{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/memorization/papers/4","list_of":"/task/memorization","task":"Memorization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":11,"rows_per_page":100,"rows":[301,400],"of":1088,"counts":{"archive_papers_tagged":1088,"with_a_code_link":438,"where_syntology_ran_a_sample":177,"not_listed_spam_title":0,"listed":1088,"listed_where_code_ran":177,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":148,"every_run_a_failure_of_syntologys_instrument":29,"listed_with_a_run_with_no_instrument_failure":148,"listed_every_run_a_failure_of_syntologys_instrument":29,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/memorization","prev":"/task/memorization/papers/3","next":"/task/memorization/papers/5","papers":[{"url":"/paper/progress-measures-for-grokking-via","slug":"progress-measures-for-grokking-via","title":"Progress measures for grokking via mechanistic interpretability","date":"2023-01-12","arxiv_id":"2301.05217","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/progress-measures-for-grokking-via#ran","syntology_url":"https://syntology.ai/paper/2301.05217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05217"}},"official":{"repos":["mechanistic-interpretability-grokking/progress-measures-paper"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/odim-an-efficient-method-to-detect-outliers","slug":"odim-an-efficient-method-to-detect-outliers","title":"ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models","date":"2023-01-11","arxiv_id":"2301.04257","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/odim-an-efficient-method-to-detect-outliers#ran","syntology_url":"https://syntology.ai/paper/2301.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04257"}},"official":{"repos":["jshwang0311/odim"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/disc-learning-from-noisy-labels-via-dynamic","slug":"disc-learning-from-noisy-labels-via-dynamic","title":"DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/holistic-label-correction-for-noisy-multi","slug":"holistic-label-correction-for-noisy-multi","title":"Holistic Label Correction for Noisy Multi-Label Classification","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prototypical-mixing-and-retrieval-based","slug":"prototypical-mixing-and-retrieval-based","title":"Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bygpt5-end-to-end-style-conditioned-poetry#ran","syntology_url":"https://syntology.ai/paper/2212.10474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10474"}},"official":{"repos":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/execution-based-evaluation-for-open-domain","slug":"execution-based-evaluation-for-open-domain","title":"Execution-Based Evaluation for Open-Domain Code Generation","date":"2022-12-20","arxiv_id":"2212.10481","repositories_listed":1,"syntology":null},{"url":"/paper/when-not-to-trust-language-models","slug":"when-not-to-trust-language-models","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","date":"2022-12-20","arxiv_id":"2212.10511","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/when-not-to-trust-language-models#ran","syntology_url":"https://syntology.ai/paper/2212.10511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10511"}},"official":{"repos":["alextmallen/adaptive-retrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/planting-and-mitigating-memorized-content-in","slug":"planting-and-mitigating-memorized-content-in","title":"Planting and Mitigating Memorized Content in Predictive-Text Language Models","date":"2022-12-16","arxiv_id":"2212.08619","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-unlabeled-data-to-track","slug":"leveraging-unlabeled-data-to-track","title":"Leveraging Unlabeled Data to Track Memorization","date":"2022-12-08","arxiv_id":"2212.04461","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-unlabeled-data-to-track#ran","syntology_url":"https://syntology.ai/paper/2212.04461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04461"}},"official":{"repos":["mahf93/tracking-memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-study-on-extracting-named-entities-from","slug":"a-study-on-extracting-named-entities-from","title":"Memorization of Named Entities in Fine-tuned BERT Models","date":"2022-12-07","arxiv_id":"2212.03749","repositories_listed":1,"syntology":null},{"url":"/paper/neural-representations-reveal-distinct-modes","slug":"neural-representations-reveal-distinct-modes","title":"Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks","date":"2022-12-01","arxiv_id":"2212.00771","repositories_listed":1,"syntology":null},{"url":"/paper/data-provenance-inference-in-machine-learning","slug":"data-provenance-inference-in-machine-learning","title":"Data