{"as_of":"2026-08-17T19:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ec1884103a5400d801718b9380049ae0b04e60b84dc5b3c852b29a13c180092d","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:45:01.870747Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2608.11690/citation-record","integrity":"/paper/2608.11690/integrity","json":"/paper/2608.11690/citation-record.json","paper":"/paper/2608.11690"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:45:01.675190Z","title":"Overcoming catastrophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.675190Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:a761cfe3a680f02f035467acd28a280c7c643d74c288e8bcc2b1cae2e1506cc9","observation_id":"1c54a6ee-85ac-49a8-bcbf-86d1a84e4619","resolution":{"observed_at":"2026-08-16T00:45:01.675190Z","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":"2026-08-16T00:45:01.680164Z","title":"Continual lifelong learning with neural networks: A review,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.680164Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:e4ed94b5fd13551893539737f94c8c9d2aa7773366cad091314232ced95e1e75","observation_id":"42406683-2706-403d-b9d1-7c82ae540a94","resolution":{"observed_at":"2026-08-16T00:45:01.680164Z","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":"2026-08-16T00:45:01.684173Z","title":"A continual learning survey: Defying forgetting in classification tasks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.684173Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:1230d33ef76ed3856021c01de4f97cffbcca5473fba308bb052a4b63e7647d22","observation_id":"65b6d806-8ab3-4574-b45f-c154f2aff1ab","resolution":{"observed_at":"2026-08-16T00:45:01.684173Z","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":"2026-08-16T00:45:02.531258Z","title":"Catastrophic interference in connectionist networks: The sequential learning problem,","venue":null,"work_id":"7bc97639-e807-449d-9307-0d9fbf406676","year":1989},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.688854Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:de57b59bb36e7bf546e6275944b18fed99150f75255d71d39ae79024dec91079","observation_id":"26788a50-9b21-4637-82b4-fedd2bbf3a06","resolution":{"observed_at":"2026-08-16T00:45:02.535038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.692461Z","title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.692461Z"},"links":{"cited_paper":"/paper/1312.6211","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:c01824b697be8d283209cd353499b26c4c360aa5f111b153e3e08e16cf2d1b83","observation_id":"d7847459-b7a7-436a-80d9-fabd3879ffeb","resolution":{"observed_at":"2026-08-16T00:45:01.692461Z","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":"2026-08-16T00:45:02.519526Z","title":"Natural continual learning: success is a journey, not (just) a destination,","venue":null,"work_id":"be5c9225-3f19-42eb-919b-1d26e03450db","year":2021},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.696844Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:e6acfaabcbfe40aeabeffa1450297e901334efb4031605e9ecfa45efa41a7a17","observation_id":"1bdc86b1-03d8-4748-84b1-c2d334af9478","resolution":{"observed_at":"2026-08-16T00:45:02.524010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.508598Z","title":"Adaptive plasticity improvement for continual learning,","venue":null,"work_id":"51dc1920-278f-4612-9e87-d1f43ce50c7b","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.700747Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:980440123ca052f9a424d140e6f154447c6f095a7f61505865d6dc52550657d6","observation_id":"c93e9e9f-b33e-43a3-882c-b5cb3c6eff98","resolution":{"observed_at":"2026-08-16T00:45:02.512714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.498281Z","title":"Experience replay for continual learning,","venue":null,"work_id":"4589abfb-a7e5-4728-acb5-1a1c1b10c69f","year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.704748Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:4c8b75cfafd557005d8d9a40e8ac35999c4b5e9c204b723361ce3436a4169c8f","observation_id":"738f230d-4456-48d3-b6dd-20fe43270d30","resolution":{"observed_at":"2026-08-16T00:45:02.501926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.708413Z","title":"icarl: Incremental classifier and representation learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.708413Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:4d5ab973796c9cafa35bda8b6556970f23bc60a73331316619aac9d88633073c","observation_id":"11ff96c2-7ae9-46d7-bac1-fac12002e6f5","resolution":{"observed_at":"2026-08-16T00:45:01.708413Z","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":"2026-08-16T00:45:02.481927Z","title":"Online continual learning through mutual information