{"as_of":"2026-08-16T05:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:000bd945771c8984d063b52825e7520fc2671ba85f2f6d8de56054e9fc968728","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:35:24.500978Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.02984/citation-record","integrity":"/paper/1908.02984/integrity","json":"/paper/1908.02984/citation-record.json","paper":"/paper/1908.02984"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.461546Z","title":"Available at tiny-imagenet.herokuapp.com","venue":null,"work_id":"0632d991-6f2e-4d69-90be-642dd725eaa2","year":null},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.282117Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:9029e362254b33d941601662a2bd117259fd90a09c11fc6c9af09c92383bbb2b","observation_id":"0a3630f3-40fb-4711-9f3e-3fb0b5a05b30","resolution":{"observed_at":"2026-08-14T14:35:25.467057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.443202Z","title":"Memory aware synapses: Learning what (not) to forget","venue":null,"work_id":"42d74edd-b907-4e32-b542-d929b2c41d58","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.291321Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:b25c8b64b3fd492864e6521b773886517eae6db766cd068836d4f04680d399cd","observation_id":"6f0fd379-de7d-4b3d-8e4a-86e07554dc24","resolution":{"observed_at":"2026-08-14T14:35:25.448671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.419031Z","title":"Expert gate: Lifelong learning with a network of experts","venue":null,"work_id":"b8d14446-1cb0-41c4-b721-1cb35d3ae66f","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.300993Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:0e1971462889ea9d97756bc4f9d6bf9513c0c5ff23d8e5874aa3b16112bed149","observation_id":"d2d72dac-84ad-4eec-aed9-31a6340c5776","resolution":{"observed_at":"2026-08-14T14:35:25.426401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.309450Z","title":"Weight uncertainty in neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.309450Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:83fd9331070c263264704f44d1d4351910b521707993005a186dfdf4b9d2e4ee","observation_id":"09b48e4a-6f89-43c6-86b1-9692bdf3b326","resolution":{"observed_at":"2026-08-14T14:35:24.309450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.383134Z","title":"Streaming varia- tional bayes","venue":null,"work_id":"ca7d4139-d117-41f3-b28e-51235c69d43d","year":2013},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.318241Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:cda9ec6c114fb48e6bd1c2d53cf01f233f2747f7d0faca2d4e24b65dd0eb7d00","observation_id":"b1361d27-13bc-4393-9c85-0e71f4885079","resolution":{"observed_at":"2026-08-14T14:35:25.389992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.361748Z","title":"Riemannian walk for incremen- tal learning: Understanding forgetting and intransigence","venue":null,"work_id":"67901957-2789-4bfe-b86f-c908bee2ad7d","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.325566Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:81c9815da09ffa34301064810f3613c863db25cfc910c5aded55cb4340931287","observation_id":"9611cd44-bd8e-4651-ba1b-7978fd8b1c0d","resolution":{"observed_at":"2026-08-14T14:35:25.368077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.08734","last_updated":"2017-01-30T18:06:07Z","snapshot_observed_at":"2026-08-14T21:18:51.601049Z","submitted_at":"2017-01-30T18:06:07Z","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.08734","snapshot_observed_at":"2026-08-14T14:35:24.331804Z","title":"Pathnet: Evolution channels gradient descent in super neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.331804Z"},"links":{"cited_paper":"/paper/1701.08734","citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:fccb0ba0a3ebb45c041e7f011c58eb1e65a08fa70b7547a7938496fa321668e6","observation_id":"2b97c140-a857-4008-a07b-598e10406fe9","resolution":{"observed_at":"2026-08-14T14:35:24.331804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.343926Z","title":"Catastrophic forgetting in connectionist networks","venue":null,"work_id":"58aa9fef-b66a-496a-8778-08e7ae089bfd","year":1999},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.337878Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:76333dee046aa33cd6fa0db6011584bb9a78f7cdd0e0086f8a31e239b5f143d9","observation_id":"dc28c27a-7592-4723-a4d5-0323139bb587","resolution":{"observed_at":"2026-08-14T14:35:25.349503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.323723Z","title":"Online variational bayesian