{"as_of":"2026-08-16T20:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9443a1aafb79e3d79d29495c10a3a180a86d3f95874d964ef314356a666ae1a5","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:48:49.712385Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2412.08526/citation-record","integrity":"/paper/2412.08526/integrity","json":"/paper/2412.08526/citation-record.json","paper":"/paper/2412.08526"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.03051","last_updated":"2020-07-06T20:24:31Z","snapshot_observed_at":"2026-08-14T13:11:27.922295Z","submitted_at":"2020-07-06T20:24:31Z","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03051","snapshot_observed_at":"2026-08-11T17:48:49.108853Z","title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.108853Z"},"links":{"cited_paper":"/paper/2007.03051","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:aa8e75aea7eb32ee9d05a064e3b562b4664f4c550e4ce95fcbe20bfb7efe1418","observation_id":"a65da475-e332-44c6-a1ba-f048920849cf","resolution":{"observed_at":"2026-08-11T17:48:49.108853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.09821","last_updated":"2021-10-21T16:09:43Z","snapshot_observed_at":"2026-08-16T18:23:21.129969Z","submitted_at":"2021-05-20T15:13:30Z","title":"DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.09821","snapshot_observed_at":"2026-08-11T17:48:49.180830Z","title":"Dehb: Evolutionary hyperband for scalable, robust and efficient hyperparameter optimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.180830Z"},"links":{"cited_paper":"/paper/2105.09821","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:f448c58dce42163577022c0701a1c5a416d604c3c1f6268e59d4883e79ca4da8","observation_id":"78e0a7b6-3a52-46c1-93c7-002eebd7c02f","resolution":{"observed_at":"2026-08-11T17:48:49.180830Z","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":"2026-08-11T17:48:49.253509Z","title":"Random search for hyper-parameter optimization","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.253509Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:eacf720531fa59c0296fd330726251cbdd399332be09be416d16d1f92e1dc965","observation_id":"739545d4-14fe-4a4d-b423-3ab8cae4b4ce","resolution":{"observed_at":"2026-08-11T17:48:49.253509Z","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":"2026-08-11T17:48:49.259092Z","title":"Algorithms for hyper-parameter optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.259092Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:fa74c2216550a8142e45c2dd4411fd29a55dc1f4a527f1a0dadbbee3ba16f840","observation_id":"97d896c5-f90f-4683-a134-0a86de4a0613","resolution":{"observed_at":"2026-08-11T17:48:49.259092Z","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":"2026-08-11T17:48:49.264406Z","title":"Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.264406Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:b302dca65082406a59403404d6460dfdc3af79cecc331129e42320159420cae7","observation_id":"a8519998-dd87-4564-b5ee-3f0301f7ad5b","resolution":{"observed_at":"2026-08-11T17:48:49.264406Z","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":"2026-08-11T17:48:50.143582Z","title":"Evolution strategies--a comprehensive introduction","venue":null,"work_id":"9f717bc9-49e9-4b02-9eac-cc2100bb530e","year":2002},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.269704Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:a9fdd10e324d560ccbf592890a58f3f8e38be0a9da1263b4ea563a0e59479fb7","observation_id":"d87fd758-7732-40ff-81f9-a4ad585b5f4e","resolution":{"observed_at":"2026-08-11T17:48:50.149454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.05847","last_updated":"2021-11-24T22:40:27Z","snapshot_observed_at":"2026-08-16T18:10:28.868002Z","submitted_at":"2021-07-13T04:55:47Z","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.05847","snapshot_observed_at":"2026-08-11T17:48:49.275186Z","title":"Hyperparameter optimization: Foundations, algorithms, best practices and open