Origin Inference in Machine Learning","date":"2022-11-24","arxiv_id":"2211.13416","repositories_listed":1,"syntology":null},{"url":"/paper/validating-large-language-models-with-relm","slug":"validating-large-language-models-with-relm","title":"Validating Large Language Models with ReLM","date":"2022-11-21","arxiv_id":"2211.15458","repositories_listed":1,"syntology":null},{"url":"/paper/why-deep-learning-generalizes","slug":"why-deep-learning-generalizes","title":"Why Deep Learning Generalizes","date":"2022-11-17","arxiv_id":"2211.09639","repositories_listed":1,"syntology":null},{"url":"/paper/multi-center-anatomical-segmentation-with","slug":"multi-center-anatomical-segmentation-with","title":"Multi-center anatomical segmentation with heterogeneous labels via landmark-based models","date":"2022-11-14","arxiv_id":"2211.07395","repositories_listed":1,"syntology":null},{"url":"/paper/robust-training-of-graph-neural-networks-via","slug":"robust-training-of-graph-neural-networks-via","title":"Robust Training of Graph Neural Networks via Noise Governance","date":"2022-11-12","arxiv_id":"2211.06614","repositories_listed":1,"syntology":null},{"url":"/paper/memonet-memorizing-representations-of-all","slug":"memonet-memorizing-representations-of-all","title":"MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction","date":"2022-10-25","arxiv_id":"2211.01334","repositories_listed":1,"syntology":null},{"url":"/paper/finding-memo-extractive-memorization-in","slug":"finding-memo-extractive-memorization-in","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","date":"2022-10-24","arxiv_id":"2210.12929","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-training-sample-memorization-in-gans","slug":"reducing-training-sample-memorization-in-gans","title":"Reducing Training Sample Memorization in GANs by Training with Memorization Rejection","date":"2022-10-21","arxiv_id":"2210.12231","repositories_listed":1,"syntology":null},{"url":"/paper/fregan-exploiting-frequency-components-for","slug":"fregan-exploiting-frequency-components-for","title":"FreGAN: Exploiting Frequency Components for Training GANs under Limited Data","date":"2022-10-11","arxiv_id":"2210.05461","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fregan-exploiting-frequency-components-for#ran","syntology_url":"https://syntology.ai/paper/2210.05461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05461"}},"official":{"repos":["kobeshegu/fregan_neurips2022"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-transformer-memorization-recall","slug":"understanding-transformer-memorization-recall","title":"Understanding Transformer Memorization Recall Through Idioms","date":"2022-10-07","arxiv_id":"2210.03588","repositories_listed":1,"syntology":null},{"url":"/paper/small-transformers-compute-universal-metric","slug":"small-transformers-compute-universal-metric","title":"Small Transformers Compute Universal Metric Embeddings","date":"2022-09-14","arxiv_id":"2209.06788","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-privacy-effect-of-data-enhancement-via","slug":"on-the-privacy-effect-of-data-enhancement-via","title":"On the Privacy Effect of Data Enhancement via the Lens of Memorization","date":"2022-08-17","arxiv_id":"2208.08270","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-privacy-effect-of-data-enhancement-via#ran","syntology_url":"https://syntology.ai/paper/2208.08270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08270"}},"official":{"repos":["lixiaothu/privacy_and_aug"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-localization-via-few-shot-scene-region","slug":"visual-localization-via-few-shot-scene-region","title":"Visual Localization via Few-Shot Scene Region Classification","date":"2022-08-14","arxiv_id":"2208.06933","repositories_listed":1,"syntology":null},{"url":"/paper/lidar-based-localization-using-universal","slug":"lidar-based-localization-using-universal","title":"LiDAR-based localization using universal encoding and memory-aware regression","date":"2022-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/continual-variational-autoencoder-learning","slug":"continual-variational-autoencoder-learning","title":"Continual Variational Autoencoder Learning via Online Cooperative Memorization","date":"2022-07-20","arxiv_id":"2207.10131","repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-evaluation-for-dynamic-link","slug":"towards-better-evaluation-for-dynamic-link","title":"Towards Better Evaluation for