{"as_of":"2026-08-09T21:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d85e4ba4c2256159b3e4b7b64cb857a9c9459e44512ac89dc1ebe9ef024dcec8","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":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":21,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T20:32:06.462364Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-09T02:55:53.494035Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2405.00892","last_updated":"2026-04-30T18:09:59Z","snapshot_observed_at":"2026-07-06T18:08:30.875909Z","submitted_at":"2024-05-01T22:33:45Z","title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","version":6},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T01:06:48.298874Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2405.00892"},"observation_digest":"sha256:40c95b17b50df2da95f201c25cadd7954ec8a1a3c8360f7ab3579fdd8d268e3e","observation_id":"ff09f248-ddb9-4699-887d-6d1adbe8f715","resolution":{"observed_at":"2026-05-24T01:08:41.928544Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-09T20:32:06.462364Z","title":"MLPerf tiny benchmark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.19347","last_updated":"2025-07-15T14:44:46Z","snapshot_observed_at":"2026-08-09T20:25:27.873923Z","submitted_at":"2025-01-31T17:51:46Z","title":"An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T20:32:06.462364Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2501.19347"},"observation_digest":"sha256:a9aa4185074bdf036bfaa526ac7c70b6805f36180931f1fda4c61fcbd64ec6f2","observation_id":"70669fb1-4230-4380-8cce-560c57582ec5","resolution":{"observed_at":"2026-08-09T20:32:06.462364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-07T12:42:21.976648Z","title":"Mlperf tiny bench- mark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23939","last_updated":"2026-06-16T09:49:53Z","snapshot_observed_at":"2026-08-09T15:24:36.752434Z","submitted_at":"2025-05-29T18:42:25Z","title":"Searching Neural Architectures for Sensor Nodes on IoT Gateways","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:42:21.976648Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2505.23939"},"observation_digest":"sha256:6542231c242ee5ec843e699f7f593bc783ac589066f4a957c0af8c958e8ce740","observation_id":"7b458b84-d54a-445c-ad59-ff34b1139623","resolution":{"observed_at":"2026-08-07T12:42:21.976648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-06T20:55:37.780009Z","title":"Mlperf tiny benchmark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01457","last_updated":"2025-08-19T09:55:09Z","snapshot_observed_at":"2026-08-09T11:23:01.672855Z","submitted_at":"2025-07-02T08:15:33Z","title":"Tensor Program Optimization for the RISC-V Vector Extension Using Probabilistic Programs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:55:37.780009Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2507.01457"},"observation_digest":"sha256:4d222358ab567ba35f46861188df2a320a5d552e000ac6733bbe482ce7b44064","observation_id":"534fb257-e080-436e-a9ed-1bdc4cb56d51","resolution":{"observed_at":"2026-08-06T20:55:37.780009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-06T19:40:20.549122Z","title":"Mlperf tiny bench- mark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.05141","last_updated":"2025-07-07T15:51:18Z","snapshot_observed_at":"2026-08-06T19:29:14.539050Z","submitted_at":"2025-07-07T15:51:18Z","title":"Hardware-efficient tractable probabilistic inference for TinyML Neurosymbolic AI applications","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:40:20.549122Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2507.05141"},"observation_digest":"sha256:d54ac0ad8ff8765fb1f110617179539d987d798b45b6f7d65da97d185bd7620c","observation_id":"0eae516d-ecaf-488a-8016-aec2bb04a828","resolution":{"observed_at":"2026-08-06T19:40:20.549122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-06T16:09:32.933918Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17771","last_updated":"2025-07-19T00:57:54Z","snapshot_observed_at":"2026-08-06T15:54:22.947157Z","submitted_at":"2025-07-19T00:57:54Z","title":"Flexible Vector Integration in Embedded RISC-V SoCs for End to End CNN Inference