{"as_of":"2026-08-07T20:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a44494cde7bdc910bb1b2baaed4ae6854563db6d023c55f0069b47e825a256a1","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":30,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:17:09.819888Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T15:28:33.717389Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2408.00724","last_updated":"2025-03-03T07:53:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-01T17:16:04Z","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","version":3},"reference_index":216,"source":"arxiv_source","source_observed_at":"2026-05-18T06:38:36.517935Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2408.00724"},"observation_digest":"sha256:b7cabcaffe4537fc0929968fde583d9797e74cc2a0709d7c25032885dd875b33","observation_id":"d0e3a020-507a-4332-8f87-59ab87356012","resolution":{"observed_at":"2026-05-18T06:38:36.987482Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2503.08223","last_updated":"2026-04-09T15:28:27Z","snapshot_observed_at":"2026-07-06T20:50:33.513259Z","submitted_at":"2025-03-11T09:41:29Z","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","version":3},"reference_index":129,"source":"pdf_text","source_observed_at":"2026-05-23T01:03:26.037233Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2503.08223"},"observation_digest":"sha256:d69c7bab8e654f225a6e4cd9d51191df1dac7f96568782be1934a693e10230ed","observation_id":"b13a467c-9342-4bdb-9aea-d8d80f2f5fdc","resolution":{"observed_at":"2026-05-23T01:05:16.470471Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-07T11:17:09.819888Z","title":"https://arxiv.org/abs/2007.05558","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.02965","last_updated":"2025-06-04T05:38:31Z","snapshot_observed_at":"2026-08-07T11:09:27.978189Z","submitted_at":"2025-06-03T15:00:18Z","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:09.819888Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2506.02965"},"observation_digest":"sha256:60e750fba79dac99b25c69ff66a289557721e37ffff48bbc0a8f270174bfbfef","observation_id":"79bba974-e0e5-431f-b7fd-71a4374c9c40","resolution":{"observed_at":"2026-08-07T11:17:09.819888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-07T05:47:28.633115Z","title":"The com- putational limits of deep learning,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.07055","last_updated":"2025-06-08T09:30:48Z","snapshot_observed_at":"2026-08-07T05:40:43.749738Z","submitted_at":"2025-06-08T09:30:48Z","title":"A Layered Self-Supervised Knowledge Distillation Framework for Efficient Multimodal Learning on the Edge","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.633115Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2506.07055"},"observation_digest":"sha256:d8a7c731b3fe134afe5cf19300c6cba0af6ac6930dedab9b8e05cf6c5d78bd8b","observation_id":"d6364922-7944-43b4-8150-93649e230f69","resolution":{"observed_at":"2026-08-07T05:47:28.633115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-06T21:43:58.136260Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23505","last_updated":"2025-06-30T04:06:50Z","snapshot_observed_at":"2026-08-06T21:37:52.152974Z","submitted_at":"2025-06-30T04:06:50Z","title":"Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:43:58.136260Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2506.23505"},"observation_digest":"sha256:a82be61528b851a27cf7876a8187e7f8ab77cc2982803f65aeae812140424c35","observation_id":"f7729bdb-4615-4be6-968f-cc40d85ef720","resolution":{"observed_at":"2026-08-06T21:43:58.136260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-06T21:27:28.207329Z","title":"The computational limits of deep learning","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2507.00195","last_updated":"2025-06-30T19:06:02Z","snapshot_observed_at":"2026-08-06T21:19:32.997766Z","submitted_at":"2025-06-30T19:06:02Z","title":"What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness","version":1},"reference_index":143,"source":"pdf_text","source_observed_at":"2026-08-06T21:27:28.207329Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2507.00195"},"observation_digest":"sha256:967bdb3a0f9150b0fd836ae1cbcc9ebf2b238eca420be82ed158b15b46e1aa23","observation_id":"c8e8b453-f358-4ffa-85dc-21df1caf72b3","resolution":{"observed_at":"2026-08-06T21:27:28.207329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-06T21:16:48.484743Z","title":", author