Dynamic Link Prediction","date":"2022-07-20","arxiv_id":"2207.10128","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-better-evaluation-for-dynamic-link#ran","syntology_url":"https://syntology.ai/paper/2207.10128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10128"}},"official":{"repos":["fpour/dgb"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalization-memorization-machines","slug":"generalization-memorization-machines","title":"Generalization-Memorization Machines","date":"2022-07-08","arxiv_id":"2207.03976","repositories_listed":1,"syntology":null},{"url":"/paper/the-privacy-onion-effect-memorization-is","slug":"the-privacy-onion-effect-memorization-is","title":"The Privacy Onion Effect: Memorization is Relative","date":"2022-06-21","arxiv_id":"2206.10469","repositories_listed":1,"syntology":null},{"url":"/paper/fewer-errors-but-more-stereotypes-the-effect","slug":"fewer-errors-but-more-stereotypes-the-effect","title":"Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias","date":"2022-06-20","arxiv_id":"2206.09860","repositories_listed":1,"syntology":null},{"url":"/paper/memorization-dilation-modeling-neural","slug":"memorization-dilation-modeling-neural","title":"Memorization-Dilation: Modeling Neural Collapse Under Label Noise","date":"2022-06-11","arxiv_id":"2206.05530","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/memorization-dilation-modeling-neural#ran","syntology_url":"https://syntology.ai/paper/2206.05530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05530"}},"official":{"repos":["julilien/memorizationdilation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/large-loss-matters-in-weakly-supervised-multi-1","slug":"large-loss-matters-in-weakly-supervised-multi-1","title":"Large Loss Matters in Weakly Supervised Multi-Label Classification","date":"2022-06-08","arxiv_id":"2206.03740","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-loss-matters-in-weakly-supervised-multi-1#ran","syntology_url":"https://syntology.ai/paper/2206.03740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03740"}},"official":{"repos":["snucml/largelossmatters"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-large-pre-trained-language-models-leaking","slug":"are-large-pre-trained-language-models-leaking","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","date":"2022-05-25","arxiv_id":"2205.12628","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-large-pre-trained-language-models-leaking#ran","syntology_url":"https://syntology.ai/paper/2205.12628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12628"}},"official":{"repos":["jeffhj/lm_personalinfoleak"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-learning-with-boosted","slug":"contrastive-learning-with-boosted","title":"Contrastive Learning with Boosted Memorization","date":"2022-05-25","arxiv_id":"2205.12693","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrastive-learning-with-boosted#ran","syntology_url":"https://syntology.ai/paper/2205.12693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12693"}},"official":{"repos":["MediaBrain-SJTU/BCL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lops-learning-order-inspired-pseudo-label-1","slug":"lops-learning-order-inspired-pseudo-label-1","title":"LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification","date":"2022-05-25","arxiv_id":"2205.12528","repositories_listed":1,"syntology":null},{"url":"/paper/memorization-in-nlp-fine-tuning-methods","slug":"memorization-in-nlp-fine-tuning-methods","title":"Memorization in NLP Fine-tuning Methods","date":"2022-05-25","arxiv_id":"2205.12506","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-compressed-multilingual-machine","slug":"what-do-compressed-multilingual-machine","title":"What Do Compressed Multilingual Machine Translation Models Forget?","date":"2022-05-22","arxiv_id":"2205.10828","repositories_listed":1,"syntology":null},{"url":"/paper/towards-understanding-grokking-an-effective","slug":"towards-understanding-grokking-an-effective","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","date":"2022-05-20","arxiv_id":"2205.10343","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-understanding-grokking-an-effective#ran","syntology_url":"https://syntology.ai/paper/2205.10343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10343"}},"official":{"repos":["ejmichaud/grokking-squared"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/affective-medical-estimation-and-decision","slug":"affective-medical-estimation-and-decision","title":"Affective Medical Estimation and Decision Making via Visualized Learning and Deep