{"as_of":"2026-08-22T06:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cbd025a940c0cd1119d1c87f239d2ac11d12af88669b0875e5ad98e61b5e1641","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T13:24:18.423418Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2602.06523/citation-record","integrity":"/paper/2602.06523/integrity","json":"/paper/2602.06523/citation-record.json","paper":"/paper/2602.06523"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition","venue":null,"work_id":"01b8eebb-1b46-4a96-b9d7-f328abaaaa25","year":2016},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:712f6a1df82c5b4e6abc8e751a504998a46e7b4967a4b6d4ac9937b330a94db9","observation_id":"cde22672-33f8-439d-91dc-cd1420cb2526","resolution":{"observed_at":"2026-05-21T13:25:11.671953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"TinyHAR: A lightweight deep learning model designed for human activity recognition","venue":null,"work_id":"95af9341-9207-4e3b-92fc-d278449a8ba5","year":2022},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:1759680a429ad6cbc16013666e8f7e722aee24447f0065569664ef6919a7d567","observation_id":"9498ec5a-b683-4a54-8558-a2414b64b8ea","resolution":{"observed_at":"2026-05-21T13:25:11.603448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"TinierHAR: Towards ultra-lightweight deep learning models for efficient human activity recognition on edge devices","venue":null,"work_id":"602f248e-ce2f-41e1-a0f6-112cb701ad10","year":2025},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:17bc0d92232f77f4ea840cc567fac76c5260d1ccc0f0f5461229006f73332de0","observation_id":"fc185d0e-8e38-4610-9dae-7bb2e1481d70","resolution":{"observed_at":"2026-05-21T13:25:11.606540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Ensembles of deep LSTM learners for activity recognition using wearables","venue":null,"work_id":"2a369b39-dfb6-42bf-b9a4-3705b9675777","year":2017},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:d593a5df8c226d53cc0b0aa89329c559fcc2997091c21b9e041b858128b93450","observation_id":"33ec12f3-b675-4e65-a880-245977ca3751","resolution":{"observed_at":"2026-05-21T13:25:11.678184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Deep, convolutional, and recurrent models for human activity recognition using wearables","venue":null,"work_id":"e629ff6b-064c-4355-a3db-f681a31ac871","year":2016},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:59e49d480a26c0455e09dc4fd12ded871692f862fbf7584693675135eaf33f67","observation_id":"bdb6c978-7c28-4ac0-a3b4-47e1dffb653f","resolution":{"observed_at":"2026-05-21T13:25:11.612273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities","venue":null,"work_id":"57d7c7e3-69dd-4c07-8988-db1ed51511ed","year":2021},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:1fba6884f8d4bc75371da232ee5332eda157ff360c8d6448b386733603d1491e","observation_id":"6736bff6-cada-4641-a60f-4a6149558697","resolution":{"observed_at":"2026-05-21T13:25:11.553058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Deep learning for health informatics","venue":null,"work_id":"ae1dca66-d5bb-4c80-a55d-761279582071","year":2017},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:e1d9429a875f14cd669b32caf0a6bd328e31a2c01bf33878dbbba48c5b488c61","observation_id":"3db71fb2-2f4a-485b-a9b6-86695ad0e231","resolution":{"observed_at":"2026-05-21T13:25:11.579408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Real-time human activity recognition from accelerometer data using convolutional neural networks","venue":null,"work_id":"59cf20de-43e5-4e60-a695-5585d19369ed","year":2018},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:c0809e4e2b59a16cc7a0a9ac85ab2ad0f005b0024920ca1926b5b2f4ef627912","observation_id":"4c7086b7-4b5b-4976-a942-d113141e9965","resolution":{"observed_at":"2026-05-21T13:25:11.653786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"A tutorial on human activity recognition using body-worn inertial