Greenewald, K","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.12473","last_updated":"2025-07-01T09:13:10Z","snapshot_observed_at":"2026-08-07T18:29:13.661443Z","submitted_at":"2025-07-01T09:13:10Z","title":"The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-06T21:16:48.484743Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2507.12473"},"observation_digest":"sha256:58d0927d0ab9b8245966ebd962c27f07dc552a7563d580075ced6088cec84177","observation_id":"f3f1cd75-366b-479f-8577-9628bfa7e720","resolution":{"observed_at":"2026-08-06T21:16:48.484743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-06T15:48:43.070761Z","title":"We proved that the system's state space is bounded, and that its trajectories either converge to a unique positive fixed point or recurrently return to its neighborhood","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.22916","last_updated":"2025-07-20T15:34:47Z","snapshot_observed_at":"2026-08-06T15:40:36.610964Z","submitted_at":"2025-07-20T15:34:47Z","title":"From Propagator to Oscillator: The Dual Role of Symmetric Differential Equations in Neural Systems","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:48:43.070761Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2507.22916"},"observation_digest":"sha256:d9a5da466f2bcb4a58fb3f0198e5beb832b96f2f0977f485b19d8891f5a56ff8","observation_id":"d88ea417-a9ee-420b-83fd-832e7eb26fff","resolution":{"observed_at":"2026-08-06T15:48:43.070761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-05T22:14:24.094193Z","title":"Thompson et al.The Computational Limits of Deep Learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.07423","last_updated":"2025-09-06T20:47:36Z","snapshot_observed_at":"2026-08-07T11:28:34.123474Z","submitted_at":"2025-08-10T16:45:10Z","title":"Real-Time Analysis of Unstructured Data with Machine Learning on Heterogeneous Architectures","version":3},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-05T22:14:24.094193Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2508.07423"},"observation_digest":"sha256:88039cfcb0f3b7880a327524ec500ea3b5fa35729167c0709f270c2a458eb23f","observation_id":"e4d9741d-a37f-4be2-831a-02ed8123e63c","resolution":{"observed_at":"2026-08-05T22:14:24.094193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-05T21:47:23.819767Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.08011","last_updated":"2025-08-11T14:15:33Z","snapshot_observed_at":"2026-08-05T21:47:17.147161Z","submitted_at":"2025-08-11T14:15:33Z","title":"Progressive Depth Up-scaling via Optimal Transport","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T21:47:23.819767Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2508.08011"},"observation_digest":"sha256:cc574e527a870b959cee2602e85c5510f0cc57ea1d9b9bed81a6f5dfd9fe126a","observation_id":"69aba07d-1ebd-47ff-bc73-3ab3df3f82e4","resolution":{"observed_at":"2026-08-05T21:47:23.819767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2509.06086","last_updated":"2026-04-23T04:42:10Z","snapshot_observed_at":"2026-08-03T02:53:10.085379Z","submitted_at":"2025-09-07T15:00:55Z","title":"From Membership-Privacy Leakage to Quantum Machine Unlearning","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-18T18:08:00.127348Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2509.06086"},"observation_digest":"sha256:ed5ed2e4b5faf855a0bcbb165da1134b27ca8f3110d237b5190605081c8ed453","observation_id":"b411fca5-ae1f-4bab-8e99-66b2a2dc322a","resolution":{"observed_at":"2026-05-18T18:11:42.865600Z","resolver_source":"arxiv_id","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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-03T23:25:20.674421Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.06167","last_updated":"2026-07-30T18:27:51Z","snapshot_observed_at":"2026-08-07T14:27:06.179404Z","submitted_at":"2025-11-09T00:11:44Z","title":"Quantum optical neural networks using atom-cavity interactions to provide all-optical