Learning","date":"2022-05-09","arxiv_id":"2205.04599","repositories_listed":1,"syntology":null},{"url":"/paper/provably-confidential-language-modelling-1","slug":"provably-confidential-language-modelling-1","title":"Provably Confidential Language Modelling","date":"2022-05-04","arxiv_id":"2205.01863","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/provably-confidential-language-modelling-1#ran","syntology_url":"https://syntology.ai/paper/2205.01863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01863"}},"official":{"repos":["xuandongzhao/crt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/relation-extraction-as-open-book-examination","slug":"relation-extraction-as-open-book-examination","title":"Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning","date":"2022-05-04","arxiv_id":"2205.02355","repositories_listed":1,"syntology":null},{"url":"/paper/selc-self-ensemble-label-correction-improves","slug":"selc-self-ensemble-label-correction-improves","title":"SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels","date":"2022-05-02","arxiv_id":"2205.01156","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/selc-self-ensemble-label-correction-improves#ran","syntology_url":"https://syntology.ai/paper/2205.01156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01156"}},"official":{"repos":["maclll/selc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/polling-latent-opinions-a-method-for-1","slug":"polling-latent-opinions-a-method-for-1","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-04-15","arxiv_id":"2204.07483","repositories_listed":1,"syntology":null},{"url":"/paper/unicon-combating-label-noise-through-uniform","slug":"unicon-combating-label-noise-through-uniform","title":"UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning","date":"2022-03-28","arxiv_id":"2203.14542","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unicon-combating-label-noise-through-uniform#ran","syntology_url":"https://syntology.ai/paper/2203.14542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14542"}},"official":{"repos":["nazmul-karim170/unicon-noisy-label"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-memorization-in-nlp","slug":"an-empirical-study-of-memorization-in-nlp","title":"An Empirical Study of Memorization in NLP","date":"2022-03-23","arxiv_id":"2203.12171","repositories_listed":1,"syntology":null},{"url":"/paper/euler-state-networks","slug":"euler-state-networks","title":"Euler State Networks: Non-dissipative Reservoir Computing","date":"2022-03-17","arxiv_id":"2203.09382","repositories_listed":1,"syntology":null},{"url":"/paper/data-contamination-from-memorization-to-1","slug":"data-contamination-from-memorization-to-1","title":"Data Contamination: From Memorization to Exploitation","date":"2022-03-15","arxiv_id":"2203.08242","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/data-contamination-from-memorization-to-1#ran","syntology_url":"https://syntology.ai/paper/2203.08242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08242"}},"official":{"repos":["schwartz-lab-nlp/data_contamination"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/do-language-models-plagiarize","slug":"do-language-models-plagiarize","title":"Do Language Models Plagiarize?","date":"2022-03-15","arxiv_id":"2203.07618","repositories_listed":1,"syntology":null},{"url":"/paper/on-learning-contrastive-representations-for","slug":"on-learning-contrastive-representations-for","title":"On Learning Contrastive Representations for Learning with Noisy Labels","date":"2022-03-03","arxiv_id":"2203.01785","repositories_listed":1,"syntology":null},{"url":"/paper/membership-inference-attacks-and-defenses-in-1","slug":"membership-inference-attacks-and-defenses-in-1","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","date":"2022-02-07","arxiv_id":"2202.03335","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-through-memorization-nearest","slug":"reasoning-through-memorization-nearest","title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","date":"2022-01-14","arxiv_id":"2201.05575","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-twin-noisy-labels-for-visible","slug":"learning-with-twin-noisy-labels-for-visible","title":"Learning With Twin Noisy Labels for Visible-Infrared Person