{"work":{"id":"95a362b1-dfc7-4356-b573-94d20a6c7a42","openalex_id":"https://openalex.org/W4229933927","doi":"10.1073/pnas","arxiv_id":null,"raw_key":null,"title":"Shestyuk, Piotr J","authors":null,"authors_text":"R","year":2018,"venue":null,"abstract":null,"external_url":"https://doi.org/10.1073/pnas","cited_by_count":4193,"metadata_source":"openalex","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T17:53:53.007824+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"Overcoming catastrophic forgetting in neural networks","render_title":"Overcoming catastrophic forgetting in neural networks"},"hub":{"state":{"work_id":"95a362b1-dfc7-4356-b573-94d20a6c7a42","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":110,"external_cited_by_count":4193,"distinct_field_count":50,"first_pith_cited_at":"2024-01-12T02:41:06+00:00","last_pith_cited_at":"2026-07-09T09:45:41+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":"2026-08-24T02:39:25.786842+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":26},{"context_role":"method","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":22},{"context_polarity":"support","n":2},{"context_polarity":"unclear","n":2},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Overcoming catastrophic forgetting in neural networks","claims":[{"claim_text":"Section 2 documents the empirical violation of the com- positional assumption. Section 3 maps Holland's properties onto observable ecosystem dynamics and distinguishes AI-native ecosystems from microservice architectures, open-source contribu- tor networks, and consensus systems on theoretically precise grounds. Section 4 adapts Hoel et al. 's causal emergence framework [14] to software ecosystems, specifying state variables, coarse- graining operations, and a measurement protocol. Section 5 der","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"\"Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity\". In:Advances in Neural Information Processing Systems. V ol. 21. Curran Associates, Inc., 2008. [20] R. S. Zemelet al.\"Probabilistic Interpretation of Population Codes\".Neural Computation10.2 (Feb. 1998), pp. 403-430.DOI:10.1162/089976698300017818. [21] S. Nirenberg and P. E. Latham. \"Decoding neuronal spike trains: How important are correlations?\"Pro- ceedings of the National Academy of Sc","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Data-driven discovery of governing equations has emerged as a powerful paradigm for uncovering the underlying mechanisms of complex dynamical systems, particularly when first-principles derivations are intractable [ 1, 2, 3, 4, 5, 6, 7]. However, robustly identifying governing equations that contain small-coefficient terms in multiscale systems remains a critical challenge [ 8]. Despite their small magnitudes, such terms cannot be neglected, as they may become locally dominant in specific spatiotemp","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"accurate than the most similar published smoke classifier, which obtains an IoU and AUC of 0.15 and 0.61, respectively, on a 2015 bushfire in Australia. 1 Introduction Wildfires are an increasing threat to life, property, and the environment, with average fire size, frequency, and extent rising sharply across the western United States in recent decades [1, 37]. Increases in temperature and vapor pressure deficit have enhanced fuel aridity, roughly doubling the cumulative western US forest area b","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"1016/j. plrev.2023.12.006 arXiv:2412.15711 [q-bio.NC] [15] Warren, D.E., Power, J.D., Bruss, J., Denburg, N.L., Waldron, E.J., Sun, H., Petersen, S.E., Tranel, D.: Network measures predict neuropsychological outcome after brain injury. Proceedings of the National Academy of Science 111(39), 14247-14252 (2014) https://doi.org/10.1073/pnas.1322173111 [16] Giusti, C., Pastalkova, E., Curto, C., Itskov, V.: Clique topology reveals intrin- sic geometric structure in neural correlations. Proceedings o","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the key ingredients required to construct them. We finally introduce the specific case of photonic synthetic matter. 