nonlinearity","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T23:25:20.674421Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2511.06167"},"observation_digest":"sha256:9e60261732d256ed9e57e33c58fb0461f6ca95d71f46acc677e7e93fcfe40cd8","observation_id":"6feddc30-0839-4794-8b61-1f0c0c621921","resolution":{"observed_at":"2026-08-03T23:25:20.674421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2512.03915","last_updated":"2026-04-26T06:30:03Z","snapshot_observed_at":"2026-07-06T22:37:41.555068Z","submitted_at":"2025-12-03T16:00:02Z","title":"A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-17T02:16:48.422647Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2512.03915"},"observation_digest":"sha256:a5a8628494376514d8b76d0d237afb495c5d0bc0a982774accb6b66468475fe9","observation_id":"23f9bfe9-0cca-4e28-8b9f-c095360349f7","resolution":{"observed_at":"2026-05-17T02:18:52.587126Z","resolver_source":"arxiv_id","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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-03T11:32:57.395221Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.06315","last_updated":"2026-06-22T11:12:51Z","snapshot_observed_at":"2026-08-07T14:23:40.170125Z","submitted_at":"2026-01-09T21:18:01Z","title":"Koopman Model Dimension Reduction via Variational Bayesian Inference and Graph Search","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T11:32:57.395221Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2601.06315"},"observation_digest":"sha256:e6b0c3e0f9fd525b736abe22ee4e0a4c5e0f0de2c77be92f85ea3731a393f873","observation_id":"e4737932-7c50-47e6-87b2-256fd23806ae","resolution":{"observed_at":"2026-08-03T11:32:57.395221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-08-03T03:40:35.559151Z","title":"Thompson, K","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.07518","last_updated":"2026-06-29T11:45:40Z","snapshot_observed_at":"2026-08-07T08:32:30.278157Z","submitted_at":"2026-02-07T12:33:11Z","title":"Physical Analogue Kolmogorov-Arnold Networks based on Reconfigurable Nonlinear-Processing Units","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T03:40:35.559151Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2602.07518"},"observation_digest":"sha256:c6c80803b66d00c0b8cf3d68d7589dd94860bf14c3a09ff079ac391a50f8e4a6","observation_id":"14c9143d-e924-42d0-a111-74ec3311827d","resolution":{"observed_at":"2026-08-03T03:40:35.559151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2602.07618","last_updated":"2026-05-18T17:38:17Z","snapshot_observed_at":"2026-07-06T22:45:00.816348Z","submitted_at":"2026-02-07T16:52:38Z","title":"Neural Networks With Dense Weights Are Not Universal Approximators","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-16T06:05:00.489175Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2602.07618"},"observation_digest":"sha256:1a56444134a241dcf83957ace244bd4bf95764aed5225aab441ab7a5cb63f1eb","observation_id":"5146e170-c082-46a0-9544-4ae5d04609ff","resolution":{"observed_at":"2026-05-16T06:07:25.745442Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2602.07618","last_updated":"2026-05-18T17:38:17Z","snapshot_observed_at":"2026-07-06T22:45:00.816348Z","submitted_at":"2026-02-07T16:52:38Z","title":"Neural Networks With Dense Weights Are Not Universal Approximators","version":6},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T13:33:18.852149Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2602.07618"},"observation_digest":"sha256:cee1e3ad748d04d95e3dd7111f2702fa177a3df6901614df8a5efc82e93c44d7","observation_id":"75a8d5dd-08d4-4767-a23b-296a37d6806c","resolution":{"observed_at":"2026-05-21T13:34:11.296683Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2604.04483","last_updated":"2026-04-06T07:14:19Z","snapshot_observed_at":"2026-07-06T22:53:29.118925Z","submitted_at":"2026-04-06T07:14:19Z","title":"STRIDe: Cross-Coupled STT-MRAM Enabling Robust In-Memory-Computing for Deep Neural Network Accelerators","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T19:54:26.119428Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2604.04483"},"observation_digest":"sha256:7cda2c5b515b6780dc1d2a543b4ea55f1d00c054b62b85c6dc2f742813a43d0c","observation_id":"cc3268e0-348e-40a1-9839-b318f543baf2","resolution":{"observed_at":"2026-05-10T22:25:50.296597Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2604.06323","last_updated":"2026-04-09T08:31:16Z","snapshot_observed_at":"2026-08-05T11:56:20.326339Z","submitted_at":"2026-04-07T18:00:40Z","title":"Blockchain