{"as_of":"2026-08-10T07:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c260931a1156e52bed43f8edb01264e8d6acae7634db0b36680d3384c9d2b4a8","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:31:33.836249Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T10:20:04.345577Z","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":"2026-08-08T10:20:04.421246Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"cited_work":{"arxiv_id":"2507.07949","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.07949","snapshot_observed_at":"2026-08-08T10:20:04.421246Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","venue":"cs.CV","work_id":"20754b07-9a64-4264-859f-18ebac9b3a00","year":2025},"citing_paper":{"arxiv_id":"2608.05572","last_updated":"2026-08-06T03:47:15Z","snapshot_observed_at":"2026-08-09T23:11:05.846127Z","submitted_at":"2026-08-06T03:47:15Z","title":"Viveka: Context-Aware Sensing for Energy Efficiency in Smart Wearables","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T10:20:04.345577Z"},"links":{"cited_paper":"/paper/2507.07949","citing_paper":"/paper/2608.05572"},"observation_digest":"sha256:db4812e413c85896cb0971fec798b7a6a56cd1d277c465878c5ad8dfeb7c6b6f","observation_id":"f89fb65e-7b75-4cdb-ace6-d6f3918665d7","resolution":{"observed_at":"2026-08-08T10:20:04.427114Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.07949/citation-record","integrity":"/paper/2507.07949/integrity","json":"/paper/2507.07949/citation-record.json","paper":"/paper/2507.07949"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:31:35.118783Z","title":"https://archive.ics.uci.edu/dataset/245/daphnet+freezing+of+gait","venue":null,"work_id":"24c4ce8e-c827-42bd-9d5f-3e7b528d73e3","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.317590Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:f4e7b29e75a99722ac8604c6743e16a5bc7ad82d88283f07bb9d15cf9b875990","observation_id":"a6ed4059-0caf-485e-a1f8-ab21fd853b8f","resolution":{"observed_at":"2026-08-06T18:31:35.125175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:35.100306Z","title":"https://archive.ics.uci.edu/dataset/256/daily+and+sports+ activities","venue":null,"work_id":"38f6fa97-bee6-4067-8356-a98d2c2a3d83","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.453869Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:a1d49d419d8e71554d9373d314d0a69025dad1b16d5ad57fd6e02ed1a049abb7","observation_id":"0b95a0f6-620f-4ecd-a3af-5cff6fb6cd1a","resolution":{"observed_at":"2026-08-06T18:31:35.106824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:35.078785Z","title":"https://archive.ics.uci.edu/dataset/341/smartphone+based+ recognition+of+human+activities+and+postural+transitions","venue":null,"work_id":"56ad28e9-c60c-463d-bbc7-3a666b22a3ec","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.500909Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:9b6d6905a9457b29663974992de4d0be05e190d19afb7c394485d0631831d3e5","observation_id":"acc37948-61e7-4b23-9131-aee3534dcd89","resolution":{"observed_at":"2026-08-06T18:31:35.084048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:35.058743Z","title":"https://archive.ics.uci.edu/dataset/319/mhealth+dataset","venue":null,"work_id":"f38f5b04-a0da-46f0-ada8-4456747161fc","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.572099Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:6ca2eac9cf0a84be51762bdd2d3adbef0ad684683bb7c7612c0e066136a34907","observation_id":"454718a5-2d52-417d-895f-a103fbb16b1a","resolution":{"observed_at":"2026-08-06T18:31:35.063709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:35.022061Z","title":"https://www.kaggle.com/datasets/malekzadeh/ motionsense-dataset","venue":null,"work_id":"a70c8d6b-4e02-44fe-904c-3810faf4d5bb","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.657212Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:87fc0f9e060c681f187d715a4581105085d80f3f51b2245333fbb587cf24f962","observation_id":"3e13882d-fac1-45dc-a605-0d69235cdd8d","resolution":{"observed_at":"2026-08-06T18:31:35.029698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:35.001371Z","title":"https://archive.ics.uci.edu/dataset/226/opportunity+activity+ recognition","venue":null,"work_id":"b859646a-317a-4e49-bece-a46e814de749","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.745853Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:32cc60eabe1c7aad2cfafdde38f3be609b6c15e20bb7f9171b57a5a7e012f897","observation_id":"5b6e506c-2f57-4644-8562-bb6517a09f4f","resolution":{"observed_at":"2026-08-06T18:31:35.007112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.980758Z","title":"https://archive.ics.uci.edu/dataset/231/pamap2+physical+ activity+monitoring","venue":null,"work_id":"358ba70a-f652-4606-8e08-23624d1395f1","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.812246Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:10b4aff6070afdd83971bd446e1cc350b055debe36212f16946ddc6c3d1d291a","observation_id":"8df14035-c85e-4bbf-9291-e39af31e6118","resolution":{"observed_at":"2026-08-06T18:31:34.988032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.960547Z","title":"https://zhaxidele.github.io/RecGym/","venue":null,"work_id":"9c5db6a8-8388-430a-ae91-8964c5f354e6","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.860612Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:8324a981f3b1fd1cf0b2a35695a2c155af6a054c8bbb352dba578381dc263c90","observation_id":"9776726e-c70b-47d6-980b-39c5ee116f4f","resolution":{"observed_at":"2026-08-06T18:31:34.966078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.930973Z","title":"https://www.uni-mannheim.de/dws/research/projects/activity- recognition/dataset/dataset-realworld/","venue":null,"work_id":"08bfc99b-2e54-4637-a57a-d38512e87879","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:31.926942Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:09deb8b7dde8ba1ff2298192f16418eea27e7360ea518ba339170357059d94c2","observation_id":"429f3030-f70a-4c19-a363-491a74ed90ef","resolution":{"observed_at":"2026-08-06T18:31:34.936396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.900431Z","title":"https://www.utwente.nl/en/eemcs/ps/research/dataset/","venue":null,"work_id":"660e421e-e284-409e-a6ec-884383e3ccf7","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.004673Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:4d66538c14d00901668f992326da0f60be3d3b13205b5d6c0e9f35385456f9d0","observation_id":"cdbd88af-7471-48de-85b0-bed4dc4e2975","resolution":{"observed_at":"2026-08-06T18:31:34.909225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.865550Z","title":"http://har-dataset.org/doku.php?id=wiki:dataset","venue":null,"work_id":"a1a298c7-5048-42e8-abcc-217ca641740b","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.094346Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:d296ff6dff3f6454f0edc17332a0968fb8a9a99a2fe966fa599413908de45739","observation_id":"a78a6bd6-be32-42e4-a591-6d40a8b0e4b8","resolution":{"observed_at":"2026-08-06T18:31:34.876971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.822838Z","title":"https://archive.ics.uci.edu/dataset/240/human+activity+ recognition+using+smartphones","venue":null,"work_id":"f0e7011b-a59b-4fc7-981b-9c6fcc4e3e6f","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.179660Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:557ac7b255f8d0cc94a9348fec41effa4f5d7982114a140f20a5ad1cd5679d3a","observation_id":"beafe836-0926-4694-8248-426c2cb8688b","resolution":{"observed_at":"2026-08-06T18:31:34.844567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.782003Z","title":"https://sipi.usc.edu/had/","venue":null,"work_id":"c08dd179-10c0-4fa4-8394-c6d6f979f3b9","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.241123Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:97ad32076a5f74b5b6e6e23be56aa876ab2e959e737c3a8f0cdd11d75760aeba","observation_id":"21a610d1-e859-4898-ab2c-108cf1ab745a","resolution":{"observed_at":"2026-08-06T18:31:34.787201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.748819Z","title":"https://archive.ics.uci.edu/dataset/507/wisdm+smartphone+ and+smartwatch+activity+and+biometrics+dataset","venue":null,"work_id":"35cf52d4-2e64-4511-b189-6ce1484fb0c7","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.327877Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:e6016025785b3200953f74a95f67cccbe144ca2b5225d76ed8ac28f681f417cd","observation_id":"bfbb7c45-e22d-4ce9-80f0-db3d95383855","resolution":{"observed_at":"2026-08-06T18:31:34.755028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.727195Z","title":null,"venue":null,"work_id":"b538b538-ae25-4377-9d5a-14e7c6dd5dba","year":2020},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.398109Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:9d10713b50c1fc252bb2a6825ee51ca2b180d80ecce22f29c0eb3d6dd04474fc","observation_id":"35bd0dcf-d8ed-4688-9ce9-e77fce6a6f93","resolution":{"observed_at":"2026-08-06T18:31:34.734388Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.706618Z","title":null,"venue":null,"work_id":"7eda6fc9-4fbc-4e3a-8d86-bbe2c2c47577","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.458502Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:9efa9879228949206dbeba920580998dfc734cc4f4c3282d2df687de0f1eab8f","observation_id":"e6fe0e75-683e-4262-a1f2-0e7cbe86f01c","resolution":{"observed_at":"2026-08-06T18:31:34.711675Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.687440Z","title":null,"venue":null,"work_id":"47dd6ec7-0963-420a-baf6-7152c18ebe6c","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.575540Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:91049d69dd371a49d50d2dfe5f11d6473204808a62db055dcc64554d1f107805","observation_id":"7d0f0eeb-a0e5-449b-8494-c71eea85d887","resolution":{"observed_at":"2026-08-06T18:31:34.692599Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.669169Z","title":null,"venue":null,"work_id":"69728c5a-2e91-41d0-8b98-3e08e3d2c68c","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.670188Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:f51f6b96fbec2d3ebbac03daefb14f88c809e1066f505c7bc911b29dbbdb7299","observation_id":"06ab39d9-b1c9-432f-9df4-0d1bc447d9d6","resolution":{"observed_at":"2026-08-06T18:31:34.674863Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:31:32.730036Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.730036Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:739194f9a3fa607ee481319ae74b459ee7a45141ff05c9e2d1d0d0a1ef01caaa","observation_id":"e439164c-a418-408f-82da-67ba04677d2b","resolution":{"observed_at":"2026-08-06T18:31:32.730036Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:31:32.770578Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.770578Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:6c03dbb3971d0f8ed912782d41f9d51236faaad630244c3a1df3b194e58feb3b","observation_id":"7e6ef2f5-5cd2-41a3-825c-ec157638c876","resolution":{"observed_at":"2026-08-06T18:31:32.770578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06311","last_updated":"2025-03-08T19:05:45Z","snapshot_observed_at":"2026-08-07T17:19:54.293664Z","submitted_at":"2025-03-08T19:05:45Z","title":"Hybrid CNN-Dilated Self-attention Model Using Inertial and Body-Area Electrostatic Sensing for Gym Workout Recognition, Counting, and User Authentification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06311","snapshot_observed_at":"2026-08-06T18:31:32.900614Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:32.900614Z"},"links":{"cited_paper":"/paper/2503.06311","citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:8129a97770ba7d0cc262596d6e4ef869903b631d387e9924bfdf40694f183acd","observation_id":"63842b96-7ba5-4e1d-89c3-496694e92f22","resolution":{"observed_at":"2026-08-06T18:31:32.900614Z","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":"2026-08-06T18:31:34.614049Z","title":null,"venue":null,"work_id":"50d48c8f-019d-48b3-8cb9-afe3b53366fd","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.017240Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:c224f0e6fd62b4550a5432679fbeaefd3a90f4ec085ec984cf34d3ed65d3b14a","observation_id":"cfb6a3ea-0c83-4e18-bfa3-7fe660384df2","resolution":{"observed_at":"2026-08-06T18:31:34.620676Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.594004Z","title":null,"venue":null,"work_id":"972c3a15-05e3-48a5-b38a-9a8bc2de9407","year":2023},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.191225Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:59caeb8652a9fab3a882fa862dc951bae561caf8a79382296e84046f9018e441","observation_id":"1bf0e01a-4688-4fa9-9009-eb2def2c8f91","resolution":{"observed_at":"2026-08-06T18:31:34.599662Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.575296Z","title":null,"venue":null,"work_id":"3eca2469-9c59-4486-a01b-2d54e7ec1f6b","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.326357Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:e12f3d3c9d3ccdc1fd5e18440c49189809838a1be6e7f36685c61703a974e2a7","observation_id":"e8318847-61f3-4487-820b-59ab2655bc23","resolution":{"observed_at":"2026-08-06T18:31:34.580469Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.556697Z","title":null,"venue":null,"work_id":"de8effd2-8ab6-491b-ad9a-ef65762e9b46","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.446529Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:a6e6869fb9141d3a0c3823ce4c5caa4ae4b594b704ba5c47b6a38c39fb71b74d","observation_id":"01571cfd-c945-445c-8f97-0d73409a7ed0","resolution":{"observed_at":"2026-08-06T18:31:34.562015Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09037","last_updated":"2024-12-12T07:53:17Z","snapshot_observed_at":"2026-07-06T20:05:46.205005Z","submitted_at":"2024-12-12T07:53:17Z","title":"Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09037","snapshot_observed_at":"2026-08-06T18:31:33.561835Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.561835Z"},"links":{"cited_paper":"/paper/2412.09037","citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:4e78ac4c69024ed8300139622c80404d5c0a86fcb81023905cbf0da3791afc55","observation_id":"24c2b8f8-d372-4dec-a98d-810593d23d7c","resolution":{"observed_at":"2026-08-06T18:31:33.561835Z","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":"2026-08-06T18:31:34.535543Z","title":null,"venue":null,"work_id":"80ba6417-0613-4f46-af3c-78c825c79c10","year":null},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.654798Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:3e4b43bbfec45075fe10eb1b60bddef1e58db40736fff337c5c417325ce8dce0","observation_id":"a3dc2466-9bc8-4c8c-9c42-4f4b99bafffb","resolution":{"observed_at":"2026-08-06T18:31:34.541776Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03364","last_updated":"2025-05-20T18:04:36Z","snapshot_observed_at":"2026-08-09T05:53:13.189969Z","submitted_at":"2025-02-05T17:00:08Z","title":"Scaling