{"as_of":"2026-08-12T16:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4948db3a99175a4122b036a1a003d3bbfcebbfbbb660a24a44017a57f34cd1aa","coverage":[{"denominator":211,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:19:51.614613Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T11:54:08.395008Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T18:53:51.107769Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01566","snapshot_observed_at":"2026-08-11T11:54:08.395008Z","title":"Multi-objective deep learning: Taxonomy and survey of the state of the art,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14854","last_updated":"2024-12-19T13:48:49Z","snapshot_observed_at":"2026-08-12T12:25:57.124070Z","submitted_at":"2024-12-19T13:48:49Z","title":"Surrogate-assisted multi-objective design of complex multibody systems","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T11:54:08.395008Z"},"links":{"cited_paper":"/paper/2412.01566","citing_paper":"/paper/2412.14854"},"observation_digest":"sha256:c50ea197f14c57a60017183663a5e9c50aa08d3ddf1b5765d50ea61fbd9bff10","observation_id":"e2db7094-4d1d-4da8-91e1-938b21389d70","resolution":{"observed_at":"2026-08-11T11:54:08.395008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"cited_work":{"arxiv_id":"2412.01566","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.01566","snapshot_observed_at":"2026-08-10T18:53:51.107769Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","venue":"cs.LG","work_id":"a2e334a6-b8e6-4e77-8a05-3ed921ec9f9e","year":2024},"citing_paper":{"arxiv_id":"2501.10945","last_updated":"2025-08-06T06:47:04Z","snapshot_observed_at":"2026-08-11T00:45:09.281352Z","submitted_at":"2025-01-19T04:56:55Z","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","version":3},"reference_index":141,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:50.420404Z"},"links":{"cited_paper":"/paper/2412.01566","citing_paper":"/paper/2501.10945"},"observation_digest":"sha256:3c218c3f5d96db569c881e2e18eb2886acc2fcb7251a9bd1c0a9dddaef1b1bd9","observation_id":"60d20819-bb14-4183-932f-408627b3377f","resolution":{"observed_at":"2026-08-10T18:53:51.112967Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.01566/citation-record","integrity":"/paper/2412.01566/integrity","json":"/paper/2412.01566/citation-record.json","paper":"/paper/2412.01566"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:19:51.130062Z","title":"Dynamic weights in multi-objective deep reinforcement learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.130062Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:376b1fa155d801ee14c63f54d00d703b2bdea81c23933eb374ddf2b0253f3da8","observation_id":"b3412fd8-0340-4d77-9342-b3b32d7c9724","resolution":{"observed_at":"2026-08-12T04:19:51.130062Z","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":"2026-08-12T04:19:51.135386Z","title":"Multi-objective reinforcement learning with non-linear scalarization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.135386Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:f61d0c1fd9e13ea1326bafe3d0c9debbc0ca5fda341dde1d8f821bd7601e9738","observation_id":"f6f5c8c6-878f-4419-98fa-4dde3a784500","resolution":{"observed_at":"2026-08-12T04:19:51.135386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.01480","last_updated":"2025-04-29T12:37:51Z","snapshot_observed_at":"2026-08-12T11:47:20.518125Z","submitted_at":"2024-05-02T17:12:25Z","title":"Common pitfalls to avoid while using multiobjective optimization in machine learning","version":2},"cited_work":{"arxiv_id":"2405.01480","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.01480","snapshot_observed_at":"2026-08-12T04:19:52.917444Z","title":"Common pitfalls to avoid while using multiobjective optimization in machine learning","venue":"cs.LG","work_id":"9c5b559f-f00f-4a17-99cb-486a10db056f","year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.140276Z"},"links":{"cited_paper":"/paper/2405.01480","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:9a2f376530699e05acbb2c0fddf16dbb8fbf28429dfb44b4bf33a49e87e9c191","observation_id":"f77d3477-e397-49d5-9366-7df58340d460","resolution":{"observed_at":"2026-08-12T04:19:52.922821Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.146206Z","title":"Multi-objective unsupervised feature selection and cluster based on symbiotic organism search,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.146206Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:92ae4824713cee3269838f788cc7f3fca371c440814853c587c20dffcf176d5e","observation_id":"bdf63cbf-0cdf-4089-8677-7771baf5b3c1","resolution":{"observed_at":"2026-08-12T04:19:51.146206Z","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":"2026-08-12T04:19:51.151316Z","title":"Multi-objective training of generative adversarial net- works with multiple discriminators,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.151316Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:e7fdf4c72f972c60cc48127c137a2c76e7907a90dfb83d2dbc7931e54d8b92d6","observation_id":"2d1f4fa7-332d-4420-af30-5d22e9a904d1","resolution":{"observed_at":"2026-08-12T04:19:51.151316Z","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":"2026-08-12T04:19:51.156091Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.156091Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:9731145cb05b8324b6425f23689e13dbb4a1ecaf3cd0732d9a3af1f175250068","observation_id":"3d0e0dac-b392-4e02-8542-21bdd02c1896","resolution":{"observed_at":"2026-08-12T04:19:51.156091Z","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":"2026-08-12T04:19:51.161264Z","title":"A new semi-supervised clustering technique using multi-objective optimization,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.161264Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d2115aadcfc45ded1536ada76d54f8ed3a2cb9a1e143dd25e2c9db27cd56f1d1","observation_id":"ba405b14-3c61-4e52-a15f-7195e860b960","resolution":{"observed_at":"2026-08-12T04:19:51.161264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12044","last_updated":"2024-03-29T14:25:29Z","snapshot_observed_at":"2026-08-03T04:29:41.936250Z","submitted_at":"2023-08-23T10:08:52Z","title":"A multiobjective continuation method to compute the regularization path of deep neural networks","version":5},"cited_work":{"arxiv_id":"2308.12044","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.12044","snapshot_observed_at":"2026-08-12T04:19:52.895756Z","title":"A multiobjective continuation method to compute the regularization path of deep neural