and AI: Securing Intelligent Networks for the Future","version":2},"reference_index":131,"source":"pdf_text","source_observed_at":"2026-05-10T18:52:23.255538Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2604.06323"},"observation_digest":"sha256:89a4b372de3406cf68bf7e5f58b5f22892f13afd6f64daa905ec54bdc7ec0de6","observation_id":"ef3341d6-2796-4a11-9266-b402456b10c8","resolution":{"observed_at":"2026-05-10T23:45:53.578410Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2604.20629","last_updated":"2026-04-22T14:44:31Z","snapshot_observed_at":"2026-07-06T23:07:14.243878Z","submitted_at":"2026-04-22T14:44:31Z","title":"Rates of forgetting for the sequentially Markov coalescent","version":1},"reference_index":152,"source":"arxiv_source","source_observed_at":"2026-05-09T22:49:51.753832Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2604.20629"},"observation_digest":"sha256:72c8e5bc77318b80ba12d8899854e894d965e427cb7329cf83b7998e8c55df99","observation_id":"dd54ee20-56a2-4a9b-8ee4-7400c5923dbd","resolution":{"observed_at":"2026-05-09T22:54:16.670537Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2604.23108","last_updated":"2026-04-28T02:47:36Z","snapshot_observed_at":"2026-07-06T23:09:23.591544Z","submitted_at":"2026-04-25T02:05:56Z","title":"Mixture of Heterogeneous Grouped Experts for Language Modeling","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-08T08:28:20.057361Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2604.23108"},"observation_digest":"sha256:0626442982343097509ccfef547b34e52f0377396bb81bd8623e515fab3ae4e4","observation_id":"b6a6a210-f62a-49c5-8219-1587f624ff08","resolution":{"observed_at":"2026-05-11T20:36:10.972556Z","resolver_source":"arxiv_id","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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2604.26507","last_updated":"2026-04-29T10:12:58Z","snapshot_observed_at":"2026-07-06T23:12:10.599132Z","submitted_at":"2026-04-29T10:12:58Z","title":"Auto-Relational Reasoning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-07T10:44:33.079246Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2604.26507"},"observation_digest":"sha256:514315cfc64c08c101052986b3c024a2d6dcfb2443da441216a4673896994296","observation_id":"defa1ef1-fb75-426a-ad2b-3ed17c01601b","resolution":{"observed_at":"2026-05-12T09:31:25.702337Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2605.03241","last_updated":"2026-05-20T21:45:30Z","snapshot_observed_at":"2026-08-02T11:22:49.791704Z","submitted_at":"2026-05-05T00:19:38Z","title":"OptiLookUp: An Optical ROM-Based Lookup Table Engine for Photonic Accelerators","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-07T15:29:24.702678Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2605.03241"},"observation_digest":"sha256:e6baaade053f861259d8bf41249fb62e58d4ba8a98fcc9c952cda185571efb08","observation_id":"31482d30-ab35-42af-aba9-e7f26fa7ef84","resolution":{"observed_at":"2026-05-12T00:21:22.336150Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2605.03241","last_updated":"2026-05-20T21:45:30Z","snapshot_observed_at":"2026-08-02T11:22:49.791704Z","submitted_at":"2026-05-05T00:19:38Z","title":"OptiLookUp: An Optical ROM-Based Lookup Table Engine for Photonic Accelerators","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-22T10:52:29.434656Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2605.03241"},"observation_digest":"sha256:2011feb515a12190f61ed044f4e34e04fdfc50e7761effff1a3d088b262fb263","observation_id":"408a4169-80df-4af6-8200-39480f55b93d","resolution":{"observed_at":"2026-05-22T10:54:47.863023Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2605.11733","last_updated":"2026-05-12T08:15:04Z","snapshot_observed_at":"2026-07-06T23:23:30.499023Z","submitted_at":"2026-05-12T08:15:04Z","title":"Position: LLM Inference Should Be Evaluated as Energy-to-Token