"title":"arXiv:2022.naacl-main.342","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"epfl-dlab/GenIE","path":"genie/models/utils.py","file_url":"https://github.com/epfl-dlab/GenIE/blob/HEAD/genie/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6aa4b196697151e","mcp_get_code":{"code_sha256":"e6aa4b196697151e"}}]}