networks","venue":"cs.LG","work_id":"f0d4f544-dfeb-45b3-990c-d61c5b72cd15","year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.165684Z"},"links":{"cited_paper":"/paper/2308.12044","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:07ed312298c7180283bfdaa61d0b7765f10024efc38e64f0cc344ab3b59b6f7e","observation_id":"a85f624d-9c16-4ed3-9f2b-dfaa6ce436e0","resolution":{"observed_at":"2026-08-12T04:19:52.900920Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.170720Z","title":"Hypervolume-based multiobjective optimization: Theoretical foundations and practical im- plications,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.170720Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d24a25e2e8d327a93136d775f4c9007ebc6aa775dc419e37486b7dc943a99b1a","observation_id":"04c5e79f-7483-494e-a648-92601b271775","resolution":{"observed_at":"2026-08-12T04:19:51.170720Z","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":"2026-08-12T04:19:51.175920Z","title":"SVM classification for imbalanced data sets using a multiobjective optimization framework,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.175920Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:bd0d2a26942e75bd4e7bc215f0864e5c9f7f13674cd695a671d2eaab56f2df81","observation_id":"20a7e50a-f3b1-4f0d-8157-b2d45459a27a","resolution":{"observed_at":"2026-08-12T04:19:51.175920Z","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":"2026-08-12T04:19:51.181232Z","title":"Hype: An algorithm for fast hypervolume- based many-objective optimization,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.181232Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:84243f1ea19c5898dd83838010e24e94442fbad1eecf3a60e7820d97f3b0c9d9","observation_id":"1a66b2ba-fb16-437d-ab79-ecee32caf6b3","resolution":{"observed_at":"2026-08-12T04:19:51.181232Z","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":"2026-08-12T04:19:51.186394Z","title":"Evolutionary multi-objective optimization of large language model prompts for balancing sentiments,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.186394Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:97e7791cc633840dda9e2a6a5fd842dd04055149500b76ceb0e8cfc9dcc89bd5","observation_id":"bd3a7ed8-6709-4a28-b08b-0e4e76dfa543","resolution":{"observed_at":"2026-08-12T04:19:51.186394Z","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":"2026-08-12T04:19:51.190968Z","title":"The explicit linear quadratic regulator for constrained systems,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.190968Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:1ce88cd094bdca2643cd56f167177d04a5e9afc1719b8d3bb78151b599ccb208","observation_id":"55a99de2-52ef-426e-9744-5c5d7289c07a","resolution":{"observed_at":"2026-08-12T04:19:51.190968Z","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":"2026-08-12T04:19:51.195531Z","title":"Autoen- coders and their applications in machine learning: a survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.195531Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:bbb5ea1089ef0f58aa7b91bc6fbb5e0b2ac59a4e315a540647d2cd3c0ffaf3e8","observation_id":"058bc91c-613f-4172-bca0-0d0c09df2380","resolution":{"observed_at":"2026-08-12T04:19:51.195531Z","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":"2026-08-12T04:19:51.200697Z","title":"Derivative-free multiobjective trust region descent method using radial basis function surrogate models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.200697Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:8c1a2ee7f383680238556ca4230eefdce5d73c9074f78530c320f0d5ca24bd3f","observation_id":"b6fcc376-4e28-4e27-a034-b956dc5869e6","resolution":{"observed_at":"2026-08-12T04:19:51.200697Z","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":"2026-08-12T04:19:51.205188Z","title":"Bertsekas, Reinforcement learning and optimal control","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.205188Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d5039b579ebef43d7c8518f8e7a96fb01f542179d4af0c2119c74abb6f8a61f7","observation_id":"2af05a1d-7f5e-4d41-82d4-8cee4534b363","resolution":{"observed_at":"2026-08-12T04:19:51.205188Z","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":"2026-08-12T04:19:51.210155Z","title":"DeepSI: Interactive deep learning for semantic interaction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.210155Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:f1b7e4aaa7680a642113303694bb385bf5e9c0294411b9ae9f45da5e89598c40","observation_id":"c26c2e7a-7ff0-4315-a9bd-d4ec21484ef2","resolution":{"observed_at":"2026-08-12T04:19:51.210155Z","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":"2026-08-12T04:19:51.215386Z","title":"On the Treatment of Optimization Problems with L1 Penalty Terms via Multiobjective Continuation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.215386Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:a96ee789a35bb70805f1212b55b0afb8fea519aa7d53acd114dea97d4058364f","observation_id":"e21c1ef4-c454-423c-895f-08687e610ce2","resolution":{"observed_at":"2026-08-12T04:19:51.215386Z","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":"2026-08-12T04:19:51.219808Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.219808Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:069797e117e47c85fbdc086d755b2849ecb7dd0288cea4c15f0a5a928cad2cbf","observation_id":"2dd7f7ec-8d4b-4287-8d92-7889659c52b9","resolution":{"observed_at":"2026-08-12T04:19:51.219808Z","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":"2026-08-12T04:19:51.224722Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.224722Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:645b7c8be5c91cda2fcd1b04f20f2f8a2baa0b5873a3d560cc4d89c4c4ba10e7","observation_id":"ea041d3c-0637-4db4-8b43-291238bcb240","resolution":{"observed_at":"2026-08-12T04:19:51.224722Z","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":"2026-08-12T04:19:51.229354Z","title":"On gradients and hybrid evolutionary algorithms for real-valued multiobjective optimization,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.229354Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:3a27b6b58906515bfcc7ca5fc608f6a231f042dffefe26013536d6d5d623ae53","observation_id":"601fc0fc-ad41-49e4-8dd3-447cf8083ea5","resolution":{"observed_at":"2026-08-12T04:19:51.229354Z","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":"2026-08-12T04:19:51.233778Z","title":"Enhancing multi-objective optimisation through machine learning-supported multiphysics