maximization,","venue":null,"work_id":"41dea977-8f71-4d3d-9925-e403b61c42e0","year":2022},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.712100Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:904ccf8bbe4fd782aacec5a4cc4dce62c9bc0fe543acf43f980e2a5705e0dcca","observation_id":"cce676e8-28c3-4aa8-b98d-06d6afb8c33b","resolution":{"observed_at":"2026-08-16T00:45:02.485491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.471406Z","title":"Learning to learn without forgetting by maximizing transfer and minimizing interference,","venue":null,"work_id":"2d080ae7-c96f-41f2-8d09-11c9549b540d","year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.715674Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:44c1ec5f55aa56f38e9440347c0ee8a81e96938069068e1a2f5ada07d9db9dd8","observation_id":"8b89b1bc-651e-4b11-a921-158532941db4","resolution":{"observed_at":"2026-08-16T00:45:02.474987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.460536Z","title":"A unified approach to domain incremental learning with memory: Theory and algorithm,","venue":null,"work_id":"82ff5fed-02e5-4325-b081-76965b285224","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.719678Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:0a938cbdf5057dea0f5e41fb3907ac2e290b1cc3bc236614d4fdc218c946c1ff","observation_id":"00368bd9-6745-4f12-8f8e-99d7a829ef59","resolution":{"observed_at":"2026-08-16T00:45:02.464205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.450310Z","title":"Stability analysis for incremental adaptive dynamic programming with approximation errors,","venue":null,"work_id":"160aadcc-972d-4efd-80fd-98f33bbf1499","year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.723428Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:9a513726c2ec32377da95a73dd339c18060b80e5af76041b40255044faaa97af","observation_id":"20f2ae7f-745f-411f-b3dd-ef57254a6b0d","resolution":{"observed_at":"2026-08-16T00:45:02.453697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.438617Z","title":"Optimal continual learning has perfect memory and is np-hard,","venue":null,"work_id":"9dac2396-9285-4111-b58e-a11c0ed9b767","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.727279Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:20baa3b41c3333ed021769edf0ca1f8877cff9a8399075226cd138a1cb282fc2","observation_id":"a12183e3-ff66-40b7-a4c4-e26ab4551bae","resolution":{"observed_at":"2026-08-16T00:45:02.442266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.426775Z","title":"Information-theoretic analysis of generalization capability of learning algorithms,","venue":null,"work_id":"cfee2c40-e217-4891-a587-bf021a225355","year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.732030Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:6930d127d2b30c1ea81c6b46df4861e2d76315c497f13058935fdfa73776e6d7","observation_id":"dc6d8555-9e9b-4c63-b7be-fcace319efcf","resolution":{"observed_at":"2026-08-16T00:45:02.430645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.415492Z","title":"Reasoning about generalization via conditional mutual information,","venue":null,"work_id":"6524ab77-5084-4555-9c2b-b3078560cac2","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.735817Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:ea1ee346e1fbf4ef8137f88c0b87f3e6d41c04c837e55cb2471a3ed483a91a25","observation_id":"b5d77bd8-b11f-498e-8848-fdb77ab91805","resolution":{"observed_at":"2026-08-16T00:45:02.419401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.402882Z","title":"Sharpened generalization bounds based on conditional mutual information and an application to noisy, iterative algorithms,","venue":null,"work_id":"a1dd5678-ecfb-4664-ab27-d2a9f9bf0cfb","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.739703Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:c0c4be8ec0bb178e7436d5d3b92ec30c18b939d49ba0d5151cad4482d7927819","observation_id":"f883b3c0-d709-48ff-880b-f20c4b0ba3d8","resolution":{"observed_at":"2026-08-16T00:45:02.408186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.389667Z","title":"Hierarchical generalization bounds for deep neural networks,","venue":null,"work_id":"44609d6e-13e9-4236-aa1a-a54287d5fc07","year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.743759Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:8ddc1a7faf3cbce7c0451e5a11eee590307b8cc129f3ebdc24ed227a096c4195","observation_id":"1b2740f3-1031-4eb2-8610-ab7920fa6b70","resolution":{"observed_at":"2026-08-16T00:45:02.394612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.378922Z","title":"Catastrophic forgetting in connectionist networks,","venue":null,"work_id":"7fce9073-0d15-4be5-aa3e-94ee6a103624","year":1999},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.747732Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:8cfaddbb2eec3f910ef2f894ae561ea210237f069b5a928f7e098d9793ae3204","observation_id":"bb49febc-4a58-47d0-8519-c8438e6336ea","resolution":{"observed_at":"2026-08-16T00:45:02.382738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05175","last_updated":"2024-03-08T09:32:43Z","snapshot_observed_at":"2026-08-17T07:11:31.531084Z","submitted_at":"2024-03-08T09:32:43Z","title":"Continual