Acceleration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:09:32.933918Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2507.17771"},"observation_digest":"sha256:e56a0e059ba8b23939b1f90426fa357f67208b1cb98e7332c4423fadccbfb0c6","observation_id":"b3b818d6-0b18-4bbb-9fa2-e790c5b42821","resolution":{"observed_at":"2026-08-06T16:09:32.933918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-05T05:59:51.067059Z","title":"[Online]","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.067059Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:e4c6c8991b3689ea930813826c54252a4119fea5a41ed7d7810c3fd2984547d2","observation_id":"5d4734d2-6541-4c7e-82c9-f425f9595bdc","resolution":{"observed_at":"2026-08-05T05:59:51.067059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-03T17:24:26.197603Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.09800","last_updated":"2026-05-27T09:16:32Z","snapshot_observed_at":"2026-08-03T17:24:25.212679Z","submitted_at":"2025-12-10T16:13:29Z","title":"Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T17:24:26.197603Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2512.09800"},"observation_digest":"sha256:bf952d610964b7c44dd35024900f363a1ec36922a5abc2697a0b162b03cbe9e0","observation_id":"d2b5002d-42f3-4246-9fd4-2b028f198400","resolution":{"observed_at":"2026-08-03T17:24:26.197603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2604.19106","last_updated":"2026-04-21T05:33:11Z","snapshot_observed_at":"2026-07-06T23:05:48.885141Z","submitted_at":"2026-04-21T05:33:11Z","title":"Design Rules for Extreme-Edge Scientific Computing on AI Engines","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T02:19:21.143588Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2604.19106"},"observation_digest":"sha256:48d3c68ce4394a95bec0fc60306eaea6da08fe31ba7eb1be48e7f816062d6bc0","observation_id":"ae6129ac-7bc0-4663-9604-3ef07bcfc7fb","resolution":{"observed_at":"2026-05-11T13:06:05.521545Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2604.19342","last_updated":"2026-04-21T11:25:22Z","snapshot_observed_at":"2026-07-06T23:06:02.635464Z","submitted_at":"2026-04-21T11:25:22Z","title":"Are Large Language Models Economically Viable for Industry Deployment?","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-10T02:28:12.686424Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2604.19342"},"observation_digest":"sha256:e9038be844ba967603c71bf28c3b9c323f19ea5d35b7e131b9db3ac6b15c6a16","observation_id":"686ac15f-a227-4666-99b7-0cf926a16c67","resolution":{"observed_at":"2026-05-11T13:01:20.353349Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.07936","last_updated":"2026-05-18T10:52:05Z","snapshot_observed_at":"2026-08-02T15:45:32.526704Z","submitted_at":"2026-05-08T16:05:46Z","title":"A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-11T03:16:27.371359Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.07936"},"observation_digest":"sha256:33f009809c9ddc286e9c79f039962266e75d46f9c3685a7e22b29258bd5e2f21","observation_id":"fb75ef33-d277-4386-b014-85c06a7565cb","resolution":{"observed_at":"2026-05-11T03:20:56.108853Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.07936","last_updated":"2026-05-18T10:52:05Z","snapshot_observed_at":"2026-08-02T15:45:32.526704Z","submitted_at":"2026-05-08T16:05:46Z","title":"A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-20T22:46:56.512703Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.07936"},"observation_digest":"sha256:d3255eb98babc8357935a36e35bf44f8b44a73b963b2961366da86d481f3bceb","observation_id":"88cbba5b-de60-4451-acdd-89405e8338b7","resolution":{"observed_at":"2026-05-20T22:49:10.376572Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.10959","last_updated":"2026-05-05T08:14:28Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-05T08:14:28Z","title":"QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-13T07:47:38.066716Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.10959"},"observation_digest":"sha256:ebd853bf23e3c557b0a9bb2a67842576b0575c60e8f9a1bd16b1592decf127be","observation_id":"68b7077c-c1f3-4d8d-87d1-0a3c0484e447","resolution":{"observed_at":"2026-05-13T07:52:32.341381Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.15216","last_updated":"2026-05-26T08:47:08Z","snapshot_observed_at":"2026-08-08T06:19:18.473672Z","submitted_at":"2026-05-12T09:44:32Z","title":"Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-20T22:07:34.292536Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.15216"},"observation_digest":"sha256:6437edea40939b784808871225107991508a6a1533804adbc4cc5c9e49160411","observation_id":"43fef4f5-0840-4577-9813-ea80c5f7ec15","resolution":{"observed_at":"2026-05-20T22:09:07.264633Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.15216","last_updated":"2026-05-26T08:47:08Z","snapshot_observed_at":"2026-08-08T06:19:18.473672Z","submitted_at":"2026-05-12T09:44:32Z","title":"Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-30T22:21:16.608148Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.15216"},"observation_digest":"sha256:aa9b7af302b39ca6f1f31befcd48116649ede3c8f9cf6afad947e693b864007b","observation_id":"ff70bbb9-4f2d-4ba2-b20d-e173899b1c71","resolution":{"observed_at":"2026-07-01T14:05:46.340205Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2605.15647","last_updated":"2026-05-15T06:02:19Z","snapshot_observed_at":"2026-08-02T05:53:57.032302Z","submitted_at":"2026-05-15T06:02:19Z","title":"Perforated