simulation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.233778Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:e94fd61e572e555716f64fb6cc8f0cb999c8b42bf23fb70448fafa1e8df0f105","observation_id":"647c8040-8cfd-425c-ac89-918bc929310d","resolution":{"observed_at":"2026-08-12T04:19:51.233778Z","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":"2026-08-12T04:19:51.238844Z","title":"A survey on active learning and human-in-the-loop deep learning for medical image analysis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.238844Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:170547cac9d8f67756d571d30daa6c392fa9120ce2465d69c2463092bbd1f64b","observation_id":"da19b693-d626-4fb9-b505-1040bfd19f63","resolution":{"observed_at":"2026-08-12T04:19:51.238844Z","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":"2026-08-12T04:19:51.243358Z","title":"MoMAC: Multi-objective optimization to combine multiple association rules into an interpretable classification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.243358Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:cf9cdc3bbeae8f8c44d492405c661963f50fe232be98d1e77940e33fb121454c","observation_id":"7796dd2d-e032-49ff-8723-247ac492d4ea","resolution":{"observed_at":"2026-08-12T04:19:51.243358Z","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":"2026-08-12T04:19:51.248540Z","title":"A Bregman learning framework for sparse neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.248540Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:f264ae10dd15135b40273f13570702cadeea5f427e910934724ca86ea43d9e40","observation_id":"51d6e6bb-7b0b-446a-ad5f-54c8776357b8","resolution":{"observed_at":"2026-08-12T04:19:51.248540Z","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":"2026-08-12T04:19:51.253267Z","title":"Ad-dmkde: Anomaly detection through density matrices and fourier features,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.253267Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:8f8ec95e9f711e5c1afe0af4982d9b600e10737e88c84271fb0a26a74a2013b3","observation_id":"4c7786bb-4bf9-4581-9070-de19c6aef120","resolution":{"observed_at":"2026-08-12T04:19:51.253267Z","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":"2026-08-12T04:19:51.257494Z","title":"Deep clustering for unsupervised learning of visual features,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.257494Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:f4c3248c37c52d76c48c11018c6587ee87d8529d3df050cfe8da845051713a8c","observation_id":"5a2723fe-ea68-43a9-b172-0d0a43daa756","resolution":{"observed_at":"2026-08-12T04:19:51.257494Z","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":"2026-08-12T04:19:51.261977Z","title":"EMORL: Effective multi-objective reinforcement learning method for hyperparameter optimization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.261977Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:0a2010f7c6c1be64cd9f3a865a599b26247d0b6b3712cfe5ce57abeca173b562","observation_id":"1e6f1681-f4d5-4855-a1c0-9b1d2989601f","resolution":{"observed_at":"2026-08-12T04:19:51.261977Z","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":"2026-08-12T04:19:51.267142Z","title":"Semi-supervised and unsupervised deep visual learning: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.267142Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:c32b2b429dd54ca5f385766c721cd5189c49ea3cb2edd65918fd7c910cc75568","observation_id":"9063d768-ab74-438f-9a39-be9c32689151","resolution":{"observed_at":"2026-08-12T04:19:51.267142Z","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":"2026-08-12T04:19:51.271654Z","title":"A tutorial on kernel density estimation and recent ad- vances,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.271654Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:905f8fdad7360af1fdcb5d55c2c3a8044d6a9a3273bbcab4846c64a9ab726dc4","observation_id":"7777e722-c1fa-462d-a55f-fbb7b0b30fb6","resolution":{"observed_at":"2026-08-12T04:19:51.271654Z","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":"2026-08-12T04:19:51.276239Z","title":"Pareto self- supervised training for few-shot learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.276239Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:df5e90edb8eda809fa1eef16913630ad621a43cd7efe4f6c0c8566d970fd8635","observation_id":"93747314-843f-402c-847e-08145e2522f3","resolution":{"observed_at":"2026-08-12T04:19:51.276239Z","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":"2026-08-12T04:19:51.281501Z","title":"Handling computationally expensive multiobjective optimization problems with evolutionary algorithms-a survey,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.281501Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:0e1ad3a0bdb36f01b733c81624d1a62e7a3a06154de99bd65b8d69fba28c6078","observation_id":"1b8b083a-682d-464a-bfce-35ec7fa515e7","resolution":{"observed_at":"2026-08-12T04:19:51.281501Z","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":"2026-08-12T04:19:51.286325Z","title":null,"venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.286325Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:6742e2bd942fd347621c610e59890b78d8e9ccb6707709aeec8071620880a06b","observation_id":"c1e2af90-98c7-4d88-aabf-a34c1b28ec82","resolution":{"observed_at":"2026-08-12T04:19:51.286325Z","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":"2026-08-12T04:19:51.292330Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.292330Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b1538affef5d39e6cb17c66eeffcf4701a87959582f6907984fe8437cd28ca2a","observation_id":"118ecdc1-e6ec-4d01-9f63-34846216f092","resolution":{"observed_at":"2026-08-12T04:19:51.292330Z","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":"2026-08-12T04:19:51.297823Z","title":"A fast and elitist multiobjective genetic algorithm: NSGA-II,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.297823Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:8b9c95af47999a7aecd62b579ec89760e1ea4b6a94e41f300e373d05cb442891","observation_id":"f146cf11-98dd-4040-9cea-589e769ed76a","resolution":{"observed_at":"2026-08-12T04:19:51.297823Z","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":"2026-08-12T04:19:51.303043Z","title":"Surrogate modeling approaches for multiobjective optimization: Methods, taxonomy, and results,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.303043Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:fea8bbdd47b505cba1d58626c3a93096f2aac13f781e16488c05359cf974e23b","observation_id":"bc5aa2d8-64cb-48a2-886e-a95d492566dc","resolution":{"observed_at":"2026-08-12T04:19:51.303043Z","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":"2026-08-12T04:19:51.307588Z","title":"Magnetic