{"work":{"id":"0a3595ca-57f9-43f8-8e2f-aface7154b99","openalex_id":"https://openalex.org/W2112796928","doi":"10.1109/5.726791","arxiv_id":null,"raw_key":null,"title":"Gradient-based learning applied to document recognition,","authors":[{"given":"Y.","family":"Lecun","sequence":"first","affiliation":[]},{"given":"L.","family":"Bottou","sequence":"additional","affiliation":[]},{"given":"Y.","family":"Bengio","sequence":"additional","affiliation":[]},{"given":"P.","family":"Haffner","sequence":"additional","affiliation":[]}],"authors_text":"Y","year":1998,"venue":"Proceedings of the IEEE","abstract":null,"external_url":"https://doi.org/10.1109/5.726791","cited_by_count":44725,"metadata_source":"doi_reference","metadata_fetched_at":"2026-05-25T19:31:09.750477+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T17:28:40.230237+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Gradient-based learning applied to document recognition","render_title":"Gradient-based learning applied to document recognition"},"hub":{"state":{"work_id":"0a3595ca-57f9-43f8-8e2f-aface7154b99","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":56,"external_cited_by_count":44725,"distinct_field_count":22,"first_pith_cited_at":"2019-06-20T20:30:39+00:00","last_pith_cited_at":"2026-05-21T23:08:23+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-12T06:49:16.476847+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":7},{"context_role":"dataset","n":4},{"context_role":"method","n":3}],"polarity_counts":[{"context_polarity":"background","n":6},{"context_polarity":"use_dataset","n":4},{"context_polarity":"use_method","n":3},{"context_polarity":"support","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324","claims":[],"why_cited":"Pith tracks Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324 because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T03:05:55.469581+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"03454243-d801-4ab5-b7f1-efc27df36195","orcid":null,"display_name":"Y. Lecun"},{"id":"969017b5-d63b-4a90-958e-825a93e40fed","orcid":null,"display_name":"L. Bottou"},{"id":"8bc9ea04-e23c-44ee-8787-fc08b0a8df57","orcid":null,"display_name":"Y. Bengio"},{"id":"a7664e64-b811-4528-84be-cf1247044d19","orcid":null,"display_name":"P. Haffner"}]},"error":null,"updated_at":"2026-05-14T03:05:42.351921+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T02:55:31.091766+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","work_id":"6714d44f-1b5e-4141-9450-ea09a7e724b0","shared_citers":6},{"title":"Long short-term memory","work_id":"c3b0bfa7-6764-45f1-a40d-45baaee9d22c","shared_citers":6},{"title":"URLhttp://dx.doi.org/10.1109/CVPR.2016.90","work_id":"b353bda2-591d-479a-9c8b-22dfcba12431","shared_citers":5},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":3},{"title":"Attention Is All You Need","work_id":"baafb5a2-5272-43bc-932f-09fa9ffe5316","shared_citers":3},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":3},{"title":"Deep learning","work_id":"f959cefa-9092-49df-9fb5-a4e6654500f1","shared_citers":3},{"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","shared_citers":3},{"title":"URL https://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":3},{"title":"1987 , issue_date =","work_id":"533fbb53-38a5-4436-b2d9-6ed9f7efb0dd","shared_citers":2},{"title":"2016, Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, https://arxiv.org/abs/1506.02142","work_id":"c73cadf6-1d84-47d1-8731-c654db78aee6","shared_citers":2},{"title":"2024, MNRAS, 531, 4990, doi: 10.1093/mnras/stae1450","work_id":"d21263bd-cddd-4563-a709-4ae3389a824b","shared_citers":2},{"title":"arXiv preprint arXiv:2307.08698 , year=","work_id":"6ee263fd-c952-48d9-aae7-5dc66af5ffbd","shared_citers":2},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":2},{"title":"E., et al","work_id":"1a44c2d3-9a48-46f3-924b-d2fa43b6729a","shared_citers":2},{"title":"Girshick, and Jian Sun","work_id":"0d7ba565-3e2a-4dff-aa24-13faf1f6e69e","shared_citers":2},{"title":"Hastie, R","work_id":"db5dbf68-75ca-4123-ac22-d1b5b056831d","shared_citers":2},{"title":"Imagenet: A large-scale hierarchical image database","work_id":"effdb28b-742e-4840-b3ca-d89502a6cd4d","shared_citers":2},{"title":"Inductive representation learning on large graphs","work_id":"a84007af-8130-4a77-b631-738c9af563fd","shared_citers":2},{"title":"Jiarui Zhang, Ollie Liu, Tianyu Yu, Jinyi