{"as_of":"2026-08-07T05:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f282bf071d4d46cfc923a6d78f2541ce205cdaa007e8ac872c09f5e415f62767","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T05:29:10.780393Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.05488/citation-record","integrity":"/paper/2509.05488/integrity","json":"/paper/2509.05488/citation-record.json","paper":"/paper/2509.05488"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:10.725104Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.725104Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:26cc0c4c0b9c8e23afde5133b86b297ab0d801d6865230687cd5796279c1320f","observation_id":"d5a76b06-087d-498f-aeaa-5152e9d1d83f","resolution":{"observed_at":"2026-08-05T05:29:10.725104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-05T05:29:10.729997Z","title":"Deep compression: Compressing deep neural net- works with pruning, trained quantization and huffman coding.arXiv preprint arXiv:1510.00149, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.729997Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:acea4b943fb8773b3d837975b37e8867ccca43d4f43d210da4abc6fe517c244b","observation_id":"9770fb24-1852-4c0e-82b5-7f03a18ac31a","resolution":{"observed_at":"2026-08-05T05:29:10.729997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04821","last_updated":"2021-01-29T21:21:37Z","snapshot_observed_at":"2026-07-06T09:03:43.967832Z","submitted_at":"2020-03-10T15:58:12Z","title":"Benchmarking TinyML Systems: Challenges and Direction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04821","snapshot_observed_at":"2026-08-05T05:29:10.734983Z","title":"Benchmarking tinyml systems: Challenges and direction.arXiv preprint arXiv:2003.04821, 2020","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.734983Z"},"links":{"cited_paper":"/paper/2003.04821","citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:86dbe20add348f76d1e487de348eed4e8b764ca915cd68ee728d363f45f69263","observation_id":"cb7d2a58-2384-44e9-b822-807cd65dd084","resolution":{"observed_at":"2026-08-05T05:29:10.734983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:11.272788Z","title":"Mcunet: Tiny deep learning on iot devices.Advances in neural information processing systems, 33:11711–11722, 2020","venue":null,"work_id":"fc1b315d-7b3e-4259-8b63-f3ff6cf32e07","year":2020},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.740442Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:0f9f347fb714bfbf90509b8c7c03776c63469e64286e480054f6431a9f163618","observation_id":"7709886d-9b72-448c-8032-c9377cde8006","resolution":{"observed_at":"2026-08-05T05:29:11.278017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:11.256773Z","title":"Tensorflow lite micro: Embedded machine learning for tinyml systems.Proceedings of machine learning and systems, 3:800–811, 2021","venue":null,"work_id":"a2debe64-6fb9-403d-b1ed-22a87b090d53","year":2021},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.745496Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:bd7d69e10caf3e1984634731c4fcb7f6a47ca1d385a05ec9651e0c9b4136bdf6","observation_id":"7baf332f-a936-4ae0-8aec-3c2fe722fcad","resolution":{"observed_at":"2026-08-05T05:29:11.262132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:11.177293Z","title":"Improving the efficiency of transformers for resource-constrained devices","venue":null,"work_id":"50536218-b407-4e00-8eb3-7b069530f6b2","year":2021},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.750612Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:29f5bebbbd0791807fc171d39b2802aa92ba16ce4a5682a21f34fa97bfa051ec","observation_id":"97c809d5-f7a1-41f5-96fb-2d4fd46b2fe1","resolution":{"observed_at":"2026-08-05T05:29:11.182045Z","resolver_source":"arxiv_id_nonexistent","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:10.997481Z","title":"Machine learning for microcontroller-class hardware: A review.IEEE Sensors Journal, 22(22):21362–21390, 2022","venue":null,"work_id":"77ef112c-f5c2-4eae-8a38-ce27e7c76729","year":2022},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.755854Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:84f9e5901d1dc56fce6761d75e9fb4befe2dc92535e4aece6c5dc554173572c9","observation_id":"b281a718-315c-4e82-85e0-c54a04366c76","resolution":{"observed_at":"2026-08-05T05:29:11.003993Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-05T05:29:10.761039Z","title":"Mamba: Linear-time sequence modeling with selective state spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.761039Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:fefc88277dfb71e3a639e8f467728396f5f7bd2176029f3c980a7b8ec88bb6f5","observation_id":"11da0735-4a87-4c51-a72b-47a9f54de27d","resolution":{"observed_at":"2026-08-05T05:29:10.761039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.21060","last_updated":"2024-05-31T17:50:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-31T17:50:01Z","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.21060","snapshot_observed_at":"2026-08-05T05:29:10.765605Z","title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality.arXiv preprint arXiv:2405.21060, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.765605Z"},"links":{"cited_paper":"/paper/2405.21060","citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:e71c1306d94d9b5d634b931c23b998562f41db917eb4a3736c5bbdd8943fe032","observation_id":"e2719db8-fff0-44ac-9270-2f976715fb40","resolution":{"observed_at":"2026-08-05T05:29:10.765605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:11.240592Z","title":"Optimis- ing tinyml with quantization and distillation of transformer and mamba models for indoor localisation on edge devices.Scientific Reports, 15(1):10081, 2025","venue":null,"work_id":"555478c7-08e5-4068-b8a9-4bc2bb324c78","year":2025},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.770562Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:0a66f127a3f982ad01916311a3090e5e700976e9875a6f79b813301042e34182","observation_id":"7a04ce28-faa0-4b67-a3df-776c3b7dbf49","resolution":{"observed_at":"2026-08-05T05:29:11.246074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-05T05:29:10.775645Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.775645Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:4d952995ebeb5528b987c6906226f079f3a2da69056da2c6de424ec53e6e9e78","observation_id":"e93a4c1a-1b87-4a9f-b98f-c843d4e5a2ec","resolution":{"observed_at":"2026-08-05T05:29:10.775645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:29:11.225161Z","title":"A public domain dataset for human activity recognition using smartphones","venue":null,"work_id":"a5133e88-1610-457c-b39f-953111cdb0f8","year":2013},"citing_paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T05:29:10.780393Z"},"links":{"citing_paper":"/paper/2509.05488"},"observation_digest":"sha256:edc89424c44bfbd29f4d6a92b5f8d16e80109756cdaef9b945bcc35e88b294d1","observation_id":"f044a698-ed73-4d14-8a1c-30a614e57ce2","resolution":{"observed_at":"2026-08-05T05:29:11.229776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.05488","last_updated":"2025-09-05T20:34:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T16:17:42.101204Z","submitted_at":"2025-09-05T20:34:06Z","title":"MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":4},"total_outbound_references":12},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2509.05488."}