learning","venue":null,"work_id":"5f12c729-5b31-40fa-acbf-8cb9f4b6461e","year":2000},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.343097Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:daf9a77db613aa4a2e76e9badb0273821483d6859de19878b242bc5012ca4110","observation_id":"55982127-1ff0-42b0-b77b-ea7cc8c6ef3e","resolution":{"observed_at":"2026-08-14T14:35:25.331773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6211","last_updated":"2015-03-04T01:43:31Z","snapshot_observed_at":"2026-08-14T23:50:42.566579Z","submitted_at":"2013-12-21T06:31:41Z","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6211","snapshot_observed_at":"2026-08-14T14:35:24.347856Z","title":"An empirical investigation of catas- trophic forgetting in gradient-based neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.347856Z"},"links":{"cited_paper":"/paper/1312.6211","citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:af78de9ceb98136ebb107d9a7e33566bcb9ab9c0969053d2999edd47ae8754d6","observation_id":"50cd277a-51d4-4fb8-af32-fddbdea51f3e","resolution":{"observed_at":"2026-08-14T14:35:24.347856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.354024Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.354024Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:6a0531d621bc906162ce2e2c3c07433b216e12f9861a7ffe54e36fc9da4819b7","observation_id":"a36b2b8c-8fea-48ba-a4ff-49471b518632","resolution":{"observed_at":"2026-08-14T14:35:24.354024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.276957Z","title":"Overcoming catastrophic inter- ference using conceptor-aided backpropagation","venue":null,"work_id":"1b6fa332-b7ec-4156-ace7-4792d0297a2d","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.359042Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:267248062058c562ebceeffb880209e73186873b0e4943382a5d5810dce5992b","observation_id":"3fd5e4a1-43d1-4344-9f17-225661c61a73","resolution":{"observed_at":"2026-08-14T14:35:25.288439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.258774Z","title":"Over- coming catastrophic forgetting via model adaptation","venue":null,"work_id":"661caf05-bade-424c-90b5-d21cd154806d","year":2019},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.364014Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:1c81641486d946a6154584f588b079f349f230dc4d2190ca2b1c8d18755f1e7b","observation_id":"4a147a2f-eb60-4bab-83da-f71c6da806b8","resolution":{"observed_at":"2026-08-14T14:35:25.264267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.237502Z","title":"Less-forgetful learning for domain expansion in deep neu- ral networks","venue":null,"work_id":"142bcff8-f8e3-4620-9592-d8f2981fa2b1","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.368632Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:d063830bedc65f62783139e9436c51bf56dcb0413b22b8bb6beeb461cfb91572","observation_id":"27e6bf48-4176-40ca-8984-9212967451d5","resolution":{"observed_at":"2026-08-14T14:35:25.246405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.220177Z","title":"Fearnet: Brain- inspired model for incremental learning","venue":null,"work_id":"76fda7ff-4ae9-432e-b90d-079e4ded7d03","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.373918Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:4aeb2151ad35052297e1023513ee226c20af325a5151741838c358ea216be8d3","observation_id":"561fef74-0e39-4014-b4ae-0fe38eb9112a","resolution":{"observed_at":"2026-08-14T14:35:25.225569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.185082Z","title":"Stochastic estimation of the maximum of a regression function","venue":null,"work_id":"5aa8c1e0-8342-4ebc-bb8e-894ed04983e1","year":1952},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.379269Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:7b712de5c8b2d5b42829e4d5fcdc014d6fb778270ac2c4c21d3d914872176de3","observation_id":"def231fb-9c8d-416b-bc6a-7cd341ed8c1f","resolution":{"observed_at":"2026-08-14T14:35:25.194485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.165733Z","title":"Overcoming catastrophic forgetting in neu- ral networks","venue":null,"work_id":"db520723-55b5-46a3-8f7a-1ff57ed6a795","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.384745Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:df620f1f408cada3af7dd523d3a16fdfb7ec27f4b112cfb239587cf69aa86548","observation_id":"daf72c28-6100-45f1-a079-5763530e61b0","resolution":{"observed_at":"2026-08-14T14:35:25.171366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.145017Z","title":"The CIFAR-10 and CIFAR-100 datasets","venue":null,"work_id":"ee12e062-ca80-4aa3-9990-eab9f0628634","year":null},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.389787Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:d588f6c4b65d1fe6b0320c04d45cdbd5a83815472168d645cb2efb65c0b43295","observation_id":"d2d6a6a1-9744-430d-b4bb-514e76230dfb","resolution":{"observed_at":"2026-08-14T14:35:25.153068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.121800Z","title":null,"venue":null,"work_id":"3c3f3bcd-d35e-4456-8f47-71f582510608","year":null},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.395952Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:8c789f5158551198465316bf86965208da144eff11d4545d9de25fca4410d2b6","observation_id":"d41ad11c-0c06-4e30-8494-46c2044a05bf","resolution":{"observed_at":"2026-08-14T14:35:25.132807Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.095439Z","title":"Lifelong