sensors","venue":null,"work_id":"f589c1e0-7c3e-48ef-ae6f-344540cb029b","year":2014},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:74372fbf236a7d854481e0f9d97cec91c138fd96b3e635d4816565bca3635195","observation_id":"1b1d8db9-6d1e-46c6-b459-5c6198d7e474","resolution":{"observed_at":"2026-05-21T13:25:11.675036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Activity recognition using cell phone accelerometers","venue":null,"work_id":"4c5899d2-3deb-4ca1-8670-2534b7490f4b","year":2011},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:8253a3106fdde863b164711b7413ba47692c7a8998a428f912c52b20861f93e7","observation_id":"401fa3cc-9caa-45ba-99e7-41fb9fe2fff8","resolution":{"observed_at":"2026-05-21T13:25:11.623193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"A public domain dataset for human activity recognition using smartphones","venue":null,"work_id":"d7fcf148-cc84-46ad-8269-3029dca7a858","year":2013},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:5d5b692010ce1ce58ac88ef8926f30a0e12b1545c48bca91b9d81860a5f4f30f","observation_id":"2a11d137-1ed1-429e-b195-65d1925a25ca","resolution":{"observed_at":"2026-05-21T13:25:11.549927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Mobile sensor data anonymization","venue":null,"work_id":"7c6dded2-b606-4a76-8ceb-6144be103c9a","year":2019},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:afa0cd202fe9bdfb377d487d1b315a05dd7afe6ba793c0f3265b35ea4c2a9426","observation_id":"494a6892-ec91-418b-867a-78ae23f598bc","resolution":{"observed_at":"2026-05-21T13:25:11.647480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"The Opportunity challenge: A bench- mark database for on-body sensor-based activity recognition","venue":null,"work_id":"0b219d7e-3abc-4ba5-b008-68ef6734ebf5","year":2033},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:76b23bd9a9f9373544801bc0349da6ebeb27eb07ca16bc23efbde396651d87cd","observation_id":"6b4d2074-c29b-439c-b929-10755bdc36bb","resolution":{"observed_at":"2026-05-21T13:25:11.567268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Wearable activity tracking in car manufacturing","venue":null,"work_id":"a8482ca3-88c0-4724-9983-db7bea4f24ba","year":2008},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:337bd717024e78a4c627449864a4ce33ab35db6626685006f04bdefc893e77c9","observation_id":"d9d4ced4-8f31-4906-842f-cf447e76648b","resolution":{"observed_at":"2026-05-21T13:25:11.659944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom","venue":null,"work_id":"e5744de8-8514-46fd-b307-d81ee55c50fe","year":2010},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:d8a1c922f5af274a8e3a5e332f9c77c7c2f7af38d18239dc533a2a330b01c86a","observation_id":"e3a380d1-b649-4c3c-967f-5df5dc63685d","resolution":{"observed_at":"2026-05-21T13:25:11.589387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Introducing a new benchmarked dataset for activity monitoring","venue":null,"work_id":"34469258-90e4-4646-bb8a-9c485deb3542","year":2012},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:8605f508dd5eda8aeb9ef407e49171a1da5fd7f7566351a010e5bf131d2d0d88","observation_id":"ddf3e4a4-0970-4e79-85c7-66dd10ca0b63","resolution":{"observed_at":"2026-05-21T13:25:11.644064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"UniMiB SHAR: A dataset for human activity recognition using acceleration data from smartphones","venue":null,"work_id":"f0ffec2e-2ecf-44d0-9686-272940b77325","year":2017},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:360dca983686a6dbc88b066edc973883a59950d0412f8cc808cf76526e0fa03f","observation_id":"1402dc75-1e88-4b62-8863-189c4132ce3f","resolution":{"observed_at":"2026-05-21T13:25:11.556722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-05T04:50:42.475468Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"f85d6953-0ae3-4722-8194-570fb2ffbfa8","year":2019},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:b400b54315d5fa652322b5433386d41bf883b9e02b8c6f897bfb1a564c9cf51d","observation_id":"427fb1c2-d498-4c38-80b2-72746c603f68","resolution":{"observed_at":"2026-05-21T13:25:11.586006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Optuna: A next-generation hyperparameter optimization