control of tokamak plasmas through deep reinforcement learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.307588Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:28f2b41f3de0e1304b823ce21ca07d3d0ff59a76dcdd8e4195f403d5e08fc92c","observation_id":"27f75ff4-e503-45fb-a695-80d2e4916926","resolution":{"observed_at":"2026-08-12T04:19:51.307588Z","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":"2026-08-12T04:19:51.312168Z","title":"Covering pareto sets by multilevel subdivision techniques,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.312168Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:c689e374af675f052aef55050a25a477a2b8ccbbc6b459c9802da9a38ad66367","observation_id":"80d1347d-cbed-4195-9a4f-316867398ce3","resolution":{"observed_at":"2026-08-12T04:19:51.312168Z","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":"2026-08-12T04:19:51.316726Z","title":"Static video summarization with multi-objective constrained optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.316726Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:686865b379290b3adf39487af2807fda4ba8da3ab26ab5eeac8a61c47e9cdca6","observation_id":"bb2f9799-3c52-4461-9c55-4cb969db8b06","resolution":{"observed_at":"2026-08-12T04:19:51.316726Z","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":"2026-08-12T04:19:51.321455Z","title":"Survey on unsupervised learning methods for optical flow estimation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.321455Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:99b4b652c73ce850ddf6cb4aa64a10823ddcb393684714a51844e0c50cb048c8","observation_id":"e96e3db1-78d1-4dc2-916f-868116109117","resolution":{"observed_at":"2026-08-12T04:19:51.321455Z","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":"2026-08-12T04:19:51.326449Z","title":"Generative multi-adversarial networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.326449Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:4c343db611ffa5243450642a8046da446093763077a1ab34e3eada7522db5dae","observation_id":"e2734c0c-fa8b-40d9-861e-330cf0a2a454","resolution":{"observed_at":"2026-08-12T04:19:51.326449Z","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":"2026-08-12T04:19:51.331205Z","title":"Multiple-gradient descent algorithm (MGDA) for mul- tiobjective optimization,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.331205Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:715529a239a1c4d9056e856d50c4c1181b0e4f35036ec99fd4e4135ca13969e8","observation_id":"69e7df0c-8184-4778-aa25-d3208e0905b9","resolution":{"observed_at":"2026-08-12T04:19:51.331205Z","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":"2026-08-12T04:19:51.335878Z","title":"Ehrgott, Multicriteria optimization, 2nd ed","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.335878Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:422d00672425eb3c47cc5c94a64a0ca2022b4664d919816106bc70f1b04ce619","observation_id":"aaadb89e-29d2-4850-a247-b6a375060c46","resolution":{"observed_at":"2026-08-12T04:19:51.335878Z","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":"2026-08-12T04:19:51.341628Z","title":"An adaptive scalarization method in multiobjective optimization,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.341628Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:5c75bd3a266c46a560b79dc3ad3aade04182af5063040f202e9bad119223b18f","observation_id":"8b7d4aa8-1250-4b09-a05a-ee1b77333ae3","resolution":{"observed_at":"2026-08-12T04:19:51.341628Z","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":"2026-08-12T04:19:51.346345Z","title":"Efficient multi-objective neural architecture search via Lamarckian evolution,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.346345Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b655bfd540f1bbccda245abb907a652db25239b86707ba879af450329b458af3","observation_id":"1c956fe8-a965-4c89-99f9-30d7b96e2d86","resolution":{"observed_at":"2026-08-12T04:19:51.346345Z","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":"2026-08-12T04:19:51.351272Z","title":"Neural architecture search: A survey,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.351272Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:e5e66881a4dc7f23b0d759faed3ef2e09ec7651cb20882f21f552432ffec6bc4","observation_id":"368aa3d6-3326-4d77-ab63-9f0067d9dc05","resolution":{"observed_at":"2026-08-12T04:19:51.351272Z","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":"2026-08-12T04:19:51.356624Z","title":"Pareto navigator for interactive nonlinear multiobjective optimization,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.356624Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:a032b6e4e6e618ffbb359fc2e3740dadda1727c2b2490be7c746c41cf595aa13","observation_id":"bde455b3-8402-41bf-8a57-3a7869fbd85a","resolution":{"observed_at":"2026-08-12T04:19:51.356624Z","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":"2026-08-12T04:19:51.362186Z","title":"Multi-objective reinforcement learning based on decomposition: A taxonomy and framework,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.362186Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:6eace148d26b478780ea72f931a6714f09021d007f339d754ecfefaadbe27e08","observation_id":"01bae65a-ced6-4436-a943-7b1bc2578a84","resolution":{"observed_at":"2026-08-12T04:19:51.362186Z","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":"2026-08-12T04:19:51.367410Z","title":"Multi-objective adversarial gesture generation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.367410Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:13cfd7c4f2fbd220b36854d2a6337149d2e28996177d89a0af7c290157a8efa3","observation_id":"83b690fd-799e-4841-9d53-29c87abde049","resolution":{"observed_at":"2026-08-12T04:19:51.367410Z","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":"2026-08-12T04:19:51.372124Z","title":"Newton’s method for multiobjective optimization,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.372124Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b9f88d86a27b15438c42b84dc5714a9bb4ac568448511f4c502606e50eac12ef","observation_id":"cf2979d2-68cc-488a-a88f-3b55d1f64c34","resolution":{"observed_at":"2026-08-12T04:19:51.372124Z","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":"2026-08-12T04:19:51.376885Z","title":"Steepest descent methods for multicriteria