1.1 Regular atom arrays: from atomic monolayers to synthetic materials One of the major achievements in modern condensed matter physics was the discovery that genuine two-dimensional (2D) crystals can be isolated from bulk materials [1,2]. Graphene, obtained by exfoliation from graphite, was the first such material, and its discovery has inspired a vast body of research [3,4]. Sin","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Overcoming catastrophic forgetting in neural networks because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (25 contexts).","role_counts":[{"n":25,"context_role":"background"},{"n":2,"context_role":"method"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-06-30T00:49:23.662289+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"67728fcd-3487-40d8-b1aa-df6f631737ef","orcid":null,"display_name":"Fabrizio Gilardi"},{"id":"ecab89a4-c9f6-479e-8be5-96ca3dbc5c34","orcid":null,"display_name":"Meysam Alizadeh"},{"id":"a3bec60a-0895-42a3-b416-ee4573b4a635","orcid":null,"display_name":"and Maël Kubli"}]},"error":null,"updated_at":"2026-06-30T00:49:26.048528+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T16:32:48.508696+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"115.205901","work_id":"4deaf489-c81b-4322-bb0a-41188b0ad4db","shared_citers":2},{"title":"Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou","work_id":"cbcc5fe8-a571-4a91-8ab8-1c0164648749","shared_citers":2},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":2},{"title":"doi: 10.1063/5.0224297","work_id":"6cc71f3a-1afb-4123-b2c5-896bd4cd19ba","shared_citers":2},{"title":"Ex- ploiting short-term memory in soft body dynamics as a computational resource","work_id":"44f5f48d-4a6a-47e0-8fd0-dccfcdd050c6","shared_citers":2},{"title":"Hersbach, B","work_id":"e8d7a404-9f91-4f76-95f8-6949c6500cfa","shared_citers":2},{"title":"Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl","work_id":"666d4dea-669b-423b-9bd4-e14eee78fcb4","shared_citers":2},{"title":"Perdew, K","work_id":"6c507f87-3543-449a-b6ee-8de94abe223e","shared_citers":2},{"title":"Raissi, P","work_id":"16a1de8a-4145-44c7-a263-8f01bfe9ca2e","shared_citers":2},{"title":"Recent advances in physical reservoir computing: A review.Neural Networks, 115:100–123","work_id":"8bc1789e-14db-41d8-b837-82ef18b277e4","shared_citers":2},{"title":"Resolving uncertainty on the fly: modeling adaptive driving behavior as active inference.Frontiers in Neurorobotics 2024; 18","work_id":"9fff405f-7ebe-4e38-a4a8-daf267549270","shared_citers":2},{"title":"Shalizi, and M","work_id":"46e2680d-6660-41c1-9860-1cdcd40de375","shared_citers":2},{"title":"URL https://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":2},{"title":"When your training conflicts with the fact-check: the fact-check ALWAYS takes precedence","work_id":"9e7756a3-7305-41a3-aec6-afb462723207","shared_citers":2},{"title":"Zhang, Jonathan Bragg, Andrew Head, Kyle Lo, Doug Downey, and Daniel S","work_id":"a88fc655-55d0-4dfc-82af-f7e1abf6a05f","shared_citers":2},{"title":"1038/s41597-025-04692-8 Háden,G.P.,Bouwer,F.L.,Honing,H.,&Winkler,I.(2024)","work_id":"9c02ee38-353b-4a12-ad9c-e1b666306a99","shared_citers":1},{"title":"10x Genomics Datasets","work_id":"50821e49-cc17-46f4-b276-197e303c3ead","shared_citers":1},{"title":"1126/science.194.4271.12355 YusukeKobayashiandBingkaiLin.2025","work_id":"d8845794-7e8b-4188-ba49-eaf8b103e870","shared_citers":1},{"title":"11 Preprint","work_id":"cb34130b-203a-477e-bf34-8ca8591f3df6","shared_citers":1},{"title":"1 WieslawKubiak.2004","work_id":"7c534a66-b2f9-4b65-bdf2-5cb9487bed4e","shared_citers":1},{"title":"2003.06531.x","work_id":"4d864081-e175-40a4-96bb-746f97036f9d","shared_citers":1},{"title":"2007.Human-machine reconfigurations: Plans and situated actions","work_id":"f1db383c-bf64-4239-8624-e81a8d086b16","shared_citers":1},{"title":"2013.Measuring what matters most: Choice- based