framework","venue":null,"work_id":"ed2f2d70-7be6-4374-b513-1897ed0dbee5","year":2019},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:82dda50110d8b6a6d60b918bff71bea2952a230d8c14968202a7ec145d13faa9","observation_id":"c6c99c7a-6f59-469c-878c-6c4f838d6995","resolution":{"observed_at":"2026-05-21T13:25:11.592483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-07-11T02:07:57.922413Z","title":"Long short-term memory","venue":null,"work_id":"8c0562b6-428d-4994-837b-acde0c22b125","year":1997},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:b5efb3a533637ec62349909566f9cb6bbc75225e3f3a4722831e9da9410c3b92","observation_id":"f262a1ec-a948-4ac6-84c4-b638664df076","resolution":{"observed_at":"2026-05-21T13:25:11.656793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Speech recognition with deep recurrent neural networks","venue":null,"work_id":"a458dd99-d64c-47ab-859a-7fe13909dcce","year":2013},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:7078f9878cc4b7abfa0cda6ca42d4181f2b3af24ab4663bdc63125919760f79f","observation_id":"bdf4e2b2-f745-4439-8621-ca06df784d7e","resolution":{"observed_at":"2026-05-21T13:25:11.634954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Bidirectional recurrent neural net- works","venue":null,"work_id":"f930ad47-1f4f-49c4-ad8f-802cbde459fa","year":1997},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:a79489fc7b9d9d56016d5e7c193924324615f115d15af2e0e91b7dbc05ef900d","observation_id":"8135efac-ed01-4754-91c4-6bcc0ff14c88","resolution":{"observed_at":"2026-05-21T13:25:11.600652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":"e975c8ec-c45a-4570-b767-4ee7e804343f","year":2015},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:856be78d13b2c1188ac2f5516fd69e6128bb969be0703eecffa320a3fecfe3aa","observation_id":"8f602c62-e2a3-48d9-8c0d-ee75e7370e86","resolution":{"observed_at":"2026-05-21T13:25:11.629070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Dropout: A simple way to prevent neural networks from over- fitting","venue":null,"work_id":"6a4c5a28-c1fe-4401-9fba-0a6117fb9030","year":1929},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:f9f4b6fbc9d2a3e7955977473f99e2e248a4e18dc60bfdece051837d1453504d","observation_id":"20860215-9ce1-4aa9-9454-81bbdd713a0d","resolution":{"observed_at":"2026-05-21T13:25:11.620265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification","venue":null,"work_id":"fba26017-1f26-4fef-9a90-ef0afd561f03","year":2015},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:aa85af6b5f67d5ee65cec6ce7f8aae3debbb9feb1d6fde9d9ecc00f156d4b7d7","observation_id":"a2d77861-05b7-45ef-b1ef-512e2d912a96","resolution":{"observed_at":"2026-05-21T13:25:11.564164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":"252b5c8d-389d-4e6f-bc94-a497ef9dc1ca","year":2015},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:507f2c21d703897ab2047ad6b3f97fd59fe9b1043a552105ebd1f268b28ce814","observation_id":"c5a51850-17f7-4a9b-b093-fe65c747aeae","resolution":{"observed_at":"2026-05-21T13:25:11.560494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"430dda9b-f64b-4c79-b959-1bcd590ce426","year":2018},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:775c6a09696709c2aa636b5b2c68c2f7f330a483bb462d285f54e406da7968e8","observation_id":"4f610522-9c2e-4d33-a9b9-5f0dedb51e1c","resolution":{"observed_at":"2026-05-21T13:25:11.641057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-08-15T01:28:14.336267Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":"1806.08342","doi":"10.48550/arxiv.1806.08342","metadata_source":"pith","pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","venue":"cs.LG","work_id":"c5b5b22a-9bfc-4500-9a92-2813e7603693","year":2018},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:d4b098d6ee361f777b07f2dd079031a8204d9e4ba7aa23bb317b11d5a7f05264","observation_id":"68ac6d5b-c4a2-406d-9388-ff97b2d0096d","resolution":{"observed_at":"2026-05-21T13:25:11.508973Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"MLPerf Tiny