optimization,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.376885Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:99d5ca890ebf7711115e7324ef719776d6b575a736ff5afbf57e5fb464b03092","observation_id":"81aae381-a8f0-4c30-b02a-e8a687bc796a","resolution":{"observed_at":"2026-08-12T04:19:51.376885Z","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":"2026-08-12T04:19:51.382357Z","title":"A method for constrained multiobjective optimization based on sqp techniques,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.382357Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d345d041c6b31a643781bba328a7ed23211faef39189d2388540709f9c853b4d","observation_id":"913b43b4-b8c9-42a5-9d75-c60988a5b79e","resolution":{"observed_at":"2026-08-12T04:19:51.382357Z","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":"2026-08-12T04:19:51.387062Z","title":"An overview of evolutionary algorithms in multiobjective optimization,","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.387062Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:32d9512bd88a9061ec453a2fe421be3521a681db3f0ea66cbbae14d042493603","observation_id":"208c91f5-c0b4-4990-84ea-0b616b953d42","resolution":{"observed_at":"2026-08-12T04:19:51.387062Z","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":"2026-08-12T04:19:51.393138Z","title":"DessiLBI: Exploring structural sparsity of deep networks via differential inclusion paths,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.393138Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:5ca841661ef3f7fe14776cdca7fd6a8bc7e49505f1fc2ea799a7ec0df471eeab","observation_id":"23c60b3d-22a6-48a6-ba65-d088e6cd9445","resolution":{"observed_at":"2026-08-12T04:19:51.393138Z","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":"2026-08-12T04:19:51.397678Z","title":"Exploring structural sparsity of deep networks via inverse scale spaces,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.397678Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:7a5b4fe86898ade7af37ec1b629ad9499aff6e6f6e9759223b81c139c38fa781","observation_id":"ea885003-2501-4390-ae70-588c051b0054","resolution":{"observed_at":"2026-08-12T04:19:51.397678Z","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":"2026-08-12T04:19:51.402265Z","title":"Mpgan: Multi pareto generative adversarial network for the denoising and quantitative analysis of low-dose pet images of human brain,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.402265Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:879a2cd01ddb3e6fa1df76c46e2235cc157b64b146a2520d81f5d9c813c48266","observation_id":"06595c82-49a5-4b72-bd9b-079c14389f33","resolution":{"observed_at":"2026-08-12T04:19:51.402265Z","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":"2026-08-12T04:19:51.407148Z","title":"An Efficient Descent Method for Locally Lip- schitz Multiobjective Optimization Problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.407148Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:446d93519361e5950b4d927bc75cc1b1af1f11a0b1329f354f432c47154ad05a","observation_id":"fdaded2f-8b71-466c-ba96-cedf50e41e21","resolution":{"observed_at":"2026-08-12T04:19:51.407148Z","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":"2026-08-12T04:19:51.411564Z","title":"A Descent Method for Equality and Inequality Constrained Multiobjective Optimization Problems,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.411564Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:9526edbf749988edef2f6f346a27871ede6baca47edabef5b2a596a251e83922","observation_id":"1a71c08f-d446-4aae-9181-e2d8de17d179","resolution":{"observed_at":"2026-08-12T04:19:51.411564Z","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":"2026-08-12T04:19:51.416044Z","title":"On the hierarchical structure of Pareto critical sets,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.416044Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d293980cf1768aa7d36f158ab535bd6f29e96eae45ad36de4ea84b0f1e1d89e0","observation_id":"4fc494e8-754e-4eed-b5ef-77a0888b49db","resolution":{"observed_at":"2026-08-12T04:19:51.416044Z","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":"2026-08-12T04:19:51.420468Z","title":"Unsupervised band selection based on evolutionary multiobjective optimization for hyperspectral images,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.420468Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:3fb74b23e9532e3b3f52975390a02b0249c5f1eb5df639f804318dddf1623738","observation_id":"a5fd57dd-a096-4b54-a794-2acd28eff0ae","resolution":{"observed_at":"2026-08-12T04:19:51.420468Z","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":"2026-08-12T04:19:51.425596Z","title":"Improving constrained clustering via decomposition-based multiobjective optimization with memetic elitism,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.425596Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:58c26ad1b1bd3e827fa201d8948a1eb1f694de64d3dd5e5aa953455034b203d3","observation_id":"772b32dc-b319-4e06-8720-a8b9ae83dcb9","resolution":{"observed_at":"2026-08-12T04:19:51.425596Z","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":"2026-08-12T04:19:51.430325Z","title":"Goodfellow, Y","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.430325Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:0fa4da04632d2baa171cc400e74989c12644fb9be2a3abdc91ce89d2e290c9a9","observation_id":"80b23b43-554e-486b-a5a2-f35f0222fe4f","resolution":{"observed_at":"2026-08-12T04:19:51.430325Z","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":"2026-08-12T04:19:51.435563Z","title":"Generative adversarial nets,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.435563Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:94fde345e1e1b4ca327a7e91b740a18cc0dfaac5e5d0280fd2b8a54721838298","observation_id":"3156c659-bcab-4bd4-a19c-9eeb7b1cfa0d","resolution":{"observed_at":"2026-08-12T04:19:51.435563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.05712","last_updated":"2024-07-14T09:30:45Z","snapshot_observed_at":"2026-07-06T14:41:10.087407Z","submitted_at":"2023-01-13T14:41:05Z","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.05712","snapshot_observed_at":"2026-08-12T04:19:51.440058Z","title":"A survey on self-supervised learning: Algorithms, applications, and future