challenges","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.275186Z"},"links":{"cited_paper":"/paper/2107.05847","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:12db7ef535ff5976b981f5f82076cdfbecaecc6b684beea039905bf08731b40e","observation_id":"c0b05f7c-bd39-4a7f-8eb9-90bd1b9f559b","resolution":{"observed_at":"2026-08-11T17:48:49.275186Z","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":"2026-08-11T17:48:50.128681Z","title":"Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms","venue":null,"work_id":"1c2debd9-e715-428a-b5f5-f910575c667b","year":2017},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.280625Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:49eebc3840d2eeb61bb51a52daaa9c2637339856bb3d3844fe481c172ab1ec8d","observation_id":"ef0c6d46-da9c-4812-a4fe-295241f67e45","resolution":{"observed_at":"2026-08-11T17:48:50.133039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.114400Z","title":"Eco2ai: carbon emissions tracking of machine learning models as the first step towards sustainable ai","venue":null,"work_id":"19f05efb-e31e-41e3-88ef-c753d3e9820d","year":2022},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.323385Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:0611b84b48eeff12abe8759be75a8ade3b43550907f9c8c841d07115f1702be9","observation_id":"83a424b9-f619-4f17-87a6-90fe51ded3f2","resolution":{"observed_at":"2026-08-11T17:48:50.119401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.098832Z","title":"Cloud carbon footprint","venue":null,"work_id":"0ab7a24a-f407-495c-83e4-4f4795a33d0d","year":2023},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.379775Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:5e062baf1032369983278978b0a0ecbb86abbb74d225de5de932fc7b37472438","observation_id":"61aedc8c-a450-4196-bbd6-9b4bf916d6ad","resolution":{"observed_at":"2026-08-11T17:48:50.103749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.084591Z","title":"Code carbon","venue":null,"work_id":"c466748f-c5be-4753-a673-d9993b5cae40","year":2023},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.394782Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:f4614751aeb26b4ed4ae96f366a86ef00a245c70d646737f16203b1c939b341f","observation_id":"e5c9b6a1-ef1d-4c5c-a004-6acbdca4b393","resolution":{"observed_at":"2026-08-11T17:48:50.088669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.068815Z","title":"The power of training: How different neural network setups influence the energy demand","venue":null,"work_id":"24a0aca3-75c5-4597-8ec6-72ea72615223","year":2024},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.399431Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:48a73bf1a439ff7266de4cdbd2ef6300d9267fce73927dbdc64697488dbecb1d","observation_id":"58e3a3e2-8222-4eed-bbed-6ff5bf87fdb4","resolution":{"observed_at":"2026-08-11T17:48:50.074425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.054280Z","title":"Control batch size and learning rate to generalize well: Theoretical and empirical evidence","venue":null,"work_id":"1941a92b-e94d-4783-9d60-94008affe9f4","year":2019},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.405084Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:5796da326c32995073ca4024cd910bee24f3b7c9df40f7d29ffc8c2ae3ce8052","observation_id":"74d9ba04-533f-4040-8d19-1570e691e7cf","resolution":{"observed_at":"2026-08-11T17:48:50.059048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:50.039331Z","title":"Towards the systematic reporting of the energy and carbon footprints of machine learning","venue":null,"work_id":"de197390-9e24-4c7a-b996-03567ecdf93d","year":2020},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.410891Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:43ec75d216d0792956b405cf86494deb3264386d2cb8ad74ae806190e944376c","observation_id":"f1fa5960-307e-4c1d-a825-8c7b52f537cb","resolution":{"observed_at":"2026-08-11T17:48:50.045238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.11527","last_updated":"2019-06-27T09:59:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-06-27T09:59:44Z","title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.11527","snapshot_observed_at":"2026-08-11T17:48:49.416309Z","title":"Hyp-rl: Hyperparameter optimization by reinforcement learning","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.416309Z"},"links":{"cited_paper":"/paper/1906.11527","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:1c87743968e421d36b59f97940ac474c1fdc03318064d2f957d8772538f0a5bf","observation_id":"607a18d0-f393-471e-a046-484399dd6b33","resolution":{"observed_at":"2026-08-11T17:48:49.416309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09700","last_updated":"2019-11-04T20:37:33Z","snapshot_observed_at":"2026-08-13T09:44:21.186377Z","submitted_at":"2019-10-21T23:57:32Z","title":"Quantifying