{"as_of":"2026-08-08T05:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ebc3d009f09bb2d370f84552821d7be0a9ee43ec39e1ccf056b963daf108bbb7","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:22:12.191394Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.03225/citation-record","integrity":"/paper/2506.03225/integrity","json":"/paper/2506.03225/citation-record.json","paper":"/paper/2506.03225"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.925332Z","title":"Deep reinforcement learning at the edge of the statistical precipice","venue":null,"work_id":"3f54a6af-dbe5-4b59-9ad9-cd624ab91cae","year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.027651Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:bcf18f755731642ef54622c1fe661519d72f803fe61a1d0e567344edc33cb311","observation_id":"9277282f-542e-4949-87fa-50add0e2b1ac","resolution":{"observed_at":"2026-08-07T11:22:12.932235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.034156Z","title":"Dehb: Evolutionary hyberband for scalable, robust and efficient hyperparameter optimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.034156Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:1bf74dbf504430d34083e8fa5d986d1c82fb8ed16ad4efc0506713fe56dd8d46","observation_id":"59b55995-4a28-4940-9041-d773b0ce19d3","resolution":{"observed_at":"2026-08-07T11:22:12.034156Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.904791Z","title":"Agent57: Outperforming the A tari human benchmark","venue":null,"work_id":"e07549f0-5924-4732-8db1-eba8ff65ccdc","year":2020},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.039659Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:1f10f36eba2d7fcf4578e26f8f579c0adaa7a4748ef42231d064c27258126f39","observation_id":"cf93739c-4af3-468c-a504-6208059fc2b5","resolution":{"observed_at":"2026-08-07T11:22:12.910733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.885082Z","title":"Random search for hyper-parameter optimization","venue":null,"work_id":"ebebcbf7-a0d6-498f-b0a6-0d79475d897e","year":2012},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.044349Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:5b33d13f2536c070f82aa936e02717849d68fe80a981fa2d118a814ea06918e4","observation_id":"584f88fa-b6c0-49a9-849d-eec523cf022b","resolution":{"observed_at":"2026-08-07T11:22:12.890376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.049199Z","title":"Algorithms for hyper-parameter optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.049199Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:10f03e55bedff5ad76ae0eb077c71b0778d15cb94bedfff126fb9808bf21a620","observation_id":"97d3da53-db5d-4d90-8aa0-effb3a915dde","resolution":{"observed_at":"2026-08-07T11:22:12.049199Z","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":"2026-08-07T11:22:12.054039Z","title":"JAX : composable transformations of P ython+ N um P y programs, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.054039Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:aea42356ec779b8fb91cd540c8747d4925fc74d938b42fff92fda42deb8e833d","observation_id":"a838f0a9-4dc9-4c09-a9aa-937fb6badf3c","resolution":{"observed_at":"2026-08-07T11:22:12.054039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03349","last_updated":"2025-02-05T16:41:05Z","snapshot_observed_at":"2026-08-08T05:47:30.132299Z","submitted_at":"2025-02-05T16:41:05Z","title":"Robust Autonomy Emerges from Self-Play","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03349","snapshot_observed_at":"2026-08-07T11:22:12.059284Z","title":"Robust autonomy emerges from self-play, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.059284Z"},"links":{"cited_paper":"/paper/2502.03349","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:c79a2620c5238be1657310319eecb4800039ed2609fadbfd49218f1567150f70","observation_id":"8156596f-6c89-4e73-88de-d91278db7eb1","resolution":{"observed_at":"2026-08-07T11:22:12.059284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13800","last_updated":"2021-09-28T15:30:55Z","snapshot_observed_at":"2026-08-07T16:36:41.078725Z","submitted_at":"2021-09-28T15:30:55Z","title":"Faster Improvement Rate Population Based Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13800","snapshot_observed_at":"2026-08-07T11:22:12.064031Z","title":"Faster improvement rate population based