assessments for the digital age","work_id":"bdc13eb1-df9f-4eac-86ee-a5ad6b50acdc","shared_citers":1},{"title":"2015.00370","work_id":"0f210887-2d12-4f26-a0e0-0f320de68dfa","shared_citers":1}],"time_series":[{"n":42,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T16:32:35.265492+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":"2026-05-14T16:32:44.163149+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Overcoming catastrophic forgetting in neural networks","claims":[{"claim_text":"Section 2 documents the empirical violation of the com- positional assumption. Section 3 maps Holland's properties onto observable ecosystem dynamics and distinguishes AI-native ecosystems from microservice architectures, open-source contribu- tor networks, and consensus systems on theoretically precise grounds. Section 4 adapts Hoel et al. 's causal emergence framework [14] to software ecosystems, specifying state variables, coarse- graining operations, and a measurement protocol. Section 5 der","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"\"Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity\". In:Advances in Neural Information Processing Systems. V ol. 21. Curran Associates, Inc., 2008. [20] R. S. Zemelet al.\"Probabilistic Interpretation of Population Codes\".Neural Computation10.2 (Feb. 1998), pp. 403-430.DOI:10.1162/089976698300017818. [21] S. Nirenberg and P. E. Latham. \"Decoding neuronal spike trains: How important are correlations?\"Pro- ceedings of the National Academy of Sc","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Data-driven discovery of governing equations has emerged as a powerful paradigm for uncovering the underlying mechanisms of complex dynamical systems, particularly when first-principles derivations are intractable [ 1, 2, 3, 4, 5, 6, 7]. However, robustly identifying governing equations that contain small-coefficient terms in multiscale systems remains a critical challenge [ 8]. Despite their small magnitudes, such terms cannot be neglected, as they may become locally dominant in specific spatiotemp","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"accurate than the most similar published smoke classifier, which obtains an IoU and AUC of 0.15 and 0.61, respectively, on a 2015 bushfire in Australia. 1 Introduction Wildfires are an increasing threat to life, property, and the environment, with average fire size, frequency, and extent rising sharply across the western United States in recent decades [1, 37]. Increases in temperature and vapor pressure deficit have enhanced fuel aridity, roughly doubling the cumulative western US forest area b","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"1016/j. plrev.2023.12.006 arXiv:2412.15711 [q-bio.NC] [15] Warren, D.E., Power, J.D., Bruss, J., Denburg, N.L., Waldron, E.J., Sun, H., Petersen, S.E., Tranel, D.: Network measures predict neuropsychological outcome after brain injury. Proceedings of the National Academy of Science 111(39), 14247-14252 (2014) https://doi.org/10.1073/pnas.1322173111 [16] Giusti, C., Pastalkova, E., Curto, C., Itskov, V.: Clique topology reveals intrin- sic geometric structure in neural correlations. Proceedings o","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the key ingredients required to construct them. We finally introduce the specific case of photonic synthetic matter. 1.1 Regular atom arrays: from atomic monolayers to synthetic materials One of the major achievements in modern condensed matter physics was the discovery that genuine two-dimensional (2D) crystals can be isolated from bulk materials [1,2]. Graphene, obtained by exfoliation from graphite, was the first such material, and its discovery has inspired a vast body of research [3,4]. Sin","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Overcoming catastrophic forgetting in neural networks because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (25 