the Carbon Emissions of Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.09700","snapshot_observed_at":"2026-08-11T17:48:49.470887Z","title":"Quantifying the carbon emissions of machine learning","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.470887Z"},"links":{"cited_paper":"/paper/1910.09700","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:6114d659ff39433ab5757e2c33d90dc6b209d90edbb6497bd273cd15460ec724","observation_id":"90240494-1df3-4fda-9732-cb8e9d7ff9cc","resolution":{"observed_at":"2026-08-11T17:48:49.470887Z","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":"2026-08-11T17:48:50.023349Z","title":"Green algorithms: quantifying the carbon footprint of computation","venue":null,"work_id":"681b1d6e-cdcb-4eb5-b4a9-21cf508169d2","year":2021},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.499359Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:b668d6b79215e1c332adc1ae2713411bce6715947485b94c1c5568af520459c9","observation_id":"a0196ced-a88b-4f28-8d4f-5ab89364cb10","resolution":{"observed_at":"2026-08-11T17:48:50.028892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.504720Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.504720Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:a10266310b4bbf2cbbe11ed9837e0bb55f67614a4c8d089038c552031696ffab","observation_id":"bfa21d38-159f-47b4-9dd4-6cf29708d7bc","resolution":{"observed_at":"2026-08-11T17:48:49.504720Z","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":"2026-08-11T17:48:49.998199Z","title":"Improving multi-fidelity optimization with a recurring learning rate for hyperparameter tuning","venue":null,"work_id":"d07f0c37-99b1-4e54-96a6-2746b213377e","year":2023},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.509539Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:e5a98f9b04c7f9dc6723138e1618e8c98f2f015afd9a112bb665a94d5389acf9","observation_id":"709b83cc-2465-4b99-aeeb-ff0f9bf7c45f","resolution":{"observed_at":"2026-08-11T17:48:50.003928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.514666Z","title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.514666Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:ebf18917f401746b9e4ae4e9942d2b1b724ca716e11db956c80e0454c9134e89","observation_id":"8ebe931d-e967-473e-bca2-d49f704d9ae2","resolution":{"observed_at":"2026-08-11T17:48:49.514666Z","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":"2026-08-11T17:48:49.974129Z","title":"A system for massively parallel hyperparameter tuning","venue":null,"work_id":"236712b5-8ff1-43fa-a6eb-ccce03659e98","year":2020},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.520310Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:1f863d1a57777fa6ee0546bafbcf34b08325a28407288138cc7756d30401c853","observation_id":"d6280390-b990-48cd-ae6a-e6f5d9a7dbbc","resolution":{"observed_at":"2026-08-11T17:48:49.978975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.958961Z","title":"A survey of methods for analyzing and improving gpu energy efficiency","venue":null,"work_id":"dc007a2f-91cf-4bf8-a21b-5fe2c7db4948","year":2014},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.561755Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:c841684f1cad7f78b9fbf43232539ef7aed657df4e7a4c22833d0b3af20894a1","observation_id":"cc695e88-b849-4688-a045-e5b52d191ca4","resolution":{"observed_at":"2026-08-11T17:48:49.963286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.942782Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"aded8442-a548-474f-a9df-0ed28ba32e1f","year":2019},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.668280Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:ec08032df650f75f9c34cead969279baab59d067c8692b2a2af9514dada94279","observation_id":"c4a48f33-5f98-40cd-a67c-4a5a817ee913","resolution":{"observed_at":"2026-08-11T17:48:49.949151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-08-16T05:11:57.545339Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-11T17:48:49.674480Z","title":"Carbon emissions and large neural network