learning with dynamically expandable net- works","venue":null,"work_id":"1bc41f4b-02c0-48b9-ba0b-b7f5a9d626b1","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.403430Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:a9bac16ab118f5b93b308e5a5aaa7780e5a1b0ff4a0cb96d71b795209251d8dd","observation_id":"e7cde388-6c07-4251-bd09-3dfe464fbfa5","resolution":{"observed_at":"2026-08-14T14:35:25.107106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.073009Z","title":"Overcoming catastrophic forgetting by incremental moment matching","venue":null,"work_id":"1b5f318f-217a-4598-8724-fac1a38c54d5","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.410381Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:621572eef926de65fcf10fbc445e33dcc01d1a3439bfed021de409d715d59b7f","observation_id":"ed58ecad-ae35-4523-a02b-f475a98469f6","resolution":{"observed_at":"2026-08-14T14:35:25.079928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.051955Z","title":"Dual-memory deep learning architectures for lifelong learning of everyday human behaviors","venue":null,"work_id":"126c468f-bef5-4b47-9cbe-8b54986a36f1","year":2016},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.417793Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:77ba624965cb6575387e2f3b74c9abce45aced3bf227beba441dc8efe2671c38","observation_id":"cef78b81-5604-4144-93df-54da34d575ed","resolution":{"observed_at":"2026-08-14T14:35:25.057941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.028469Z","title":"Learning without forgetting","venue":null,"work_id":"f9beb2d3-fbc3-445c-8754-2b376943cb58","year":2016},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.422860Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:955cd8b19ff15489894298241e80310abb446d2edf8eb7660cf9d52c4b90bc46","observation_id":"c984c0eb-2099-43a2-a90e-76988f784c68","resolution":{"observed_at":"2026-08-14T14:35:25.036298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:25.009362Z","title":"Gradient episodic memory for contin- ual learning","venue":null,"work_id":"67271006-13f1-4c68-9037-b629a12e7845","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.429225Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:ca130b4a4e3aa96d0d2d50d3a59739aa2c5aa964cdf1c71fe80955c46cea9640","observation_id":"a6891d69-290d-4a01-a857-835e5b07a9e3","resolution":{"observed_at":"2026-08-14T14:35:25.015234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.987876Z","title":"Packnet: Adding mul- tiple tasks to a single network by iterative pruning","venue":null,"work_id":"801ffb46-135a-4bd2-afaf-446e417b9936","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.436686Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:039c89c23721b641d2a62c72a2676ce3c8f3d05c3a7c8e28e55622521fb7c25f","observation_id":"0d7e6ca9-af5a-406b-88b2-57dff0d53b73","resolution":{"observed_at":"2026-08-14T14:35:24.993347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.968565Z","title":"Catastrophic inter- ference in connectionist networks: The sequential learning problem","venue":null,"work_id":"8029ec5a-ceb5-461c-a0d7-12e87e5c32b1","year":1989},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.442509Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:3ce348bf8f8b18ce6ed693279401af89ac3ad96452c1bb01e7ec152995f9bb5d","observation_id":"7d011f99-dd1b-4212-9f5e-5d7eeda449dc","resolution":{"observed_at":"2026-08-14T14:35:24.974093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.948721Z","title":"Variational continual learning","venue":null,"work_id":"61c9f86a-507c-402b-95b9-2776996224e3","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.448775Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:c8d39e40d181933208cd943a0990a0da54b38c469a47430ca44bce23bc037df0","observation_id":"cf6ef8db-a987-4061-8813-54f20099b640","resolution":{"observed_at":"2026-08-14T14:35:24.956878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.930089Z","title":"icarl: Incremental classifier and representation learning","venue":null,"work_id":"26e09f53-cc23-4d81-a0ee-4b1fea986ba0","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.453518Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:155bcfa29a79dc00fd43294da54e23e4cfefa3a14c62ff30018c6fead79d57f7","observation_id":"c3084a97-b852-4d7b-8c3d-6a025e572e49","resolution":{"observed_at":"2026-08-14T14:35:24.935987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.761215Z","title":"A stochastic approxima- tion