trends,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.440058Z"},"links":{"cited_paper":"/paper/2301.05712","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:3b987e90a21c7c737ed88388ac46d6fa5d060e83ebd14f671908c4f3283408da","observation_id":"9f6fea67-fcb3-47d0-bd00-67c35adadef5","resolution":{"observed_at":"2026-08-12T04:19:51.440058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07518","last_updated":"2019-11-18T10:04:08Z","snapshot_observed_at":"2026-07-06T08:37:46.034443Z","submitted_at":"2019-11-18T10:04:08Z","title":"Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features","version":1},"cited_work":{"arxiv_id":"1911.07518","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.07518","snapshot_observed_at":"2026-08-12T04:19:52.857505Z","title":"Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features","venue":"cs.CV","work_id":"42368121-5fc2-42bf-912f-0831528a9f06","year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.446098Z"},"links":{"cited_paper":"/paper/1911.07518","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:05d781b28f8c90c17552681c878446a0ba7c4440556c1bac8ed82b5668cc9372","observation_id":"c7371f3a-2de5-4944-b49c-6215a3edc368","resolution":{"observed_at":"2026-08-12T04:19:52.863782Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.451267Z","title":"Soft actor-critic: Off- policy maximum entropy deep reinforcement learning with a stochastic actor,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.451267Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:fdc9473980af2255bd6c6204f05772a5b4489926fe7c890f2a429b064a692489","observation_id":"d44bf095-c3b7-45e8-879b-e56bf98e63c2","resolution":{"observed_at":"2026-08-12T04:19:51.451267Z","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":"2026-08-12T04:19:51.456259Z","title":"Kill two birds with one stone: A multi-view multi-adversarial learning approach for joint air quality and weather prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.456259Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:e7bf5abaeb3986bd5c0e9c2af7f26dfb015f69b1c39e1ca11e1f324bb0c3a847","observation_id":"5dc4e224-8035-4d26-922b-9ffd96ac053f","resolution":{"observed_at":"2026-08-12T04:19:51.456259Z","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":"2026-08-12T04:19:51.460873Z","title":"Feature subset selection in unsupervised learning via multiobjective optimization,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.460873Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:1f32374bf06d5939a7daa7290176e117ac3301a1c1ade3c74a7268aee5ac89e1","observation_id":"8757acda-ba06-4c45-aec9-c27e093d1893","resolution":{"observed_at":"2026-08-12T04:19:51.460873Z","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":"2026-08-12T04:19:51.465726Z","title":"Hastie, R","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.465726Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:66443b3b55cadabea1374a47a6ff743975540fbff50f231970dfd0d549ec7cbc","observation_id":"b2ef5e08-e1d2-4e95-88b4-628fa28c90e5","resolution":{"observed_at":"2026-08-12T04:19:51.465726Z","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":"2026-08-12T04:19:51.470303Z","title":"A practical guide to multi- objective reinforcement learning and planning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.470303Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b47e5676a1c3008fbe2feef67909ed3dd55e586f2c74b3ae9089acc087aa96c2","observation_id":"84159b04-60b6-4f52-b2c9-f213f73e15b7","resolution":{"observed_at":"2026-08-12T04:19:51.470303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04966","last_updated":"2020-04-09T06:19:45Z","snapshot_observed_at":"2026-07-06T08:28:38.267138Z","submitted_at":"2019-10-11T04:28:41Z","title":"Evolutionary Multiobjective Optimization Driven by Generative Adversarial Networks (GANs)","version":2},"cited_work":{"arxiv_id":"1910.04966","doi":null,"metadata_source":"pith","pith_arxiv_id":"1910.04966","snapshot_observed_at":"2026-08-12T04:19:52.835683Z","title":"Evolutionary Multiobjective Optimization Driven by Generative Adversarial Networks (GANs)","venue":"cs.NE","work_id":"7ccba732-d2f2-421f-b40a-f70ada857b9f","year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.475001Z"},"links":{"cited_paper":"/paper/1910.04966","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:8e5e957e954f0a9e79519e8606f9fd5c9975175e7fe168fdc4f4aa576cf16c85","observation_id":"5cf6884e-b2f4-45d8-a38f-596553d591f6","resolution":{"observed_at":"2026-08-12T04:19:52.840795Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.480130Z","title":"Masked autoencoders are scalable vision learners,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.480130Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:658bf2eb1a38f28350f1ab6cd4de7ed7990a3cb665b8194ca2f9698dda2598cf","observation_id":"5ee17009-8ce7-4be7-81b1-cc50a81ec525","resolution":{"observed_at":"2026-08-12T04:19:51.480130Z","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":"2026-08-12T04:19:51.484687Z","title":"Hillermeier, Nonlinear Multiobjective Optimization: A Generalized Homotopy Approach","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.484687Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:1e70a3addfdd0bf8bd15507a8c76406392b2939f3fad72cc626a32f972f0e200","observation_id":"4594a6fa-197a-4f19-ac27-b49f50e2fbd6","resolution":{"observed_at":"2026-08-12T04:19:51.484687Z","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":"2026-08-12T04:19:51.489753Z","title":"Multi-objective optimiza- tion for sparse deep multi-task learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.489753Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:d91c615073b07d49bc602b0403a88b08f4915fa6c8e07f57822673d5b27e3f23","observation_id":"bc9429c6-7c75-4479-b550-132319012c03","resolution":{"observed_at":"2026-08-12T04:19:51.489753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01697","last_updated":"2025-06-29T20:23:44Z","snapshot_observed_at":"2026-07-06T19:26:12.102947Z","submitted_at":"2024-10-02T16:05:03Z","title":"Enhancing Adversarial Robustness through Multi-Objective Representation Learning","version":4},"cited_work":{"arxiv_id":"2410.01697","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.01697","snapshot_observed_at":"2026-08-12T04:19:52.814467Z","title":"Enhancing Adversarial Robustness through Multi-Objective Representation Learning","venue":"cs.LG","work_id":"3e3b0399-9b3a-4e1e-a469-5fa7560913ce","year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.494159Z"},"links":{"cited_paper":"/paper/2410.01697","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:82683db2f82533b2b1e1de0333e4e7bfc2131b24e79073c09e82b620f69017ae","observation_id":"e5960275-c05b-4a83-8c4a-28407350daeb","resolution":{"observed_at":"2026-08-12T04:19:52.819575Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.499130Z","title":"A generative