Re-Identification","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evidentiality-guided-generation-for-knowledge","slug":"evidentiality-guided-generation-for-knowledge","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","date":"2021-12-16","arxiv_id":"2112.08688","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/evidentiality-guided-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2112.08688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08688"}},"official":{"repos":["akariasai/evidentiality_qa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-with-noisy-correspondence-for-cross","slug":"learning-with-noisy-correspondence-for-cross","title":"Learning with Noisy Correspondence for Cross-modal Matching","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-memorization-in-probabilistic-deep-1","slug":"on-memorization-in-probabilistic-deep-1","title":"On Memorization in Probabilistic Deep Generative Models","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-refit-for-convex-learning","slug":"learning-to-refit-for-convex-learning","title":"ModelPred: A Framework for Predicting Trained Model from Training Data","date":"2021-11-24","arxiv_id":"2111.12545","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-membership-inference-attacks-against","slug":"enhanced-membership-inference-attacks-against","title":"Enhanced Membership Inference Attacks against Machine Learning Models","date":"2021-11-18","arxiv_id":"2111.09679","repositories_listed":1,"syntology":null},{"url":"/paper/demystifying-how-self-supervised-features-1","slug":"demystifying-how-self-supervised-features-1","title":"Mitigating Memorization of Noisy Labels via Regularization between Representations","date":"2021-10-18","arxiv_id":"2110.09022","repositories_listed":1,"syntology":null},{"url":"/paper/the-low-resource-double-bind-an-empirical","slug":"the-low-resource-double-bind-an-empirical","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","date":"2021-10-06","arxiv_id":"2110.03036","repositories_listed":1,"syntology":null},{"url":"/paper/excess-capacity-and-backdoor-poisoning","slug":"excess-capacity-and-backdoor-poisoning","title":"Excess Capacity and Backdoor Poisoning","date":"2021-09-02","arxiv_id":"2109.00685","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/excess-capacity-and-backdoor-poisoning#ran","syntology_url":"https://syntology.ai/paper/2109.00685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00685"}},"official":{"repos":["narenmanoj/mnist-adv-training"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/learning-transferable-parameters-for","slug":"learning-transferable-parameters-for","title":"Learning Transferable Parameters for Unsupervised Domain Adaptation","date":"2021-08-13","arxiv_id":"2108.06129","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-transferable-parameters-for#ran","syntology_url":"https://syntology.ai/paper/2108.06129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06129"}},"official":{"repos":["zhyhan/transpar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memorization-in-deep-neural-networks-does-the","slug":"memorization-in-deep-neural-networks-does-the","title":"Memorization in Deep Neural Networks: Does the Loss Function matter?","date":"2021-07-21","arxiv_id":"2107.09957","repositories_listed":1,"syntology":null},{"url":"/paper/affect-expression-behaviour-analysis-in-the-1","slug":"affect-expression-behaviour-analysis-in-the-1","title":"Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training","date":"2021-07-08","arxiv_id":"2107.05736","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-lstm-and-gru-networks-for","slug":"a-comparison-of-lstm-and-gru-networks-for","title":"A comparison of LSTM and GRU networks for learning symbolic sequences","date":"2021-07-05","arxiv_id":"2107.02248","repositories_listed":1,"syntology":null},{"url":"/paper/slope-and-generalization-properties-of-neural","slug":"slope-and-generalization-properties-of-neural","title":"Slope and generalization properties of neural networks","date":"2021-07-03","arxiv_id":"2107.01473","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-and-improving-early-stopping","slug":"understanding-and-improving-early-stopping","title":"Understanding and Improving Early Stopping for Learning with Noisy Labels","date":"2021-06-30","arxiv_id":"2106.15853","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-sample-selection-for-robust-learning","slug":"adaptive-sample-selection-for-robust-learning","title":"Adaptive Sample Selection for Robust Learning under Label Noise","date":"2021-06-29","arxiv_id":"2106.15292","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adaptive-sample-selection-for-robust-learning#ran","syntology_url":"https://syntology.ai/paper/2106.15292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.15292"}},"official":{"repos":["dbp1994/bare-wacv-2023"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-convolutional-memory-for-deep","slug":"graph-convolutional-memory-for-deep","title":"Graph