Learning and Catastrophic Forgetting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05175","snapshot_observed_at":"2026-08-16T00:45:01.751561Z","title":"Continual learning and catastrophic forgetting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.751561Z"},"links":{"cited_paper":"/paper/2403.05175","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:8bd2f4bb052444d0a3fd4bd01dba4207d83226c6ab733fbec0df7e324b237ae9","observation_id":"0b471f2f-f9fb-4dac-b523-d566f9f3618a","resolution":{"observed_at":"2026-08-16T00:45:01.751561Z","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":"2026-08-16T00:45:02.367461Z","title":"A comprehensive survey of continual learning: Theory, method and application,","venue":null,"work_id":"0031384a-022a-4130-8cad-290c9d10821d","year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.756408Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:9bbda02074ae16a194b728e72205554c37892714e1276be941e621d3778afa7c","observation_id":"0cd95a4c-f5fd-4fe7-b231-c0095b49a961","resolution":{"observed_at":"2026-08-16T00:45:02.371295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.759901Z","title":"Continual learning through synaptic intelligence,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.759901Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:d44c9165c6598c21260c242c000610c3e6a81c7388c49cff2ef71f80ed131c46","observation_id":"64769784-777b-4dc9-be18-6080d005ea2c","resolution":{"observed_at":"2026-08-16T00:45:01.759901Z","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":"2026-08-16T00:45:02.349530Z","title":"Memory aware synapses: Learning what (not) to forget,","venue":null,"work_id":"c1f2b703-da77-4bc4-8cfa-d8b1e14cbf9b","year":2018},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.763715Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:5b444bbc347c3eece423c256e472d575e118cf8db711f787cb0f061a5d24f4fb","observation_id":"d0af1f1e-0a54-41db-8a6d-75b8ed28c25d","resolution":{"observed_at":"2026-08-16T00:45:02.353311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.04671","last_updated":"2022-10-22T14:34:44Z","snapshot_observed_at":"2026-08-16T23:40:37.342111Z","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":"2026-08-16T00:45:01.767119Z","title":"Progressive neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.767119Z"},"links":{"cited_paper":"/paper/1606.04671","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:0de294b92e0abe230807706c6f10ba0fb0a03dd537a2e1ee108fc6e568a7b5d5","observation_id":"5f8b5638-eafe-4df7-be08-b5112eb580e5","resolution":{"observed_at":"2026-08-16T00:45:01.767119Z","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":"2026-08-16T00:45:01.771244Z","title":"Packnet: Adding multiple tasks to a single network by iterative pruning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.771244Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:fb36e3cb4232c369380a26fad2c312726de0450028ee0dd0046171e79ec442b6","observation_id":"723782a3-f804-4814-8e08-18957397c64f","resolution":{"observed_at":"2026-08-16T00:45:01.771244Z","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":"2026-08-16T00:45:01.775160Z","title":"Continual learning with deep generative replay,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.775160Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:6102e93a8649b1ff34aab06a930b291d3c2396d843df25cec6789f1c24d0dd36","observation_id":"89d0a2af-ad1b-4894-9a20-ed5c72548e33","resolution":{"observed_at":"2026-08-16T00:45:01.775160Z","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":"2026-08-16T00:45:02.324752Z","title":"Online continual learning from imbalanced data,","venue":null,"work_id":"35b30277-237f-4166-8e2f-86b2b66d79b1","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.778569Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:fad86cd5b43bc5badc40b8c9e415bbd72540f33bfa106598a6ca858c1caea034","observation_id":"e0e868dc-73cd-4970-8723-2e85db65e973","resolution":{"observed_at":"2026-08-16T00:45:02.328883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.04763","last_updated":"2022-04-10T20:07:23Z","snapshot_observed_at":"2026-08-16T23:11:18.820453Z","submitted_at":"2022-04-10T20:07:23Z","title":"Information-theoretic Online Memory Selection for Continual Learning","version":1},"cited_work":{"arxiv_id":"2204.04763","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.04763","snapshot_observed_at":"2026-08-16T00:45:02.090496Z","title":"Information-theoretic Online Memory Selection for Continual