benchmark","venue":null,"work_id":"8e17298c-56fe-47de-84ba-70f167ad30e5","year":2021},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:86c2b12cd4efb603026d04016def513f28f4411e601d0aae05641217c0b66e7d","observation_id":"23caeacc-18a4-4d82-9133-10b5e8f67e60","resolution":{"observed_at":"2026-05-21T13:25:11.595136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Warden and D","venue":null,"work_id":"17f76134-097d-45cd-ac67-9ddca5b5a5a2","year":2019},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:10a41caa9f12e6752ef7eac8fa86fd692e9483ce8dea950ccab3ac728e8e720a","observation_id":"7cb269d8-ba47-434f-bf04-3f54da635c28","resolution":{"observed_at":"2026-05-21T13:25:11.573340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"MCUNet: Tiny deep learning on IoT devices","venue":null,"work_id":"78f00dc0-e7d0-4271-9763-93234a04221d","year":2020},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:e06204ae847928d4c02f0643ff517e83584834dc1eb8fe9bc3990e1f907a8e2c","observation_id":"8e18924d-de06-4ec4-8ddd-ee08cecbe926","resolution":{"observed_at":"2026-05-21T13:25:11.650630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06601","last_updated":"2018-01-19T23:39:15Z","snapshot_observed_at":"2026-08-14T19:53:38.140071Z","submitted_at":"2018-01-19T23:39:15Z","title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","version":1},"cited_work":{"arxiv_id":"1801.06601","doi":"10.48550/arxiv.1801.06601","metadata_source":"pith","pith_arxiv_id":"1801.06601","snapshot_observed_at":"2026-07-11T03:27:45.739818Z","title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","venue":"cs.NE","work_id":"69ae0df4-8381-4f4e-b7e4-79c11ea7c479","year":2018},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"cited_paper":"/paper/1801.06601","citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:7b49bff8aa8fec4caa1ffefd1dbd9a3dac416bd603d72fe7c2ef0c41680d9f89","observation_id":"31517eb1-44db-422b-ad85-3b327e80e564","resolution":{"observed_at":"2026-05-21T13:25:11.504220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Attend and discriminate: Beyond the state-of-the-art for human activity recognition using wearable sensors","venue":null,"work_id":"3a9cdc07-c558-4d64-9762-736ff11422c3","year":2021},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:85fc5ccf350953c5dc6cdfb4acf197a707ed4546ae665cee3f7244b0fa1129e0","observation_id":"bc0a288a-828b-4759-99fb-b3c4f5a569eb","resolution":{"observed_at":"2026-05-21T13:25:11.609372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"GlobalFusion: A global attentional deep learning framework for multisensor information fusion","venue":null,"work_id":"1d096197-a83c-48d1-a962-89043849e110","year":2020},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:59a383ee89a895ecfce5dd57fb9b0cd718d3bf960cb5bb3a7f5daa402e8a053d","observation_id":"88310963-17bd-42cc-813e-221ffc5370d3","resolution":{"observed_at":"2026-05-21T13:25:11.631870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"AttnSense: Multi-level attention mechanism for multimodal human activity recognition","venue":null,"work_id":"f9660161-bf57-419e-b7b4-0f32a1728c35","year":2019},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:f35e053e1361af1170e51631acb7c4ce64d0673bec9d55acab5e6b8efdcb964e","observation_id":"706e3fde-7eca-4822-a98b-fc1a3c5b0ae5","resolution":{"observed_at":"2026-05-21T13:25:11.614709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"On attention models for human activ- ity recognition","venue":null,"work_id":"2a9cbb28-a27a-418e-8ca6-a3ec35234eed","year":2018},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:514dcec4e0237b4c17331868bd151327c0df5fbdf7708e4088aac19ae67c8fd5","observation_id":"14546774-b235-4f51-a420-431ff8454683","resolution":{"observed_at":"2026-05-21T13:25:11.598040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"MLP- HAR: Boosting performance and efficiency of HAR models on edge devices with purely fully connected layers","venue":null,"work_id":"0122dff1-5548-4158-acc3-a4800bfd9ac7","year":2024},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:17f26f3ebeb6d9d016f873d2a86225cd19297067c4f82f81f03b1033fa77bdcf","observation_id":"c4d77d05-6eba-41b3-81d0-8e5201fd9fea","resolution":{"observed_at":"2026-05-21T13:25:11.669083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"LHAR: Lightweight human activity recognition on knowledge distilla- tion","venue":null,"work_id":"341476c7-e83c-4094-a943-df8a0ebd40f5","year":2023},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:1f14f6f2490599d22a9b34a1091dbd70ff3ca4162bae49d55d24865a1c839d41","observation_id":"db210e0d-63c6-4ae6-82d5-61484c1ccecf","resolution":{"observed_at":"2026-05-21T13:25:11.570466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"A human activity recognition method based on lightweight feature extraction combined with pruned and quantized CNN for wearable device","venue":null,"work_id":"c7897aa6-3055-489b-b000-c3e4b04afc0d","year":2023},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:ac8668d3afa6262310cf1f74cb83e60cf050b592a6ace3e4f4d7f2ed4a1770f2","observation_id":"af3dbbf7-a409-42ae-b2a2-fbe74ba61eb1","resolution":{"observed_at":"2026-05-21T13:25:11.617596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Efficient human activity recognition using lookup table-based neural architecture search for mobile devices","venue":null,"work_id":"719c40fc-8dc4-42fc-90d6-490311c2b9b5","year":2023},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:4d2d3c30264ee31f00b08f4c004b1cf799c0e8d68e3d226ec274c036e7a146af","observation_id":"4f158e47-b766-4dcc-a4de-21a26fc10f90","resolution":{"observed_at":"2026-05-21T13:25:11.662917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Attention is all you need","venue":null,"work_id":"6264e843-c8ef-4543-94fa-7e3209cea147","year":2017},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:7d6dda9b1b85abbb9fac8157914a76b17049a749fb42c87ef09ea4b80e7846ae","observation_id":"0595527d-ecf1-412a-99b4-8103f836d8b7","resolution":{"observed_at":"2026-05-21T13:25:11.576532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Are Transformers a useful tool for tiny devices in human activity recognition?","venue":null,"work_id":"2a1439ea-700e-429d-af7a-54a617e59461","year":2024},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:dabc873548e0297d86e1a407e108fea3f1c340bb73dda047cf00ca970eb690c9","observation_id":"638f9af5-987d-4087-bad1-e1b4323b153a","resolution":{"observed_at":"2026-05-21T13:25:11.638057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Improv- ing deep learning for HAR with shallow LSTMs","venue":null,"work_id":"be4abb48-39a6-4d10-81fd-089f637f0bdc","year":2021},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:5dc9b3cf2b9df913784e5fc938cc522315a99101dd6b490af233935f13b807a7","observation_id":"6d67109d-4bff-487c-865c-b850d8552885","resolution":{"observed_at":"2026-05-21T13:25:11.666025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"A lightweight framework for human activity recognition on wearable devices","venue":null,"work_id":"be01a0f9-7a24-42ff-b671-746c2a1b7d7b","year":2021},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:9c63b028bce55927c54f0da5ca2026af8c51d01983cd5b20b7627a4155256505","observation_id":"271a8f43-5182-4af6-b484-01eb72121e62","resolution":{"observed_at":"2026-05-21T13:25:11.582749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-05T21:23:00.469572Z","title":"Human activity recognition with smart- phone sensors using deep learning neural networks","venue":null,"work_id":"9d1fbd99-ab11-4f3f-af7f-77b6acf542d8","year":2016},"citing_paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-21T13:24:18.423418Z"},"links":{"citing_paper":"/paper/2602.06523"},"observation_digest":"sha256:92b06429e074d53ef8fd1dee19c45573ab27876f437524bdcca5963e7f0ba29d","observation_id":"ac786ac6-0c6f-4a3d-8688-5d596ff7004a","resolution":{"observed_at":"2026-05-21T13:25:11.626132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2602.06523","last_updated":"2026-05-17T05:51:48Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T10:33:38.316167Z","submitted_at":"2026-02-06T09:26:29Z","title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":2,"verified_fuzzy":43},"total_outbound_references":45},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2602.06523."}