{"as_of":"2026-08-19T02:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:58b3571516b96f8b2681fe3bf32c2d13bc2d86294ba680d6f404144a8ac64ead","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":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:02:16.463283Z","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":"2026-07-04T14:59:55.532477Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-08-11T17:42:15.075194Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommenda- tions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.17830","last_updated":"2024-12-11T19:00:00Z","snapshot_observed_at":"2026-08-18T01:24:11.995952Z","submitted_at":"2024-12-11T19:00:00Z","title":"A Beginner's Guide to Power and Energy Measurement and Estimation for Computing and Machine Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:15.075194Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2412.17830"},"observation_digest":"sha256:f2008183347e6b44fb76412d7ce20176e1e7bfb3a7b38b52df42cadd0aabaebe","observation_id":"1c2ba5fc-4075-4f69-bd47-6fa91c6d2057","resolution":{"observed_at":"2026-08-11T17:42:15.075194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2503.13386","last_updated":"2025-06-11T12:56:38Z","snapshot_observed_at":"2026-08-17T17:39:44.294995Z","submitted_at":"2025-03-17T17:16:47Z","title":"Neuromorphic Computing with Microfluidic Memristors","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-22T23:34:11.155400Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2503.13386"},"observation_digest":"sha256:88e90e9c01126f4377b2ccec832ebb77c42d9158679df75b80fe75ea5beab9cc","observation_id":"0398e3a8-1649-4df8-8ee3-6a3674d82741","resolution":{"observed_at":"2026-05-22T23:35:13.388946Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-08-15T18:02:16.463283Z","title":"Tripp, Jordan Perr-Sauer, Luke Hayne, Monte Lunacek, Ryan N","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19261","last_updated":"2025-07-25T13:37:45Z","snapshot_observed_at":"2026-08-16T22:53:24.411241Z","submitted_at":"2025-07-25T13:37:45Z","title":"Knowledge Grafting: A Mechanism for Optimizing AI Model Deployment in Resource-Constrained Environments","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:02:16.463283Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2507.19261"},"observation_digest":"sha256:78ab39be19c029506a384fded3b0473ec53654041df88e85ac9e41660bdba5a6","observation_id":"d000562a-907d-493d-a27d-38e7997de03d","resolution":{"observed_at":"2026-08-15T18:02:16.463283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-08-15T17:55:04.230859Z","title":"Measuring the energy consumption and efficiency of deep neural networks: An empirical analysis and design recommendations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.20063","last_updated":"2025-07-26T21:15:05Z","snapshot_observed_at":"2026-08-18T01:24:11.460773Z","submitted_at":"2025-07-26T21:15:05Z","title":"Racing to Idle: Energy Efficiency of Matrix Multiplication on Heterogeneous CPU and GPU Architectures","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T17:55:04.230859Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2507.20063"},"observation_digest":"sha256:825fb9ffa937ad72ace4aef80a256e693f88512193e186161cea3bba13afc754","observation_id":"0810ab0a-1703-404d-9086-94797917c247","resolution":{"observed_at":"2026-08-15T17:55:04.230859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-08-05T21:59:28.682858Z","title":"Measuring the energy consumption and efficiency of deep neural networks: An empirical analysis and design recommendations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07706","last_updated":"2025-08-11T07:34:04Z","snapshot_observed_at":"2026-08-08T22:46:05.653614Z","submitted_at":"2025-08-11T07:34:04Z","title":"Energy Consumption in Parallel Neural Network Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T21:59:28.682858Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2508.07706"},"observation_digest":"sha256:91d2a06dd57a5c5e7c31cf5b07043de53e0f6e0f84b57c76d337d8f840fd16a3","observation_id":"53845b63-b8e3-442c-9ce6-0d1353f403c1","resolution":{"observed_at":"2026-08-05T21:59:28.682858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2511.04776","last_updated":"2026-05-19T11:11:39Z","snapshot_observed_at":"2026-08-15T02:15:05.242652Z","submitted_at":"2025-11-06T19:52:02Z","title":"Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-18T00:33:28.444546Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2511.04776"},"observation_digest":"sha256:1c351769ae4d4fdb87ce54d27232a5d0a36a17693cda9bebae57cbb6df50e22b","observation_id":"9e743e44-80ff-400f-9422-e350b16f8d6f","resolution":{"observed_at":"2026-05-18T00:35:32.860118Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2511.04776","last_updated":"2026-05-19T11:11:39Z","snapshot_observed_at":"2026-08-15T02:15:05.242652Z","submitted_at":"2025-11-06T19:52:02Z","title":"Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T18:54:54.484299Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2511.04776"},"observation_digest":"sha256:33e790fef1b1775fcf1146f262f6f468978f6f6f2a5e938d758506482def3316","observation_id":"d4f1dfbb-c82d-4085-817d-8c5a9d81699c","resolution":{"observed_at":"2026-05-21T18:55:29.875100Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2601.00823","last_updated":"2026-04-26T18:34:17Z","snapshot_observed_at":"2026-08-15T16:22:05.914387Z","submitted_at":"2025-12-23T17:33:29Z","title":"Energy-Aware