Hu, and Willie Neiswanger","work_id":"eb18b0c2-9ed0-4254-b208-425469f09e64","shared_citers":2},{"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","shared_citers":2},{"title":"Matus Telgarsky","work_id":"1496bd95-cdd3-4b5c-a899-57e2470c31d9","shared_citers":2},{"title":"Neural Computation , author =","work_id":"f12adc07-3a93-46d5-a446-3adbf2ab035c","shared_citers":2},{"title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","work_id":"c30b6d2c-7bb4-4ab0-8ef8-2015313610a9","shared_citers":2}],"time_series":[{"n":30,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T02:55:22.377271+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T02:55:35.497130+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324","claims":[],"why_cited":"Pith tracks Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324 because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T02:55:22.296837+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324","claims":[],"why_cited":"Pith tracks Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324 because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T02:55:22.343933+00:00"}},"summary":{"title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324","claims":[],"why_cited":"Pith tracks Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324 because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","work_id":"6714d44f-1b5e-4141-9450-ea09a7e724b0","shared_citers":6},{"title":"Long short-term memory","work_id":"c3b0bfa7-6764-45f1-a40d-45baaee9d22c","shared_citers":6},{"title":"URLhttp://dx.doi.org/10.1109/CVPR.2016.90","work_id":"b353bda2-591d-479a-9c8b-22dfcba12431","shared_citers":5},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":3},{"title":"Attention Is All You Need","work_id":"baafb5a2-5272-43bc-932f-09fa9ffe5316","shared_citers":3},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":3},{"title":"Deep learning","work_id":"f959cefa-9092-49df-9fb5-a4e6654500f1","shared_citers":3},{"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","shared_citers":3},{"title":"URL https://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":3},{"title":"1987 , issue_date =","work_id":"533fbb53-38a5-4436-b2d9-6ed9f7efb0dd","shared_citers":2},{"title":"2016, Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, https://arxiv.org/abs/1506.02142","work_id":"c73cadf6-1d84-47d1-8731-c654db78aee6","shared_citers":2},{"title":"2024, MNRAS, 531, 4990, doi: 10.1093/mnras/stae1450","work_id":"d21263bd-cddd-4563-a709-4ae3389a824b","shared_citers":2},{"title":"arXiv preprint arXiv:2307.08698 , year=","work_id":"6ee263fd-c952-48d9-aae7-5dc66af5ffbd","shared_citers":2},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":2},{"title":"E., et al","work_id":"1a44c2d3-9a48-46f3-924b-d2fa43b6729a","shared_citers":2},{"title":"Girshick, and Jian Sun","work_id":"0d7ba565-3e2a-4dff-aa24-13faf1f6e69e","shared_citers":2},{"title":"Hastie, R","work_id":"db5dbf68-75ca-4123-ac22-d1b5b056831d","shared_citers":2},{"title":"Imagenet: A large-scale hierarchical image database","work_id":"effdb28b-742e-4840-b3ca-d89502a6cd4d","shared_citers":2},{"title":"Inductive representation learning on large graphs","work_id":"a84007af-8130-4a77-b631-738c9af563fd","shared_citers":2},{"title":"Jiarui Zhang, Ollie Liu, Tianyu Yu, Jinyi Hu, and Willie Neiswanger","work_id":"eb18b0c2-9ed0-4254-b208-425469f09e64","shared_citers":2},{"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","shared_citers":2},{"title":"Matus Telgarsky","work_id":"1496bd95-cdd3-4b5c-a899-57e2470c31d9","shared_citers":2},{"title":"Neural Computation , author =","work_id":"f12adc07-3a93-46d5-a446-3adbf2ab035c","shared_citers":2},{"title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","work_id":"c30b6d2c-7bb4-4ab0-8ef8-2015313610a9","shared_citers":2}],"time_series":[{"n":30,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"969017b5-d63b-4a90-958e-825a93e40fed","orcid":null,"display_name":"L. Bottou","source":"manual","import_confidence":0.72},{"id":"a7664e64-b811-4528-84be-cf1247044d19","orcid":null,"display_name":"P. Haffner","source":"manual","import_confidence":0.72},{"id":"8bc9ea04-e23c-44ee-8787-fc08b0a8df57","orcid":null,"display_name":"Y. Bengio","source":"manual","import_confidence":0.72},{"id":"03454243-d801-4ab5-b7f1-efc27df36195","orcid":null,"display_name":"Y. Lecun","source":"manual","import_confidence":0.72}]}}