contexts).","role_counts":[{"n":25,"context_role":"background"},{"n":2,"context_role":"method"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-06-30T00:49:26.051006+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences2019; : 201820676DOI:10.1073/pnas","claims":[],"why_cited":"Pith tracks Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences2019; : 201820676DOI:10.1073/pnas because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T16:32:39.177627+00:00"}},"summary":{"title":"Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences2019; : 201820676DOI:10.1073/pnas","claims":[],"why_cited":"Pith tracks Social behavior for autonomous vehicles.Proceedings of the National Academy of Sciences2019; : 201820676DOI:10.1073/pnas because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"115.205901","work_id":"4deaf489-c81b-4322-bb0a-41188b0ad4db","shared_citers":2},{"title":"Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou","work_id":"cbcc5fe8-a571-4a91-8ab8-1c0164648749","shared_citers":2},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":2},{"title":"doi: 10.1063/5.0224297","work_id":"6cc71f3a-1afb-4123-b2c5-896bd4cd19ba","shared_citers":2},{"title":"Ex- ploiting short-term memory in soft body dynamics as a computational resource","work_id":"44f5f48d-4a6a-47e0-8fd0-dccfcdd050c6","shared_citers":2},{"title":"Hersbach, B","work_id":"e8d7a404-9f91-4f76-95f8-6949c6500cfa","shared_citers":2},{"title":"Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl","work_id":"666d4dea-669b-423b-9bd4-e14eee78fcb4","shared_citers":2},{"title":"Perdew, K","work_id":"6c507f87-3543-449a-b6ee-8de94abe223e","shared_citers":2},{"title":"Raissi, P","work_id":"16a1de8a-4145-44c7-a263-8f01bfe9ca2e","shared_citers":2},{"title":"Recent advances in physical reservoir computing: A review.Neural Networks, 115:100–123","work_id":"8bc1789e-14db-41d8-b837-82ef18b277e4","shared_citers":2},{"title":"Resolving uncertainty on the fly: modeling adaptive driving behavior as active inference.Frontiers in Neurorobotics 2024; 18","work_id":"9fff405f-7ebe-4e38-a4a8-daf267549270","shared_citers":2},{"title":"Shalizi, and M","work_id":"46e2680d-6660-41c1-9860-1cdcd40de375","shared_citers":2},{"title":"URL https://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":2},{"title":"When your training conflicts with the fact-check: the fact-check ALWAYS takes precedence","work_id":"9e7756a3-7305-41a3-aec6-afb462723207","shared_citers":2},{"title":"Zhang, Jonathan Bragg, Andrew Head, Kyle Lo, Doug Downey, and Daniel S","work_id":"a88fc655-55d0-4dfc-82af-f7e1abf6a05f","shared_citers":2},{"title":"1038/s41597-025-04692-8 Háden,G.P.,Bouwer,F.L.,Honing,H.,&Winkler,I.(2024)","work_id":"9c02ee38-353b-4a12-ad9c-e1b666306a99","shared_citers":1},{"title":"10x Genomics Datasets","work_id":"50821e49-cc17-46f4-b276-197e303c3ead","shared_citers":1},{"title":"1126/science.194.4271.12355 YusukeKobayashiandBingkaiLin.2025","work_id":"d8845794-7e8b-4188-ba49-eaf8b103e870","shared_citers":1},{"title":"11 Preprint","work_id":"cb34130b-203a-477e-bf34-8ca8591f3df6","shared_citers":1},{"title":"1 WieslawKubiak.2004","work_id":"7c534a66-b2f9-4b65-bdf2-5cb9487bed4e","shared_citers":1},{"title":"2003.06531.x","work_id":"4d864081-e175-40a4-96bb-746f97036f9d","shared_citers":1},{"title":"2007.Human-machine reconfigurations: Plans and situated actions","work_id":"f1db383c-bf64-4239-8624-e81a8d086b16","shared_citers":1},{"title":"2013.Measuring what matters most: Choice- based assessments for the digital age","work_id":"bdc13eb1-df9f-4eac-86ee-a5ad6b50acdc","shared_citers":1},{"title":"2015.00370","work_id":"0f210887-2d12-4f26-a0e0-0f320de68dfa","shared_citers":1}],"time_series":[{"n":42,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"a3bec60a-0895-42a3-b416-ee4573b4a635","orcid":null,"display_name":"and Maël Kubli","source":"manual","import_confidence":0.72},{"id":"67728fcd-3487-40d8-b1aa-df6f631737ef","orcid":null,"display_name":"Fabrizio Gilardi","source":"manual","import_confidence":0.72},{"id":"ecab89a4-c9f6-479e-8be5-96ca3dbc5c34","orcid":null,"display_name":"Meysam Alizadeh","source":"manual","import_confidence":0.72}]}}