method","venue":null,"work_id":"fc9c439d-5569-48c5-b7a1-9439a79af479","year":1951},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.458459Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:23344cea6540f053fabcbf8391ccd622b59bc2a2bc77562810d36ca42ac5e2a9","observation_id":"dda79d15-cc2b-4591-9183-0689e02b56f9","resolution":{"observed_at":"2026-08-14T14:35:24.767344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.04671","last_updated":"2022-10-22T14:34:44Z","snapshot_observed_at":"2026-08-14T06:05:49.699878Z","submitted_at":"2016-06-15T08:20:51Z","title":"Progressive Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.04671","snapshot_observed_at":"2026-08-14T14:35:24.463066Z","title":"Progressive neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.463066Z"},"links":{"cited_paper":"/paper/1606.04671","citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:ef02717404c1ede8262021325ebc37db5cfd302ca1ab0107aebc5d86b3a26ced","observation_id":"f2aa5137-1d45-4abf-a307-474bdeb888f2","resolution":{"observed_at":"2026-08-14T14:35:24.463066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.743298Z","title":"Online model selection based on the varia- tional bayes","venue":null,"work_id":"cbdfb448-f303-47ca-9cc4-77b6d0743509","year":2001},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.468282Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:62b4e450a6a797527ad6281aef4c5d7c3b77b33ef8632fcb85da173d91ac5046","observation_id":"d3021a22-c8b9-4112-8542-2b7a3af7b4d8","resolution":{"observed_at":"2026-08-14T14:35:24.748817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.718006Z","title":"Progress compress: A scalable framework for continual learning","venue":null,"work_id":"de8fb23f-2788-4b29-a879-91297c1615d0","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.472934Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:8c1c9a6eaaba6fa8aa702e469df7b73d9aa0042a68271b1e499568ca1213ff80","observation_id":"e842defb-b77d-4a10-bd0c-5a519b84c253","resolution":{"observed_at":"2026-08-14T14:35:24.729991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.697633Z","title":"Overcoming catastrophic forgetting with hard attention to the task","venue":null,"work_id":"e7a1a792-93c3-47eb-a594-6d8c50d7443c","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.478319Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:b01d04aa6dc3054a6177f6150cd730ba067ddb4d9e6739f24deb6696c1161bf4","observation_id":"c2d7a7e1-6dcc-43f4-ae25-2d3823e25006","resolution":{"observed_at":"2026-08-14T14:35:24.703938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.675756Z","title":"Continual learning with deep generative replay","venue":null,"work_id":"4f7ba33d-d096-4325-a2b4-45b56bf083c4","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.484222Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:9dae083ceb9baeab14340962823ac0739453504ad49f1e2a02d2199f87cfc493","observation_id":"7d89f852-8d54-43fb-a668-527dc9dccd58","resolution":{"observed_at":"2026-08-14T14:35:24.683849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.656351Z","title":"Memory-based parameter adaptation","venue":null,"work_id":"1d6361dd-89f5-4d42-ace8-dd9affa80c3a","year":2018},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.489867Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:906db1acc426d8e551fc6db50111ccbcf886a231b83cb0935ce3180ff45a1208","observation_id":"deb0b2d5-efb5-4e2f-ac20-e91c3d230934","resolution":{"observed_at":"2026-08-14T14:35:24.662080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.636314Z","title":"Compete to com- pute","venue":null,"work_id":"864dddf3-29ba-40b0-af54-ec55f4224123","year":2013},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.495510Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:8b4c614623c78ea6c2fde77b6af441b68bbc233fc7bb4d120632a2ea61939f59","observation_id":"022f72ce-65f9-47c6-b756-153ca716ab85","resolution":{"observed_at":"2026-08-14T14:35:24.643861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:35:24.613257Z","title":"Contin- ual learning through synaptic intelligence","venue":null,"work_id":"4f75501d-e806-4096-9a39-5047fc6539ed","year":2017},"citing_paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:35:24.500978Z"},"links":{"citing_paper":"/paper/1908.02984"},"observation_digest":"sha256:480550b7e0e03f0898ac6052567072f3a5fbbcc0ef6388521fc5887a613cce50","observation_id":"98c3f44a-ba72-4b66-b302-ab33e0cc4f49","resolution":{"observed_at":"2026-08-14T14:35:24.620715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.02984","last_updated":"2019-10-22T03:25:38Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T14:25:32.717070Z","submitted_at":"2019-08-08T09:21:21Z","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":31},"total_outbound_references":37},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:1908.02984."}