Kriging surrogate model for constrained and unconstrained multi-objective optimization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.499130Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:af4cdea4ef835c0cb92985cff4aacc6e1c63b1664413f704444c9d2cf1f8e091","observation_id":"93f6adfb-f1a6-49cb-a17a-09e8809227c7","resolution":{"observed_at":"2026-08-12T04:19:51.499130Z","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":"2026-08-12T04:19:51.504166Z","title":"Multi-objective GFlowNets,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.504166Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b04c515fc91fc503f5dec89358ce90cd729b40522a88185f7a9a0e8cc504d881","observation_id":"0356914d-19dc-4374-847f-231b59306f72","resolution":{"observed_at":"2026-08-12T04:19:51.504166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07398","last_updated":"2024-08-08T19:48:10Z","snapshot_observed_at":"2026-08-08T20:23:12.137375Z","submitted_at":"2024-06-11T16:05:15Z","title":"Visual Representation Learning with Stochastic Frame Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07398","snapshot_observed_at":"2026-08-12T04:19:51.508905Z","title":"Visual rep- resentation learning with stochastic frame prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.508905Z"},"links":{"cited_paper":"/paper/2406.07398","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:aacc434a1501d8358a271d4ace0cda2f1f11239263214ad75839d22b187c3705","observation_id":"9e5db9f8-5b7e-45d4-92a7-eb0702028bda","resolution":{"observed_at":"2026-08-12T04:19:51.508905Z","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":"2026-08-12T04:19:51.513661Z","title":"Feature dimensionality reduction: a review,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.513661Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:ce843bd47b99fb9dd8d7d9ea5ca398b95b5bb55bcba4f012f16e8019d9ab0de0","observation_id":"99bdecba-efd0-487a-bb1b-b13591f27f7d","resolution":{"observed_at":"2026-08-12T04:19:51.513661Z","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":"2026-08-12T04:19:51.519053Z","title":"Jin, Ed., Multi-Objective Machine Learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.519053Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:07469178ca198fb930207f11f01c46aa74da80a825b837e377649e69a600a2b4","observation_id":"04076228-4f41-4c67-8eb1-dd678e4d74d3","resolution":{"observed_at":"2026-08-12T04:19:51.519053Z","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":"2026-08-12T04:19:51.523894Z","title":"Pareto-based multiobjective machine learning: An overview and case studies,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.523894Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:3ebed20e7d83d11db7b95af868610af8df1ea21d426ef49278fc7449026b7829","observation_id":"c293e667-7c3e-4301-a569-35e8b41ddd20","resolution":{"observed_at":"2026-08-12T04:19:51.523894Z","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":"2026-08-12T04:19:51.528580Z","title":"Evolutionary multi-objective opti- mization of spiking neural networks,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.528580Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:c65720d668a0bb5bdf4402930c9dcbbd353bdbfde944dcfec23607a97a336926","observation_id":"9d4b5d64-83e5-4987-9f81-2bfbc1f36fce","resolution":{"observed_at":"2026-08-12T04:19:51.528580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.11387","last_updated":"2019-04-04T02:51:59Z","snapshot_observed_at":"2026-07-06T07:17:31.201039Z","submitted_at":"2018-11-28T05:04:34Z","title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.11387","snapshot_observed_at":"2026-08-12T04:19:51.533011Z","title":"Self-supervised spatiotem- poral feature learning via video rotation prediction,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.533011Z"},"links":{"cited_paper":"/paper/1811.11387","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:90fc2f965f6c5509ea2458e2cb9c4a95c8cd97de752d3e171999352ee0a04f07","observation_id":"11a1d2f4-d5a1-47c6-ad6d-13848b3685a3","resolution":{"observed_at":"2026-08-12T04:19:51.533011Z","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":"2026-08-12T04:19:51.537904Z","title":"Multi-objective hyperparameter optimization in machine learning—an overview,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.537904Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:4a87ecb6fbf9f6fc813b202c5c4bfb7e2241f14be7fea96176ea85e7a73d4349","observation_id":"65442d86-fe5c-4571-bb54-e136024ce8b9","resolution":{"observed_at":"2026-08-12T04:19:51.537904Z","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":"2026-08-12T04:19:51.542777Z","title":"Physics-informed machine learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.542777Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:2e0bef37fddabaaa1d42f7d76c3afe533d3fc37c83334de70d8b7f702215e3e7","observation_id":"ed7bc697-a1b3-4cc8-bda3-66a8481fb200","resolution":{"observed_at":"2026-08-12T04:19:51.542777Z","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":"2026-08-12T04:19:51.547263Z","title":"A conic scalarization method in multi-objective opti- mization,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.547263Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:25065965a69500da43d6b37597cff652c575e08bfe2e1e2b21345450010dbe73","observation_id":"5b3c1fa1-db3d-4229-bca9-eb4f4ad4a4db","resolution":{"observed_at":"2026-08-12T04:19:51.547263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.17059","last_updated":"2025-08-25T15:16:46Z","snapshot_observed_at":"2026-08-12T11:46:42.506627Z","submitted_at":"2024-08-30T07:38:28Z","title":"A Survey of the Self Supervised Learning Mechanisms for Vision Transformers","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.17059","snapshot_observed_at":"2026-08-12T04:19:51.551717Z","title":"A survey of the self supervised learning mechanisms for vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.551717Z"},"links":{"cited_paper":"/paper/2408.17059","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:34322820516078b5db715b2d66ae86e646c340b92c7120bc38bc014e2b08ac35","observation_id":"6bed391f-4c8e-4157-b57e-e39185cb6bd1","resolution":{"observed_at":"2026-08-12T04:19:51.551717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00282","last_updated":"2024-05-31T07:19:03Z","snapshot_observed_at":"2026-08-06T02:15:47.201579Z","submitted_at":"2024-03-01T04:57:13Z","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2403.00282","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.00282","snapshot_observed_at":"2026-08-12T04:19:52.743990Z","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","venue":"cs.LG","work_id":"24be1e54-b4b3-4569-8765-0824f04fd5f2","year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.557137Z"},"links":{"cited_paper":"/paper/2403.00282","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:b72e021d12f77690d30e36ccefce903073e87d7a4cb9b62d9b40716ee1f5cffc","observation_id":"5d23acbe-22c9-4182-a66f-95a1116105b5","resolution":{"observed_at":"2026-08-12T04:19:52.749452Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:19:51.562259Z","title":"MDARTS: Multi-objective differentiable neural architecture search,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.562259Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:5bb430bc63ab1f8e62b5665cacf19233ce036e412e24dea7e78dcaf298ddf330","observation_id":"51c3044b-eab2-490d-ae77-de79bbfed714","resolution":{"observed_at":"2026-08-12T04:19:51.562259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T04:19:51.567420Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.567420Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:95a017b9ac56e39287451f17a47d8a5f1687569581571ee8f8343a02dcf87b3f","observation_id":"dc1468b7-7459-460f-abbe-f3e5721de726","resolution":{"observed_at":"2026-08-12T04:19:51.567420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-12T04:19:51.572114Z","title":"Auto-encoding variational Bayes,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.572114Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:98379ae1a35ed28232505660cc72832a1f96e5299b357a88957befc85fba1ee8","observation_id":"1887f6c6-941c-4d5e-ace8-3e8b13f9e1dd","resolution":{"observed_at":"2026-08-12T04:19:51.572114Z","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":"2026-08-12T04:19:51.576752Z","title":"An introduction to variational autoencoders,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.576752Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:91e2dde93bb8057a0e7ec116a91670ae4ac479556854d1157a83b60d343fb60b","observation_id":"4b4bebea-3754-4934-8c06-34dcffad57f1","resolution":{"observed_at":"2026-08-12T04:19:51.576752Z","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":"2026-08-12T04:19:51.581904Z","title":"Reinforcement learning in robotics: A survey,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.581904Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:2aa75bf5c787089d918306bf1b37ace12873d855d4183e3aac5cc980c5e326ad","observation_id":"9b7051e2-3c19-4e45-9e19-8d188a56154e","resolution":{"observed_at":"2026-08-12T04:19:51.581904Z","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":"2026-08-12T04:19:51.586379Z","title":"Intensity-modulated radiotherapy - a large scale multi- criteria programming problem,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.586379Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:4a6480bbbdfc9bf4709aa47d0525534092188e4eb058d0a0f770b4f04bcc0cb1","observation_id":"6953c816-b8a9-4b3d-894f-3741eed8db3e","resolution":{"observed_at":"2026-08-12T04:19:51.586379Z","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":"2026-08-12T04:19:51.590928Z","title":"Contrastive self-supervised learning: review, progress, challenges and future research directions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.590928Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:19fbf141efc432296ee76287869fb7ae2d1d172c9cc12aee323be61b5ca88c8f","observation_id":"d7f597b6-4040-470b-98ba-11dc3829d9ec","resolution":{"observed_at":"2026-08-12T04:19:51.590928Z","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":"2026-08-12T04:19:51.595467Z","title":"Deep learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.595467Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:13a4bec9e71f7cfacaf82a372a4d4ebaf48fd47367ba2f4b7eb5cfcd06adfdd0","observation_id":"f82aa998-5efc-4856-8811-7c0cae33f40a","resolution":{"observed_at":"2026-08-12T04:19:51.595467Z","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":"2026-08-12T04:19:51.600020Z","title":"Lassonet: A neural network with feature sparsity,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.600020Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:8659805682683adc65c09ff629493d540a3545acf04e11ecffd6650f63395648","observation_id":"a2eb1d42-f589-4f17-8356-1758d7eebb48","resolution":{"observed_at":"2026-08-12T04:19:51.600020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00487","last_updated":"2024-11-24T14:11:56Z","snapshot_observed_at":"2026-08-09T18:37:31.688429Z","submitted_at":"2024-06-29T16:34:23Z","title":"It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.00487","snapshot_observed_at":"2026-08-12T04:19:51.604587Z","title":"It’s morphing time: Unleashing the potential of multiple llms via multi-objective optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.604587Z"},"links":{"cited_paper":"/paper/2407.00487","citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:3c6ce4b20442c97a7f79cc2e5c2c11fcabbebd7875aba3a426a42dd42617e058","observation_id":"0afbccda-4ee5-438b-964f-2934c508591f","resolution":{"observed_at":"2026-08-12T04:19:51.604587Z","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":"2026-08-12T04:19:51.609383Z","title":"Deep reinforcement learning for mul- tiobjective optimization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.609383Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:12de982a60b3f4fc2e9c38c8730e49cadf580e015ca46658a34bdb3b4d532abc","observation_id":"dd42c863-8062-4bde-9030-e0c534ae58ed","resolution":{"observed_at":"2026-08-12T04:19:51.609383Z","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":"2026-08-12T04:19:51.614613Z","title":"Multi-augmentation contrastive learning as multi- objective optimization for graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T04:19:51.614613Z"},"links":{"citing_paper":"/paper/2412.01566"},"observation_digest":"sha256:fae1abf4fce933f97a1d10bbe6d2e5c27cd3f5afdd55ecf1a78af5f043924d0c","observation_id":"68e347c2-8ad5-440f-8088-cebb2baea595","resolution":{"observed_at":"2026-08-12T04:19:51.614613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.01566","last_updated":"2024-12-03T08:42:37Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T11:47:08.936685Z","submitted_at":"2024-12-02T14:51:21Z","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":94,"verified_exact":6,"verified_fuzzy":0},"total_outbound_references":211},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 100 of 211 outbound references and 2 inbound Pith citation observations for arXiv:2412.01566."}