Convolutional Memory using Topological Priors","date":"2021-06-27","arxiv_id":"2106.14117","repositories_listed":1,"syntology":null},{"url":"/paper/dat-training-deep-networks-robust-to-label","slug":"dat-training-deep-networks-robust-to-label","title":"DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/schema-guided-paradigm-for-zero-shot-dialog","slug":"schema-guided-paradigm-for-zero-shot-dialog","title":"Schema-Guided Paradigm for Zero-Shot Dialog","date":"2021-06-13","arxiv_id":"2106.07056","repositories_listed":1,"syntology":null},{"url":"/paper/muddling-label-regularization-deep-learning","slug":"muddling-label-regularization-deep-learning","title":"Muddling Label Regularization: Deep Learning for Tabular Datasets","date":"2021-06-08","arxiv_id":"2106.04462","repositories_listed":1,"syntology":null},{"url":"/paper/antipodes-of-label-differential-privacy-pate","slug":"antipodes-of-label-differential-privacy-pate","title":"Antipodes of Label Differential Privacy: PATE and ALIBI","date":"2021-06-07","arxiv_id":"2106.03408","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":5,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/antipodes-of-label-differential-privacy-pate#ran","syntology_url":"https://syntology.ai/paper/2106.03408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03408"}},"official":{"repos":["facebookresearch/label_dp_antipodes"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/on-memorization-in-probabilistic-deep","slug":"on-memorization-in-probabilistic-deep","title":"On Memorization in Probabilistic Deep Generative Models","date":"2021-06-06","arxiv_id":"2106.03216","repositories_listed":1,"syntology":null},{"url":"/paper/on-training-sample-memorization-lessons-from","slug":"on-training-sample-memorization-lessons-from","title":"On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition","date":"2021-06-06","arxiv_id":"2106.03062","repositories_listed":1,"syntology":null},{"url":"/paper/fundamental-tradeoffs-between-memorization","slug":"fundamental-tradeoffs-between-memorization","title":"Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes","date":"2021-06-04","arxiv_id":"2106.02630","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-generation-modes-for-abstractive","slug":"dissecting-generation-modes-for-abstractive","title":"Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution","date":"2021-06-03","arxiv_id":"2106.01518","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-memorization-in-adversarial","slug":"exploring-memorization-in-adversarial","title":"Exploring Memorization in Adversarial Training","date":"2021-06-03","arxiv_id":"2106.01606","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-memorization-in-adversarial#ran","syntology_url":"https://syntology.ai/paper/2106.01606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01606"}},"official":{"repos":["dongyp13/memorization-AT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-classification-of-attributes-in","slug":"automatic-classification-of-attributes-in","title":"Automatic Classification of Attributes in German Adjective-Noun Phrases","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-and-explaining-natural-language","slug":"evaluating-and-explaining-natural-language","title":"Evaluating and Explaining Natural Language Generation with GenX","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-novel-scene-compositions","slug":"learning-to-generate-novel-scene-compositions","title":"Learning to Generate Novel Scene Compositions from Single Images and Videos","date":"2021-05-12","arxiv_id":"2105.05847","repositories_listed":1,"syntology":null},{"url":"/paper/self-paced-resistance-learning-against","slug":"self-paced-resistance-learning-against","title":"Self-paced Resistance Learning against Overfitting on Noisy Labels","date":"2021-05-07","arxiv_id":"2105.03059","repositories_listed":1,"syntology":null},{"url":"/paper/broccoli-sprinkling-lightweight-vocabulary","slug":"broccoli-sprinkling-lightweight-vocabulary","title":"Broccoli: Sprinkling Lightweight Vocabulary Learning into Everyday Information Diets","date":"2021-04-16","arxiv_id":"2104.07941","repositories_listed":1,"syntology":null},{"url":"/paper/contrast-to-divide-self-supervised-pre-1","slug":"contrast-to-divide-self-supervised-pre-1","title":"Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels","date":"2021-03-25","arxiv_id":"2103.13646","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrast-to-divide-self-supervised-pre-1#ran","syntology_url":"https://syntology.ai/paper/2103.13646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13646"}},"official":{"repos":["ContrastToDivide/C2D"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/one-shot-gan-learning-to-generate-samples","slug":"one-shot-gan-learning-to-generate-samples","title":"Generating