training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.064031Z"},"links":{"cited_paper":"/paper/2109.13800","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:4df48618281ac3cf8ce5e987bd4d0339c08ed170d1e4f0398664d7c235a121cb","observation_id":"488b3ef7-c3ea-40be-9b9b-6a7a06d0a2ef","resolution":{"observed_at":"2026-08-07T11:22:12.064031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.844888Z","title":"Hyperparameters in reinforcement learning and how to tune them","venue":null,"work_id":"80c743ff-eeba-4caf-bbe9-8c0763c90bc3","year":2023},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.068403Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:d0bde2ba58fecdd0d4b51b111a3540502efd1e61a1a1ad00f3a4745660f1028d","observation_id":"f70428d4-4c1f-4fd6-873b-3c723261e8dd","resolution":{"observed_at":"2026-08-07T11:22:12.851255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.823011Z","title":"BOHB : Robust and efficient hyperparameter optimization at scale","venue":null,"work_id":"620ed4ba-558b-445d-ad97-31623940126a","year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.072575Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:82081861f1016980a46adeef8d395c5a00966f048f7c54f0fafead08cce4e28b","observation_id":"512a7e88-7906-458c-aa6d-4dc6ab7cd833","resolution":{"observed_at":"2026-08-07T11:22:12.829756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.801045Z","title":"Hyperparameter optimization","venue":null,"work_id":"252e020e-64c1-4097-9b43-5b73726efc6a","year":2019},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.077585Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:3e0f7d6a43468e35e9dc744d466f4c271e33c5c4bf422c3f24adb8603d7cc54f","observation_id":"9a6c291d-752e-4ce4-88ec-3d86c3577638","resolution":{"observed_at":"2026-08-07T11:22:12.805967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.784170Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":"21e59c3f-c6b8-47f6-ae29-3ab1fd258094","year":2017},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.082963Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:ea75ce067a2cb20643fc913d1a4dcc18da6a7ec2b4dfdcfb8c451068a4f1efc8","observation_id":"f47feaee-f810-456a-8799-737908e2dd41","resolution":{"observed_at":"2026-08-07T11:22:12.789744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.767405Z","title":"Franke, Gregor Koehler, Andr \\'e Biedenkapp, and Frank Hutter","venue":null,"work_id":"f4c42096-f86a-456c-987f-b85fd50e4655","year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.087947Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:3a1e79159d197e490c2fe3137ef1d4e373674a3855756b87ef951c40082a33de","observation_id":"ebc7eed6-7e75-490d-bd20-492ab42f7ba7","resolution":{"observed_at":"2026-08-07T11:22:12.772781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.749836Z","title":"Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, and Olivier Bachem","venue":null,"work_id":"2c29470c-28d3-46ae-8323-542fa4d7c340","year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.092720Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:3754cecfadc086d81485e83ef1fbbf6dd865003f32fe58cb24ccf97197a2fa0b","observation_id":"7df6aecc-dac8-4164-9830-d5316aaed0ee","resolution":{"observed_at":"2026-08-07T11:22:12.755390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.097718Z","title":"Deep reinforcement learning that matters","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.097718Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:6f24a428c20bbc09b2a45d167cf2e7a872f242340a003dade65eb8aa19d7f33d","observation_id":"eee2772b-4f44-46da-ace5-bba2560cb11f","resolution":{"observed_at":"2026-08-07T11:22:12.097718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09846","last_updated":"2017-11-28T16:16:21Z","snapshot_observed_at":"2026-07-06T06:11:24.949724Z","submitted_at":"2017-11-27T17:33:27Z","title":"Population Based Training of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.09846","snapshot_observed_at":"2026-08-07T11:22:12.102205Z","title":"Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyan, Chrisantha Fernando, and Koray