laws in wearable human activity recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03364","snapshot_observed_at":"2026-08-06T18:31:33.672568Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.672568Z"},"links":{"cited_paper":"/paper/2502.03364","citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:e944597f1ee2ae577c0725087b1a0aa25f989cd360189f08d226c7da9700b37c","observation_id":"8630383d-33ad-4c2d-bbaf-5b43443d949e","resolution":{"observed_at":"2026-08-06T18:31:33.672568Z","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":"2026-08-06T18:31:34.484220Z","title":null,"venue":null,"work_id":"0cf98e16-234e-49f6-87f8-9d8f49512439","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.678959Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:f4850e58144cdba32ed4989c67f4122ff66031e0e68a2183f235fbea9af287dc","observation_id":"2e97890d-6fd7-498b-84b1-d53d919d15a5","resolution":{"observed_at":"2026-08-06T18:31:34.492456Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.457422Z","title":null,"venue":null,"work_id":"27d924e3-7774-4068-8313-24e29749776e","year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.684953Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:4917184a8fb24fecf2dddeab9cbc03c8bef36576965320446086eff638d49c44","observation_id":"905d3c89-89e2-463c-854e-b9fe64f4c226","resolution":{"observed_at":"2026-08-06T18:31:34.465832Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.426624Z","title":null,"venue":null,"work_id":"4fe274fb-84e0-41c6-92dd-788ee8e49991","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.690611Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:c792636372657956c85770cf35d07edb9db21c330cd2fb00a00b306db31a10d9","observation_id":"c75a7e27-b000-4c47-af76-1f062dcfd055","resolution":{"observed_at":"2026-08-06T18:31:34.437552Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.03644","last_updated":"2024-07-04T05:32:54Z","snapshot_observed_at":"2026-07-06T18:41:18.308899Z","submitted_at":"2024-07-04T05:32:54Z","title":"On-Device Training Empowered Transfer Learning For Human Activity Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.03644","snapshot_observed_at":"2026-08-06T18:31:33.696989Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.696989Z"},"links":{"cited_paper":"/paper/2407.03644","citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:d816fcb0497c50f23f0fc28975b5c8bedcbef8fdc4ff8e877a40eb39125320a0","observation_id":"04723a86-a872-40de-8c54-d3078e54ab3f","resolution":{"observed_at":"2026-08-06T18:31:33.696989Z","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":"2026-08-06T18:31:34.405853Z","title":null,"venue":null,"work_id":"8740e6b5-3b0b-4b3c-bacc-b52c60dcafd4","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.702863Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:b753aacbd6f7e21d5b3c3a0bd3606570d761887f32b0e15be7cdc48ae10884d1","observation_id":"fb282fcd-45b7-4f17-a51e-aa321730c80f","resolution":{"observed_at":"2026-08-06T18:31:34.411594Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.383402Z","title":null,"venue":null,"work_id":"2034bcc0-35a6-493a-8951-1dd4872a04f4","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.708637Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:e560f0c87b9118ae4874fa2ae7a9ac1fd758ab96402715bfd8526319ce2ab292","observation_id":"8169d986-065e-45c7-a254-1ade536a813b","resolution":{"observed_at":"2026-08-06T18:31:34.389856Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.361496Z","title":null,"venue":null,"work_id":"c2b93576-3b8f-4626-a07b-5acc06c23d18","year":2023},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.714855Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:06a733aec3b80b879c106256520cb3cbacc5915e28f17ef14dddaffb296e5c5a","observation_id":"ace7b9b9-3cf9-48aa-aa58-dfdc16b79613","resolution":{"observed_at":"2026-08-06T18:31:34.367297Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:31:33.720511Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.720511Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:ffb82983078b9f2f12df9abf1a68715874eb90b0fee9ed37b959e1250956bf69","observation_id":"9205be36-43e1-468d-9089-b2079ecb68dc","resolution":{"observed_at":"2026-08-06T18:31:33.720511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15330","last_updated":"2025-01-25T21:39:01Z","snapshot_observed_at":"2026-07-06T20:26:12.109891Z","submitted_at":"2025-01-25T21:39:01Z","title":"Assessing the Impact of Sampling Irregularity in Time Series Data: Human Activity Recognition As A Case