training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.674480Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:2d7c345bc94acaae5fe549fd481661f4ad389dd1b4d34bad7b5dac1bff827205","observation_id":"8b4c32ff-8a7a-4eed-ab39-5acdcb009dc1","resolution":{"observed_at":"2026-08-11T17:48:49.674480Z","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":"2026-08-11T17:48:49.926902Z","title":"Cyclical learning rates for training neural networks","venue":null,"work_id":"546b830c-b8ce-49f4-976c-873139431610","year":2017},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.680044Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:abd9dd17ad209f6d561cfe9fbfaef6541234ee8f783484b3eac7811888d0e830","observation_id":"6339949e-50a6-4ef0-aca6-efbb9faef79b","resolution":{"observed_at":"2026-08-11T17:48:49.931872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09820","last_updated":"2018-04-24T17:43:51Z","snapshot_observed_at":"2026-08-14T19:32:15.430767Z","submitted_at":"2018-03-26T20:05:59Z","title":"A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.09820","snapshot_observed_at":"2026-08-11T17:48:49.686467Z","title":"A disciplined approach to neural network hyper-parameters: Part 1--learning rate, batch size, momentum, and weight decay","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.686467Z"},"links":{"cited_paper":"/paper/1803.09820","citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:e076cb80f6b4f03d831b8924589dff5822035318efb6d6e33aa4ad57e3fe35d2","observation_id":"d93d9d62-f7ae-4771-85a9-ec5964fc4a4c","resolution":{"observed_at":"2026-08-11T17:48:49.686467Z","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":"2026-08-11T17:48:49.691883Z","title":"Practical bayesian optimization of machine learning algorithms","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.691883Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:09393c71e98f9c25347647507fbb134f2ebef894514db0beb0afb2174764eb4c","observation_id":"8792fc10-1f5e-454f-a378-014fad0ba473","resolution":{"observed_at":"2026-08-11T17:48:49.691883Z","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":"2026-08-11T17:48:49.899096Z","title":"Supervising the multi-fidelity race of hyperparameter configurations","venue":null,"work_id":"9c90ba95-be2f-49c1-84fb-cc3fe036ad24","year":2022},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.696216Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:686d3f93599c13c302211a810f1e90518daba2dff416e36676a8565b1e8781e6","observation_id":"7367ee74-f1bd-41ba-bbab-9a66d1350db9","resolution":{"observed_at":"2026-08-11T17:48:49.905150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.884473Z","title":"Hyperparameter optimization through context-based meta-reinforcement learning with task-aware representation","venue":null,"work_id":"4bcf5990-65ac-40ec-94e0-12f7dee8718a","year":2023},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.702237Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:89d014f959f620b165b64014b9ddf38460e6b10ec277b547c746f582de42e6d9","observation_id":"e4fcd618-aa63-4605-8d00-fec3919f7dbf","resolution":{"observed_at":"2026-08-11T17:48:49.888866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.866898Z","title":"Zeus: Understanding and optimizing \\ GPU \\ energy consumption of \\ DNN \\ training","venue":null,"work_id":"ddbc9ac3-7210-478e-9625-5fe15c95a571","year":2023},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.707192Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:2802637ba91bbc9bca6924843b6da05d04d293a068379548b5a40b58604bbc42","observation_id":"032ac3cc-f21c-4a54-84c1-524e2c799efe","resolution":{"observed_at":"2026-08-11T17:48:49.873639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T17:48:49.712385Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:49.712385Z"},"links":{"citing_paper":"/paper/2412.08526"},"observation_digest":"sha256:9d1ec1f876b52804f3303f93fd6b6921b93ac8415fe33e44e75f56a67125eae6","observation_id":"e2d99835-f8e9-4895-b518-6e991f00a243","resolution":{"observed_at":"2026-08-11T17:48:49.712385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.08526","last_updated":"2024-12-11T16:37:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T09:46:12.207991Z","submitted_at":"2024-12-11T16:37:44Z","title":"Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":17},"total_outbound_references":31},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2412.08526."}