Neural Networks for Keyword Spotting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-20T21:10:09.974162Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2605.15647"},"observation_digest":"sha256:bfa03460ee3def2542a5bc581485c06e317d5333e3df5710db008ee520f76b32","observation_id":"d512dca2-2df3-4f78-99be-17008ae256da","resolution":{"observed_at":"2026-05-20T21:13:44.818066Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2606.07431","last_updated":"2026-06-08T14:50:28Z","snapshot_observed_at":"2026-08-02T03:22:26.305321Z","submitted_at":"2026-06-05T16:27:02Z","title":"OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T22:03:18.602151Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2606.07431"},"observation_digest":"sha256:e31630a6c5f507698fb91c9e556859fad734d7d7ceabe49b431a1bcb3b8e7e6f","observation_id":"28373b91-2567-4615-ae97-d2e682ab8820","resolution":{"observed_at":"2026-07-02T17:27:15.080350Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-12T14:06:47.857777Z","title":"Mlperf tiny bench- mark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.14427","last_updated":"2026-06-12T13:05:34Z","snapshot_observed_at":"2026-08-04T19:13:08.620726Z","submitted_at":"2026-06-12T13:05:34Z","title":"Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T14:06:47.857777Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2606.14427"},"observation_digest":"sha256:6dfd2aae037d1735707d8222498b2104332038691a40eb36005318cd9b634393","observation_id":"2fa0aaf9-1cb5-45be-9346-41cfdfe39fde","resolution":{"observed_at":"2026-07-12T14:06:47.857777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2606.23210","last_updated":"2026-06-22T11:54:34Z","snapshot_observed_at":"2026-08-03T19:07:50.330806Z","submitted_at":"2026-06-22T11:54:34Z","title":"Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T09:21:01.698209Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2606.23210"},"observation_digest":"sha256:845ac56ae05b478ae4b5306b9a679bdf721de95b20f3b30429d15cc0e8786705","observation_id":"d03f2752-f7a4-47e6-86b2-c7d6c476e2aa","resolution":{"observed_at":"2026-07-04T09:49:45.040981Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2606.27704","last_updated":"2026-06-26T04:04:08Z","snapshot_observed_at":"2026-07-07T00:01:54.432346Z","submitted_at":"2026-06-26T04:04:08Z","title":"AdvScan: Black-Box Adversarial Example Detection at Runtime through Power Analysis","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-29T04:27:36.458570Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2606.27704"},"observation_digest":"sha256:1ab9c71e7eabf491ebe19611fed7de22521714797021a69b29f7b11a4620e36f","observation_id":"57eff531-f8b7-415f-a30f-9623b599e7f1","resolution":{"observed_at":"2026-07-01T16:55:50.973127Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":"2106.07597","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-07-09T02:55:53.494035Z","title":"Mlperf tiny benchmark.arXiv preprint arXiv:2106.07597, 2021a","venue":"cs.LG","work_id":"32e70299-7b54-46e9-a827-b6ef5ed171d1","year":2021},"citing_paper":{"arxiv_id":"2607.07683","last_updated":"2026-07-08T17:42:00Z","snapshot_observed_at":"2026-08-06T22:01:38.533451Z","submitted_at":"2026-07-08T17:42:00Z","title":"ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-09T02:52:36.673562Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2607.07683"},"observation_digest":"sha256:ca643470939f476b2e6f8251bc4ead0b407228778df7e624f964053fc8de03bf","observation_id":"c30300be-bc0c-489a-9b83-5af0a5ad5b2a","resolution":{"observed_at":"2026-07-09T02:55:53.495667Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.07597/citation-record","integrity":"/paper/2106.07597/integrity","json":"/paper/2106.07597/citation-record.json","paper":"/paper/2106.07597"},"outbound":[],"paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 21 inbound Pith citation observations for arXiv:2106.07597."}