Kavukcuoglu","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.102205Z"},"links":{"cited_paper":"/paper/1711.09846","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:fb23b30c2f617508592d00f4c048ff282e50c8e704e3a7dbe59a76857fd4b797","observation_id":"09db5e96-ed3d-4cf2-870f-81fd6d1fe03d","resolution":{"observed_at":"2026-08-07T11:22:12.102205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.714315Z","title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","venue":null,"work_id":"1900ae4e-29cf-4827-a9c9-056393017584","year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.107849Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:5fbb95f630e4a1bca85fbd3d4e59dd5b3eb143726eed0ce0667e128affa02237","observation_id":"633d8309-c3bb-494c-aee3-3331cdd71403","resolution":{"observed_at":"2026-08-07T11:22:12.719967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1126/scirobotics.abo0235","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.305240Z","title":null,"venue":null,"work_id":"d5e69740-ba13-4f00-848e-510ab95a82c6","year":2022},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.113358Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:de4bdaac23fbd051b5394b39da9798d753dbf17e5c76b3c6a96afd4a9f310c96","observation_id":"138bc37d-9e79-4c80-a584-c34ff91f96ea","resolution":{"observed_at":"2026-08-07T11:22:12.311519Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.696371Z","title":"Provably efficient online hyperparameter optimization with population-based bandits","venue":null,"work_id":"22a85475-1475-4fd0-b2da-bc975be0fc6b","year":2020},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.119609Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:50cd33aec869ed8df3e3795dffa156d3eb9fa9e1afc33c0efa34fa315fcba085","observation_id":"8a51ca2d-c154-4c05-b8b9-d412311751e1","resolution":{"observed_at":"2026-08-07T11:22:12.701548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.677888Z","title":"Tuning mixed input hyperparameters on the fly for efficient population based autorl","venue":null,"work_id":"565651f5-2f13-4143-89b6-3302d7f235f4","year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.125864Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:e2d6aeb3a80bea26ff3283d447dc53829f05d8d83dc7793e62d55c290ad2171f","observation_id":"5428cee0-1fef-4dfc-ae09-ab2b66bbbe4a","resolution":{"observed_at":"2026-08-07T11:22:12.683373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1613/jair.1.13596","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.289088Z","title":"Automated reinforcement learning (autorl): A survey and open problems","venue":null,"work_id":"7d4d2bc4-6cf1-4f82-8383-a1e64cfac65d","year":2022},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.131225Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:7c9fa5434957b629c93c561fd135ec94b4dfbef53377803d41302f179a5e209f","observation_id":"0cdee8c1-9d52-4f8a-9f36-b939b85cd4b6","resolution":{"observed_at":"2026-08-07T11:22:12.294513Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06295","last_updated":"2016-01-07T18:43:03Z","snapshot_observed_at":"2026-07-06T04:37:06.738855Z","submitted_at":"2015-11-19T18:38:47Z","title":"Policy Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06295","snapshot_observed_at":"2026-08-07T11:22:12.136807Z","title":"Rusu, Sergio Gomez Colmenarejo, C aglar G \\\" u l c ehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, and Raia Hadsell","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.136807Z"},"links":{"cited_paper":"/paper/1511.06295","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:3937e33ad731fb2b367c7b9255468fd7909aed6ce29fa655455e1b524fbcc237","observation_id":"60daa1b4-3e28-40c1-94fc-ffb681da7ae3","resolution":{"observed_at":"2026-08-07T11:22:12.136807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-07T11:22:12.142290Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.142290Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:0df4ad53935f37e9c673d919322a15d4b51aa4909d77e5e8dd100121d5654f62","observation_id":"11e0e02d-e09d-4154-ae2b-520dfbb0b25f","resolution":{"observed_at":"2026-08-07T11:22:12.142290Z","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":"10.1007/978-3-540-92910-9_32","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.268901Z","title":null,"venue":null,"work_id":"4f2781be-8614-4818-baa5-b7177c6042ca","year":2012},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.147941Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:dcd83c9e8ba3ca203ac3193b445b3050434cff095021b9454762d980e68233e8","observation_id":"76e417fe-20a9-4866-bc0c-08dba7d9d4fa","resolution":{"observed_at":"2026-08-07T11:22:12.277715Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.153426Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.153426Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:f43d2dc5cef76be35b43313689d302653e908019be401403af8659cc9bdcb614","observation_id":"387628c5-e65f-4168-9beb-a1827e040875","resolution":{"observed_at":"2026-08-07T11:22:12.153426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.12238","last_updated":"2019-09-26T16:34:22Z","snapshot_observed_at":"2026-07-31T01:38:27.388070Z","submitted_at":"2019-09-26T16:34:22Z","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.12238","snapshot_observed_at":"2026-08-07T11:22:12.160191Z","title":"Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg, Aidan Clark, Hubert Soyer, Jack W","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.160191Z"},"links":{"cited_paper":"/paper/1909.12238","citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:ded6fef3c5cc7e814861914c312b1eaeda94f104a250073755044a1af3c2b022","observation_id":"51e6b5d6-6b16-4642-8a87-d472fa8029d2","resolution":{"observed_at":"2026-08-07T11:22:12.160191Z","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":"10.7551/mitpress/2887.003.0035","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.237225Z","title":"Adapting Crossover in Evolutionary Algorithms","venue":null,"work_id":"f65072e6-2a2d-4e2f-afda-1e63cdea1f7a","year":1995},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.166562Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:8fcab75ba17fb31ac89a2024913ea7c947f1b76eac0e3cd380c67c9c78022c44","observation_id":"bfb20547-870a-4469-9b27-cb9fd12c7e77","resolution":{"observed_at":"2026-08-07T11:22:12.244917Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.171604Z","title":"Sutton and Andrew G","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.171604Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:9344e7fbddca5eff0cf9820ff33b2948aeb375b5a5407171942dc09d6d8c909f","observation_id":"2a3e4fe4-b97e-4b1d-a182-dfb90cf35ea5","resolution":{"observed_at":"2026-08-07T11:22:12.171604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.651209Z","title":"Ball, Vu Nguyen, Binxin Ru, and Michael Osborne","venue":null,"work_id":"8df36b2e-dd9f-48dc-8161-7822f310a97d","year":2022},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.176950Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:4bd7815be876406e33d0306602a9ead017d62d0284e81cc55117efe608ad5981","observation_id":"e7fb554d-1622-48cb-8b00-3ee226a28729","resolution":{"observed_at":"2026-08-07T11:22:12.656346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"file/2715518","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.484105Z","title":"Meta-gradient reinforcement learning","venue":null,"work_id":"5d9e9409-df51-4a39-a997-d31b72ace022","year":2018},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.181959Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:194fcebeef691069ffceb578fd163a9194d3bad4be2bfb2d3f51b6c0b7b52588","observation_id":"0ad8d103-808f-494b-b1fc-392a78be557a","resolution":{"observed_at":"2026-08-07T11:22:12.492116Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:22:12.634194Z","title":"On the importance of hyperparameter optimization for model-based reinforcement learning","venue":null,"work_id":"b6b9aedc-745d-4a3f-bc63-9cb8fdbdbe12","year":2021},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.186527Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:b8c0312519591ff111206130473c8e906ecf7d63c23cf7c3c5834e0f95760791","observation_id":"6a90400e-f386-479e-b627-0947d4a4976d","resolution":{"observed_at":"2026-08-07T11:22:12.640169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:22:12.191394Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T11:22:12.191394Z"},"links":{"citing_paper":"/paper/2506.03225"},"observation_digest":"sha256:88a6ce9034df9f6faf812fba382a686a7ec4f6c0673ec548bd630cee2fca6f22","observation_id":"07d74611-f451-42cc-bcea-cf63da2eab88","resolution":{"observed_at":"2026-08-07T11:22:12.191394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.03225","last_updated":"2025-07-17T15:41:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T16:37:13.864952Z","submitted_at":"2025-06-03T11:19:21Z","title":"Multiple-Frequencies Population-Based Training"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":5,"verified_fuzzy":14},"total_outbound_references":32},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2506.03225."}