Novel Scene Compositions from Single Images and Videos","date":"2021-03-24","arxiv_id":"2103.13389","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-privacy-utility-trade-off-in","slug":"on-the-privacy-utility-trade-off-in","title":"On the privacy-utility trade-off in differentially private hierarchical text classification","date":"2021-03-04","arxiv_id":"2103.02895","repositories_listed":1,"syntology":null},{"url":"/paper/reconstruction-based-membership-inference","slug":"reconstruction-based-membership-inference","title":"Membership Inference Attacks are Easier on Difficult Problems","date":"2021-02-15","arxiv_id":"2102.07762","repositories_listed":1,"syntology":null},{"url":"/paper/driving-style-representation-in-convolutional","slug":"driving-style-representation-in-convolutional","title":"Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification","date":"2021-02-11","arxiv_id":"2102.05843","repositories_listed":1,"syntology":null},{"url":"/paper/robust-generalization-and-safe-query","slug":"robust-generalization-and-safe-query","title":"Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank","date":"2021-02-11","arxiv_id":"2102.05990","repositories_listed":1,"syntology":null},{"url":"/paper/memorization-vs-generalization-quantifying","slug":"memorization-vs-generalization-quantifying","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","date":"2021-02-03","arxiv_id":"2102.01818","repositories_listed":1,"syntology":null},{"url":"/paper/meta-regularization-by-enforcing-mutual","slug":"meta-regularization-by-enforcing-mutual","title":"Meta-Regularization by Enforcing Mutual-Exclusiveness","date":"2021-01-24","arxiv_id":"2101.09819","repositories_listed":1,"syntology":null},{"url":"/paper/the-truth-is-out-there-investigating","slug":"the-truth-is-out-there-investigating","title":"Investigating Memorization of Conspiracy Theories in Text Generation","date":"2021-01-02","arxiv_id":"2101.00379","repositories_listed":1,"syntology":null},{"url":"/paper/grounding-consistency-distilling-spatial","slug":"grounding-consistency-distilling-spatial","title":"Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-do-your-biomedical-named-entity-models","slug":"how-do-your-biomedical-named-entity-models","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","date":"2021-01-01","arxiv_id":"2101.00160","repositories_listed":1,"syntology":null},{"url":"/paper/introducing-orthogonal-constraint-in","slug":"introducing-orthogonal-constraint-in","title":"Introducing Orthogonal Constraint in Structural Probes","date":"2020-12-30","arxiv_id":"2012.15228","repositories_listed":1,"syntology":null},{"url":"/paper/when-is-memorization-of-irrelevant-training","slug":"when-is-memorization-of-irrelevant-training","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","date":"2020-12-11","arxiv_id":"2012.06421","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-is-memorization-of-irrelevant-training#ran","syntology_url":"https://syntology.ai/paper/2012.06421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.06421"}},"official":{"repos":["gavinrbrown1/training-data-memorization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-objective-interpolation-training-for","slug":"multi-objective-interpolation-training-for","title":"Multi-Objective Interpolation Training for Robustness to Label Noise","date":"2020-12-08","arxiv_id":"2012.04462","repositories_listed":1,"syntology":null},{"url":"/paper/artificial-neural-variability-for-deep","slug":"artificial-neural-variability-for-deep","title":"Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting","date":"2020-11-12","arxiv_id":"2011.06220","repositories_listed":1,"syntology":null},{"url":"/paper/short-term-memory-optimization-in-recurrent","slug":"short-term-memory-optimization-in-recurrent","title":"Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization","date":"2020-11-05","arxiv_id":"2011.02886","repositories_listed":1,"syntology":null},{"url":"/paper/toward-a-generalization-metric-for-deep","slug":"toward-a-generalization-metric-for-deep","title":"Toward a Generalization Metric for Deep Generative Models","date":"2020-11-02","arxiv_id":"2011.00754","repositories_listed":1,"syntology":null}],"record_sha256":"7f051cd91ed5d1518279f4c203c4a687a1b0f53014e5b3d8f5ef4f7120656f1a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}