Learning","venue":"cs.LG","work_id":"dc55c2f6-7939-4e85-ba14-3cd933173977","year":2022},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.782305Z"},"links":{"cited_paper":"/paper/2204.04763","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:3a777c2bdc017e41ba3145e683f2e8cbc10c6360b4c36119a56b2060f81b9d84","observation_id":"a2943fd0-4975-40b5-bef2-5a2bf36d9f9a","resolution":{"observed_at":"2026-08-16T00:45:02.094530Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.313648Z","title":"New insights on reducing abrupt representation change in online continual learning,","venue":null,"work_id":"f77cbf3e-219d-4675-83b1-84bb96ebac02","year":2022},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.785725Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:a473561321bd10dbe710ed83d000d3dacccdd43c65842e4a66f973681f5bb2cc","observation_id":"93f4c29e-fdfa-4101-838e-35182cf9129a","resolution":{"observed_at":"2026-08-16T00:45:02.317459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.788960Z","title":"Gradient based sample selection for online continual learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.788960Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:7fc7457b83d023dae45da745c18f55ff002599190340695e444298983eca4ca9","observation_id":"6b6d3ef5-77ea-4f83-a730-c99fbf5d6778","resolution":{"observed_at":"2026-08-16T00:45:01.788960Z","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":"2026-08-16T00:45:01.792087Z","title":"Gradient episodic memory for continual learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.792087Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:0bec1b8488bd497b281e10a9d494b9ed19085e080c48e86c3341e211b2037b39","observation_id":"4929516b-602f-419f-a341-96696c63674d","resolution":{"observed_at":"2026-08-16T00:45:01.792087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00420","last_updated":"2019-01-09T11:11:47Z","snapshot_observed_at":"2026-08-15T06:05:04.839393Z","submitted_at":"2018-12-02T16:39:19Z","title":"Efficient Lifelong Learning with A-GEM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00420","snapshot_observed_at":"2026-08-16T00:45:01.795483Z","title":"Efficient lifelong learning with a-gem,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.795483Z"},"links":{"cited_paper":"/paper/1812.00420","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:1f1e0e45ae3fb556d2eb2d0ccf01070dfd38226008590413824eecba81af35a7","observation_id":"6ee5a7b0-0b40-4cac-b085-7a3c561cbe91","resolution":{"observed_at":"2026-08-16T00:45:01.795483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09762","last_updated":"2021-03-17T16:31:29Z","snapshot_observed_at":"2026-08-16T18:38:13.687991Z","submitted_at":"2021-03-17T16:31:29Z","title":"Gradient Projection Memory for Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.09762","snapshot_observed_at":"2026-08-16T00:45:01.799231Z","title":"Gradient projection memory for continual learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.799231Z"},"links":{"cited_paper":"/paper/2103.09762","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:949608d47eff24e60e0284163a07635fde2de0a8eb3f38b7345588351b093c7b","observation_id":"15be4fc9-8dcc-40fb-add2-144506e6bc3c","resolution":{"observed_at":"2026-08-16T00:45:01.799231Z","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":"2026-08-16T00:45:02.288609Z","title":"Theory on forgetting and generalization of continual learning,","venue":null,"work_id":"02b3c125-b8d3-4da9-aed4-91c9ef8cb0ca","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.802962Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:1d5d9281299c5255a5492c9cca0598dd3f21db647ce0341bdb0687d0542b7b7c","observation_id":"18779305-6448-456b-8431-2edd0791d62d","resolution":{"observed_at":"2026-08-16T00:45:02.292764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17583","last_updated":"2024-05-27T18:33:37Z","snapshot_observed_at":"2026-08-16T13:48:54.489995Z","submitted_at":"2024-05-27T18:33:37Z","title":"Understanding Forgetting in Continual Learning with Linear Regression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17583","snapshot_observed_at":"2026-08-16T00:45:01.806825Z","title":"Understanding forgetting in continual learning with linear regression,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.806825Z"},"links":{"cited_paper":"/paper/2405.17583","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:2f11429b8ce015d8a34432697ca04c218cb2630f0c81f83eae3978e64f92b853","observation_id":"091971e5-a616-4650-82cd-458d882876cb","resolution":{"observed_at":"2026-08-16T00:45:01.806825Z","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":"2507.12043","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:45:02.039062Z","title":"Information-theoretic generalization bounds of replay-based continual