Production","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-13T05:17:24.147248Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2605.11733"},"observation_digest":"sha256:35cdb6cbf71a737258975d1068e5da60b2cf012809059ebccec8d1b698060cf2","observation_id":"2441701d-2c7f-4d98-aa6a-46c32420ff9f","resolution":{"observed_at":"2026-05-13T05:27:19.408590Z","resolver_source":"arxiv_id","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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2605.23051","last_updated":"2026-05-21T21:33:59Z","snapshot_observed_at":"2026-07-06T23:33:19.375527Z","submitted_at":"2026-05-21T21:33:59Z","title":"General-Purpose Photonic Computing Primitive for Contemporary Artificial Intelligence","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-25T05:06:13.575675Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2605.23051"},"observation_digest":"sha256:6b743550725581a890989e64fcb15fc6c7a791a98eb5cf9b60f703939220370b","observation_id":"5f944148-e103-4679-a6e2-1f4cecdb750d","resolution":{"observed_at":"2026-05-25T05:06:38.219710Z","resolver_source":"arxiv_id","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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2605.23656","last_updated":"2026-05-22T14:08:22Z","snapshot_observed_at":"2026-08-03T05:35:58.265801Z","submitted_at":"2026-05-22T14:08:22Z","title":"Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-25T04:44:42.434712Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2605.23656"},"observation_digest":"sha256:5381b1cd99da82a81e94497489a107f7370c8861860ec54d5b6b5db342cdfaa0","observation_id":"eb058f75-5394-48d5-8480-2bbf2a6898e1","resolution":{"observed_at":"2026-05-25T04:45:20.016621Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2606.10969","last_updated":"2026-06-20T08:01:59Z","snapshot_observed_at":"2026-07-06T23:50:06.645076Z","submitted_at":"2026-06-09T15:11:52Z","title":"A Functional Data Framework For Analyzing Shapes and Textures in Images","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-27T12:21:09.703003Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2606.10969"},"observation_digest":"sha256:78ccbf6c0ccac62a5177ac394c9435b7c63995ab8baa3efe83105497d32c5943","observation_id":"e51182af-f5da-456d-9833-6836ab5ec566","resolution":{"observed_at":"2026-07-03T06:57:43.377663Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":"2007.05558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-03T15:28:33.717389Z","title":"and Manso, G.F","venue":null,"work_id":"51dd45a4-6247-4e57-baac-e78856de99cf","year":2007},"citing_paper":{"arxiv_id":"2607.02158","last_updated":"2026-07-02T13:31:29Z","snapshot_observed_at":"2026-08-07T04:20:08.981474Z","submitted_at":"2026-07-02T13:31:29Z","title":"Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-03T15:21:11.367562Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2607.02158"},"observation_digest":"sha256:13c79898c866915321e5c1ff191c891d91c71f7ecdd106970ef38000fa7fbe8a","observation_id":"4d6c1b03-6e73-4f7b-8439-f55a930e15c2","resolution":{"observed_at":"2026-07-03T15:28:33.718862Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2007.05558","last_updated":"2022-07-27T17:26:18Z","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05558","snapshot_observed_at":"2026-07-31T01:02:43.793258Z","title":"Thompson and Kristjan H","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25107","last_updated":"2026-07-27T22:09:46Z","snapshot_observed_at":"2026-08-03T10:00:54.967586Z","submitted_at":"2026-07-27T22:09:46Z","title":"MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics","version":1},"reference_index":233,"source":"arxiv_source","source_observed_at":"2026-07-31T01:02:43.793258Z"},"links":{"cited_paper":"/paper/2007.05558","citing_paper":"/paper/2607.25107"},"observation_digest":"sha256:45f1221953478a0ef68a5783a80fc880ce1fd27ba7633d527f5d5412d94a7dc4","observation_id":"238c3819-bd33-48c5-8c67-ca3b5db61beb","resolution":{"observed_at":"2026-07-31T01:02:43.793258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2007.05558/citation-record","integrity":"/paper/2007.05558/integrity","json":"/paper/2007.05558/citation-record.json","paper":"/paper/2007.05558"},"outbound":[],"paper":{"arxiv_id":"2007.05558","last_updated":"2022-07-27T17:26:18Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:39:38.269667Z","submitted_at":"2020-07-10T18:26:17Z","title":"The Computational Limits of Deep Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 30 inbound Pith citation observations for arXiv:2007.05558."}