Routing to Large Reasoning Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-16T20:32:49.030941Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2601.00823"},"observation_digest":"sha256:03e556c6730cca32b9d5f961fe2ef687cf605112ea07c480dcd38bed8a265d5d","observation_id":"5f013518-8d56-4f45-950c-1cc56d254832","resolution":{"observed_at":"2026-05-16T20:33:24.071020Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2601.01253","last_updated":"2026-04-05T14:16:03Z","snapshot_observed_at":"2026-08-14T01:07:05.371380Z","submitted_at":"2026-01-03T18:25:18Z","title":"Stochastic Thermodynamics of Associative Memory","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-16T17:33:51.646212Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2601.01253"},"observation_digest":"sha256:99f42e710311f60205d0b94d380824cc7c86d9d5ca9690f2fc1ea51dda99f4e4","observation_id":"63654293-9076-4bad-a7fe-2dcdc6b63d5e","resolution":{"observed_at":"2026-05-16T17:38:11.283289Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-13T23:54:54.872017Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.16164","last_updated":"2026-06-19T08:59:41Z","snapshot_observed_at":"2026-08-14T16:20:07.698592Z","submitted_at":"2026-03-17T06:32:41Z","title":"AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-13T23:54:54.872017Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2603.16164"},"observation_digest":"sha256:c63cd20afe4d0a414313dd60aac570c60f6fe1acccb8769a3b080d779f6b6804","observation_id":"b8443be4-a89b-43d9-9b19-f2f13e22f14e","resolution":{"observed_at":"2026-07-13T23:54:54.872017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2604.22688","last_updated":"2026-04-27T02:54:19Z","snapshot_observed_at":"2026-07-06T23:09:01.221922Z","submitted_at":"2026-04-24T16:24:05Z","title":"COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC","version":2},"reference_index":144,"source":"pdf_text","source_observed_at":"2026-05-08T08:53:25.483782Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2604.22688"},"observation_digest":"sha256:65e4f0e006950efb0e324ceb768ca85dc39dca7263bfc09165f07910bfdc457f","observation_id":"c4ad2ab9-4b7e-4dea-b1f6-198816e7c267","resolution":{"observed_at":"2026-05-11T20:26:14.515264Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2605.05416","last_updated":"2026-05-06T20:20:17Z","snapshot_observed_at":"2026-08-16T11:16:46.129304Z","submitted_at":"2026-05-06T20:20:17Z","title":"From Cradle to Cloud: A Life Cycle Review of AI's Environmental Footprint","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-08T15:43:50.422887Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2605.05416"},"observation_digest":"sha256:a6e7045472968eac30b20d871c839b0a8c82186bd75fd4a0332865d3b0efe4dd","observation_id":"40bdec9d-1144-4fa8-9a72-26863ac90cf8","resolution":{"observed_at":"2026-05-11T18:31:12.717275Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":"2403.08151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-07-04T14:59:55.532477Z","title":"arXiv preprint arXiv:2403.08151 URL:https://arxiv.org/abs/2403.08151","venue":null,"work_id":"98897fb9-c354-4ad9-93b3-ad852d0b6523","year":2024},"citing_paper":{"arxiv_id":"2606.26989","last_updated":"2026-06-25T13:04:27Z","snapshot_observed_at":"2026-08-05T16:40:18.139626Z","submitted_at":"2026-06-25T13:04:27Z","title":"Physical Neural Networks Need Nonlinearity, Amplification, and Suppression for Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-26T02:02:23.398340Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2606.26989"},"observation_digest":"sha256:9448bda11a605a295f6c4bacf80fe67246cecdb5982bf956646920814545be61","observation_id":"81db4731-6c64-4aa7-a1af-8751ece989be","resolution":{"observed_at":"2026-07-04T14:59:55.534131Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08151","snapshot_observed_at":"2026-08-03T11:21:50.696176Z","title":"arXiv, 1–25 (2024) arXiv:2403.08151","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29225","last_updated":"2026-07-31T09:55:38Z","snapshot_observed_at":"2026-08-09T15:28:35.471478Z","submitted_at":"2026-07-31T09:55:38Z","title":"Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T11:21:50.696176Z"},"links":{"cited_paper":"/paper/2403.08151","citing_paper":"/paper/2607.29225"},"observation_digest":"sha256:adb0b726c5dcb78224a7d3fcb972aaf8984f5f932168fde19e0019e81c7900cd","observation_id":"82f23ace-06a8-4794-8aba-be3708398463","resolution":{"observed_at":"2026-08-03T11:21:50.696176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.08151/citation-record","integrity":"/paper/2403.08151/integrity","json":"/paper/2403.08151/citation-record.json","paper":"/paper/2403.08151"},"outbound":[],"paper":{"arxiv_id":"2403.08151","last_updated":"2024-03-13T00:27:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T01:23:49.791055Z","submitted_at":"2024-03-13T00:27:19Z","title":"Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2403.08151."}