learning,","venue":null,"work_id":"e2f9b211-5e22-4f62-bfa3-04127fe8f688","year":2026},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.811042Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:a1399084d07f3e41cc7ebaaa7bd27564e3b8360f750820d6e6435740ab44db7e","observation_id":"7dbe4112-0d97-4ef0-8d54-f44dd91eea12","resolution":{"observed_at":"2026-08-16T00:45:02.045431Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.276878Z","title":"Information-theoretic generalization bounds for sgld via data-dependent estimates,","venue":null,"work_id":"79b2f6ab-5b65-4e7c-bb1d-8797a3783f22","year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.814747Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:51660e2612b288660da9053efe8d9114fb2861a4f78e6523fe899cdc22ce76bb","observation_id":"6e34c2d5-c2e0-4df1-a32c-f2ace55214c8","resolution":{"observed_at":"2026-08-16T00:45:02.280771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.01143","last_updated":"2023-05-02T01:17:15Z","snapshot_observed_at":"2026-08-17T02:19:59.740957Z","submitted_at":"2023-05-02T01:17:15Z","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","version":1},"cited_work":{"arxiv_id":"2305.01143","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.01143","snapshot_observed_at":"2026-08-16T00:45:01.918932Z","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","venue":"stat.ML","work_id":"13c7ac88-c5e5-4236-8a22-7aef6853974a","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.818495Z"},"links":{"cited_paper":"/paper/2305.01143","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:650b55aa6fb272b232fdcdfb7de5cae2ea7d5824e5f622d1fc33aa4a50cccaea","observation_id":"7253c2aa-f5c2-4d68-8f51-420e6a2fe761","resolution":{"observed_at":"2026-08-16T00:45:01.922686Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15064","last_updated":"2026-05-07T15:02:45Z","snapshot_observed_at":"2026-08-16T23:11:03.078739Z","submitted_at":"2025-05-21T03:32:30Z","title":"Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning","version":4},"cited_work":{"arxiv_id":"2505.15064","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.15064","snapshot_observed_at":"2026-08-16T00:45:01.901858Z","title":"Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning","venue":"cs.LG","work_id":"789ce0cb-65cb-4f81-9ad5-426fea01f342","year":2025},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.822526Z"},"links":{"cited_paper":"/paper/2505.15064","citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:13f964d7501bf705c76cddbdefdcdafda060f2a9f4c17c7ba4bd09e08735dd30","observation_id":"5856beee-0467-4719-8445-e2612ec3678b","resolution":{"observed_at":"2026-08-16T00:45:01.907698Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.827057Z","title":"Computational optimal transport: With applications to data science,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.827057Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:b54534c5cf79e9445618cc6a9c4c9522e7f8b4f176eb9e7302ebaf9cd3510d7c","observation_id":"98fb48d3-54d3-40c5-a71a-c83660480506","resolution":{"observed_at":"2026-08-16T00:45:01.827057Z","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":"2026-08-16T00:45:02.258817Z","title":"Theoretical analysis of domain adaptation with optimal transport,","venue":null,"work_id":"d448fb96-2e00-4e48-970c-d7e061efa26c","year":2017},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.830727Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:980a5c9b2631122db072a8a0680ce0f3328d12d0012f6704631352902d5aadcc","observation_id":"3977625a-660a-4c14-9e4e-a2f683b274b5","resolution":{"observed_at":"2026-08-16T00:45:02.262569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.247478Z","title":"Generalization error bounds using wasserstein distances,","venue":null,"work_id":"075263d8-1d57-4688-bca4-e558fc91eb79","year":2018},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.834564Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:4b0a148902f2d0066143e73b17109f19fb2ebde719a0c2b7cb822fdee7fe6984","observation_id":"755ee23e-e5b8-41d6-9c89-c26b6d0b5e53","resolution":{"observed_at":"2026-08-16T00:45:02.251447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.234057Z","title":"An information-theoretic view of generalization via wasserstein distance,","venue":null,"work_id":"d9d0c2c9-3b45-4f11-a3c8-e0b5e92f98b8","year":2019},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.838098Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:1112df5ba4c0b969553763df51a35ff52d9de09207a0b601ae2e9f4315140aed","observation_id":"6b182289-f2ee-4400-a2ea-c7e453d4aa29","resolution":{"observed_at":"2026-08-16T00:45:02.238705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.220180Z","title":"Podnet: Pooled outputs distillation for small-tasks incremental