{"as_of":"2026-08-08T03:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8fe1dc1ce1e63378dc66046ae5a9ff5eee7ab2df6b1bc98e9145795f8d0daeff","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T22:29:41.042742Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"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/2607.15745/citation-record","integrity":"/paper/2607.15745/integrity","json":"/paper/2607.15745/citation-record.json","paper":"/paper/2607.15745"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:29:38.079080Z","title":"Review of deep learning: concepts, convolutional neural network architectures, challenges, and applications,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.079080Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:ce4aab4019e6773fc761730fb12d2467e67321786d49acce0d6e97d0e2289ebc","observation_id":"66c80e04-4e28-4da4-a5ee-fd2e7c0feb0b","resolution":{"observed_at":"2026-08-01T22:29:38.079080Z","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":"2026-08-01T22:29:38.162105Z","title":"A formal basis for the heuristic determination of minimum cost paths,","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.162105Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:ad85d2159d5eff24e9f8c9a08e847fc3f9a6aae352b1cb0d5ea02aee489fbb1d","observation_id":"f3f71524-1877-4c91-92fc-c940def3138c","resolution":{"observed_at":"2026-08-01T22:29:38.162105Z","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":"2026-08-01T22:29:38.231204Z","title":"A Systematic Literature Review of A* Pathfinding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.231204Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:97b8d5b3985548c672ed5dbef7d90d368608b8fd83ff43d31d195922a7221413","observation_id":"3ca67bea-7595-4f9b-83f7-43bdc45d2d1c","resolution":{"observed_at":"2026-08-01T22:29:38.231204Z","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":"2026-08-01T22:29:38.287515Z","title":"MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.287515Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:0d56ae20bc8486130c1a38346b7a5b92ceeb0d3cd42f2563293193dab94e7c29","observation_id":"375894d6-6365-480e-9195-8ddc0d2a0427","resolution":{"observed_at":"2026-08-01T22:29:38.287515Z","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":"2026-08-01T22:29:38.378581Z","title":"Curriculum Learning,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.378581Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:aed0d5a444b00c57fee04b76282e2101c8294f09fff9054a38fc6a6ce94d2568","observation_id":"a4a7f93f-4c0b-43aa-bd18-28563848bde8","resolution":{"observed_at":"2026-08-01T22:29:38.378581Z","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":"2026-08-01T22:29:38.496271Z","title":"Self-Paced Learning for Latent Variable Models,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.496271Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:2f4e0810648047c01569146c0b63fc7be2213d72b422a0ad37e43fff1efb4404","observation_id":"748dee43-ba2b-47d9-aebb-5dd35b0ef823","resolution":{"observed_at":"2026-08-01T22:29:38.496271Z","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":"2026-08-01T22:29:38.759902Z","title":"Training Region-Based Object Detectors with Online Hard Example Mining,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.759902Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:61f399ce61cb0bef512264450a9b22753932cf4e4bc6bcf539a0477c0589ea81","observation_id":"4626fb54-7803-4644-8c3b-ee9b991aafc3","resolution":{"observed_at":"2026-08-01T22:29:38.759902Z","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":"2026-08-01T22:29:38.932374Z","title":"Focal Loss for Dense Object Detection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:38.932374Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:918853d786bd18a5268e3ab100a0aff993fa4f8efe374abce9784c73df5fbd9a","observation_id":"90f97955-e1cf-47a7-8ec4-1330d7e0b603","resolution":{"observed_at":"2026-08-01T22:29:38.932374Z","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":"2026-08-01T22:29:39.149851Z","title":"Online Batch Selection for Faster Train- ing of Neural Networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.149851Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:252645c5a3567d29569a19a4ca045ab2197c738b7ffdbdc26117c6a7f92d995a","observation_id":"bc2976be-6c76-47b1-9b52-8816671b610b","resolution":{"observed_at":"2026-08-01T22:29:39.149851Z","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":"2026-08-01T22:29:39.348930Z","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.348930Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:8fe11d054d8a0f377eec21a906864ca0327d3da8758436e76dc92f9d75602245","observation_id":"c627ee1f-b24c-4b6c-9480-c65a0b6a7333","resolution":{"observed_at":"2026-08-01T22:29:39.348930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13871","last_updated":"2024-06-19T22:28:18Z","snapshot_observed_at":"2026-07-06T18:33:54.443005Z","submitted_at":"2024-06-19T22:28:18Z","title":"Robust Time Series Forecasting with Non-Heavy-Tailed Gaussian Loss-Weighted Sampler","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13871","snapshot_observed_at":"2026-08-01T22:29:39.518783Z","title":"Ro- bust Time Series Forecasting with Non-Heavy-Tailed Gaussian Loss- Weighted Sampler,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.518783Z"},"links":{"cited_paper":"/paper/2406.13871","citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:fcb4ea9b2009be50849f03f7c17874752504f1c8346f6ad7e107d0fde733f06c","observation_id":"4a342d2b-3974-4d4f-a799-c736571612f4","resolution":{"observed_at":"2026-08-01T22:29:39.518783Z","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":"2026-08-01T22:29:39.604067Z","title":"An empirical study of example forgetting during deep neural network learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.604067Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:7bbde3b612cc392969bc5188201c6cc7730be004f4d0a7a9648fc1d7dea66e0a","observation_id":"61d7d239-12fe-4769-b0b0-4a42240eaea9","resolution":{"observed_at":"2026-08-01T22:29:39.604067Z","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":"2026-08-01T22:29:39.742287Z","title":"Beyond neural scaling laws: Beating power law scaling via data pruning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.742287Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:28f684276e293e7703c07bbf0e6618afe59e9d749ab8fce50661acbf04ecfe86","observation_id":"24ae0dc6-336d-4189-b354-d86122170d6c","resolution":{"observed_at":"2026-08-01T22:29:39.742287Z","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":"2026-08-01T22:29:39.880219Z","title":"Prioritized training on points that are learnable,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:39.880219Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:55aadf99cc94461104c1c37a2784227ae1445e91cde7eb37cc71adf7e7ac573f","observation_id":"a1667388-7035-4c18-bb0e-ec80be7f4393","resolution":{"observed_at":"2026-08-01T22:29:39.880219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04947","last_updated":"2023-10-20T04:38:34Z","snapshot_observed_at":"2026-07-06T15:00:24.620138Z","submitted_at":"2023-03-08T23:40:47Z","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.04947","snapshot_observed_at":"2026-08-01T22:29:40.050893Z","title":"InfoBatch: Lossless Train- ing Speed Up by Unbiased Dynamic Data Pruning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.050893Z"},"links":{"cited_paper":"/paper/2303.04947","citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:a70a929cd810817340f0cf93860f1295139d13c9b64d06d28d0db884a572f9c6","observation_id":"03e26409-0670-4bd3-ba20-6d1819113de9","resolution":{"observed_at":"2026-08-01T22:29:40.050893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.08499","last_updated":"2022-06-29T11:33:48Z","snapshot_observed_at":"2026-08-05T20:16:31.473274Z","submitted_at":"2022-04-18T18:14:30Z","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.08499","snapshot_observed_at":"2026-08-01T22:29:40.239890Z","title":"DeepCore: A comprehensive library for coreset selection in deep learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.239890Z"},"links":{"cited_paper":"/paper/2204.08499","citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:598f634396ae4ba9322eacaf67110fc703aed2d919d8d6ec6ac7067ab84d596a","observation_id":"41deb0ca-c918-4b8c-8cec-e9cf874ec817","resolution":{"observed_at":"2026-08-01T22:29:40.239890Z","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":"2026-08-01T22:29:40.395308Z","title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.395308Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:3a60507185ae7b1577466c8629a5f0c06874d421affe0b56d972bd872dfbd07c","observation_id":"d21ac4e8-8bc7-4ddc-9db6-ab37cee2e6c8","resolution":{"observed_at":"2026-08-01T22:29:40.395308Z","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":"2026-08-01T22:29:40.481246Z","title":"Lecture 6.5 — RMSProp,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.481246Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:0a05600896a16e3af1d8442cf6e77a07fb9eb996a1ad8a9f6eaed84d8d7fb654","observation_id":"1c4bd5a7-6c1f-43be-83ee-52da954a65c0","resolution":{"observed_at":"2026-08-01T22:29:40.481246Z","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":"2026-08-01T22:29:40.605633Z","title":"Adam: A Method for Stochastic Opti- mization,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.605633Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:13d86dd69d81446cd05ed04aa97ffec9f71328d814bbd02f9741bb4beda966b7","observation_id":"a813d9c7-14db-488b-a04f-315283359ebc","resolution":{"observed_at":"2026-08-01T22:29:40.605633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09820","last_updated":"2018-04-24T17:43:51Z","snapshot_observed_at":"2026-07-06T06:30:19.251357Z","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":"2026-08-01T22:29:40.726017Z","title":"A Disciplined Approach to Neural Network Hyperparameters: Part 1 – Learning Rate, Batch Size, Momentum, and Weight Decay,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.726017Z"},"links":{"cited_paper":"/paper/1803.09820","citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:e899f9225487283cfa3d8746c5667493099c646eab90be10ad7b4011eac09bbc","observation_id":"77ecc468-44c0-4851-9227-c9750ba300df","resolution":{"observed_at":"2026-08-01T22:29:40.726017Z","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":"2026-08-01T22:29:40.895382Z","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:40.895382Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:c59074cdd27507b1fb0b73ddab3a9de89c6e251941957d157b778ae91065d798","observation_id":"332e77b7-4572-4bce-b1ec-cd798007c88f","resolution":{"observed_at":"2026-08-01T22:29:40.895382Z","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":"2026-08-01T22:29:41.042742Z","title":"Deep Residual Learning for Image Recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:41.042742Z"},"links":{"citing_paper":"/paper/2607.15745"},"observation_digest":"sha256:64d44351a91e3bb825f875f1d60fc3353ef9b595ab3fa06665b299d33756e3f9","observation_id":"1c3013ea-a4eb-4533-a387-6af03cbb2257","resolution":{"observed_at":"2026-08-01T22:29:41.042742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.15745","last_updated":"2026-07-17T08:33:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T01:31:37.335722Z","submitted_at":"2026-07-17T08:33:43Z","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":22},"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 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.15745."}