learning,","venue":null,"work_id":"29baa472-86d0-44a8-ab3b-f9a619331aee","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.841555Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:cec9a7d0422b30ef3026890f4c84b236e5df6b702be3fac94e907b0fe9e815be","observation_id":"1f8cddca-6793-4ae9-9ff8-26304f84729e","resolution":{"observed_at":"2026-08-16T00:45:02.225077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.206402Z","title":"Reducing catastrophic forgetting with associative learning: a lesson from fruit flies,","venue":null,"work_id":"ba45de74-2b44-4d92-a058-29ff8f421a9e","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.845220Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:7f484d6371197f65c754f74ad6db172e0c3a1b2040ff5703a4464e51bc341ea0","observation_id":"2f771b32-963f-45ed-95a7-d76a09580fa9","resolution":{"observed_at":"2026-08-16T00:45:02.211096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.193902Z","title":"Selective freezing for efficient continual learning,","venue":null,"work_id":"7eadda41-fb90-4454-b6b7-7cde67bc46b9","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.848852Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:7c003958510d055fb1bfae158c8476b5a8c3096fa9abedd1b6f1e3f733069f86","observation_id":"154f5d01-3210-46bf-b3c8-ef66a029f55f","resolution":{"observed_at":"2026-08-16T00:45:02.197893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.182827Z","title":"On the stability-plasticity dilemma in continual meta-learning: Theory and algorithm,","venue":null,"work_id":"0697b0a3-46bd-458c-9f90-8c5c404ce6c8","year":2023},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.852187Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:f5663543aeddaadf169551e484109e25aa7ce306a26bd6c59b91f484fef99edd","observation_id":"7b1f5543-f167-4e73-8b6f-4edcf74f73ab","resolution":{"observed_at":"2026-08-16T00:45:02.186817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.170526Z","title":"Dark experience for general continual learning: a strong, simple baseline,","venue":null,"work_id":"67ce64bf-de57-4d13-9608-1bcc394c01d0","year":2020},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.855670Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:d7bd783dc49eddbd4b46a08b6c4690cd8a5d13339c7c982e6422b0a6e55f7c6e","observation_id":"2273b53e-da20-4075-9906-e7a5440ab7b6","resolution":{"observed_at":"2026-08-16T00:45:02.175100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:01.858993Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.858993Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:99227e590c22a10188e354eaa4b1d6bccd24af6bd6cceb23066aafdc4b821d59","observation_id":"b09ba46c-4893-4680-9f4b-36c92cb63df6","resolution":{"observed_at":"2026-08-16T00:45:01.858993Z","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":"2026-08-16T00:45:01.862337Z","title":"Information-theoretic generalization bounds for black-box learning algorithms,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.862337Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:ad74cbed53a6483760230fc2e33f1f342e7ee2014f0fa6e687cb3609773de8d2","observation_id":"bae38747-6f4e-45ea-8c22-48433628c92e","resolution":{"observed_at":"2026-08-16T00:45:01.862337Z","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":"2026-08-16T00:45:02.146084Z","title":"Towards generalization beyond pointwise learning: A unified information-theoretic perspective,","venue":null,"work_id":"6af35379-731b-4a14-b3cf-6274abb8287a","year":2024},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.865875Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:26acbd15ffc3ddbcb11b483a1f1c26a7ec5546f52b2de80130dbec30cf180156","observation_id":"f1c98ddb-75f1-4942-b43a-a1484a4f7a23","resolution":{"observed_at":"2026-08-16T00:45:02.149977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-16T00:45:02.133970Z","title":"¯ρl(W)· TX i=1 W1 ˆPAl,Y|S i,W1:l, PAl,Y|i,W 1:l # .(56) Since the bound (56) holds for everyl∈{0,...,L}, taking the minimum overlgives, genW ≤min l∈{0,...,L} E","venue":null,"work_id":"20bd8cd5-f1ae-468b-a670-725ddc90576f","year":null},"citing_paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T00:45:01.870747Z"},"links":{"citing_paper":"/paper/2608.11690"},"observation_digest":"sha256:348bf268358950c04a0e86fae98bd90ca28e62b3ee4116965b8d6cdc72bda774","observation_id":"ceeb821f-9662-4881-b27a-e265670f7dda","resolution":{"observed_at":"2026-08-16T00:45:02.138084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.11690","last_updated":"2026-08-12T06:01:49Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T04:03:22.389049Z","submitted_at":"2026-08-12T06:01:49Z","title":"Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":4,"verified_fuzzy":30},"total_outbound_references":52},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2608.11690."}