Study","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15330","snapshot_observed_at":"2026-08-06T18:31:33.729147Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.729147Z"},"links":{"cited_paper":"/paper/2501.15330","citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:7dc593a3e4de5d19d2249aec9a598c165a3e13183e79dd461eee90cdacfa79ba","observation_id":"f59086d2-6778-43c1-94c2-5af3bfd46c68","resolution":{"observed_at":"2026-08-06T18:31:33.729147Z","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":"2026-08-06T18:31:34.328238Z","title":null,"venue":null,"work_id":"2d0b885c-4634-43a2-ba01-79ffbcb5966a","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.743524Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:ee5f1cf905b36b8d3ba8e7eb90be0bd6f22dc3cf154d615b8bdcc885d17c4264","observation_id":"47866007-3276-4cfb-89b4-10c389204baf","resolution":{"observed_at":"2026-08-06T18:31:34.333205Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.309676Z","title":null,"venue":null,"work_id":"f96b9c43-2345-476a-87d9-b4fbd1af1969","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.749808Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:0737f990540c6162d11bd29ba0df4f3d47aac33665184e81db37dc7e15eea77b","observation_id":"47f04fa6-4300-4fc3-86fa-525517741070","resolution":{"observed_at":"2026-08-06T18:31:34.315221Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:31:33.756613Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.756613Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:bbbc98a1e857ab56f60c76ffabc98c3ef00beac43c475e69070ec19b8abaec4d","observation_id":"2c7ddd37-566d-49f3-81dd-e396bd5a971a","resolution":{"observed_at":"2026-08-06T18:31:33.756613Z","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":"2026-08-06T18:31:34.269590Z","title":null,"venue":null,"work_id":"cd329d9b-336d-4aa8-acff-0c793d84de52","year":2023},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.762791Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:fa41fd9d229f29364d92d10a15340ddfd265b2f026839a5039b990605fef3a4d","observation_id":"12fb3305-2971-49b7-8fdb-683fc50414b4","resolution":{"observed_at":"2026-08-06T18:31:34.275617Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.245296Z","title":null,"venue":null,"work_id":"91db67e5-083c-4649-9a83-32caf092f6b3","year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.768634Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:c443436d902e2dfed0560e1a856f008a3e59479bd6eb7fac6c4d343c2533c07a","observation_id":"f79c2f2e-13d6-4f04-a2ee-6a9b7c8a2db9","resolution":{"observed_at":"2026-08-06T18:31:34.253915Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.215507Z","title":null,"venue":null,"work_id":"3f021731-9b6b-471e-b8f5-9f8f56bfd099","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.773365Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:902fb76b85b2b04126f07b40b22fa5cec5e119a24057983e1214897d1087ae6f","observation_id":"30c805cc-cc75-427c-a896-7d4612b98b0e","resolution":{"observed_at":"2026-08-06T18:31:34.224369Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.196492Z","title":null,"venue":null,"work_id":"5fa55394-58d0-43e8-86b2-830c4be6a4d0","year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.780516Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:dbab5640375532681e9b5696100583369bce94f616e40f4f5028e0d6725fa6b7","observation_id":"5efa5e9e-905d-4347-8e64-749e8b35e7f0","resolution":{"observed_at":"2026-08-06T18:31:34.201555Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.177415Z","title":null,"venue":null,"work_id":"d3a5491d-5269-44fc-8f0f-4b76efa048e9","year":null},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.785754Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:861822c66cf930f59b3b49352d00f031fb157793a6229616741c76c5e344588b","observation_id":"f48f53b0-6b80-4f9c-9d25-17e183ac4354","resolution":{"observed_at":"2026-08-06T18:31:34.182794Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.125905Z","title":null,"venue":null,"work_id":"58385d7d-0873-4885-8850-20736552dfc3","year":2025},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.795171Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:d92c65e512aefbbd978b7b65b919a403308a3fbad05add7edd2287221f559588","observation_id":"f07fd3d5-7159-4d35-829c-f1f9b6a96741","resolution":{"observed_at":"2026-08-06T18:31:34.131265Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.104117Z","title":null,"venue":null,"work_id":"6e856c2a-44bc-4047-a1ec-327cf2dbc312","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.800353Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:1829e5c96f79c6821de86831a12ffe61324c60383d604359ddc88811feff721e","observation_id":"640ae83b-0427-4326-94fc-c2b490f4884d","resolution":{"observed_at":"2026-08-06T18:31:34.111152Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.084631Z","title":null,"venue":null,"work_id":"7b46b9c9-8935-4f5f-b52b-c7f99d6dd71c","year":2023},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.809279Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:e8c364cf7c085dd34f091ec37e6f21abea12ae8b63390d42d5914d282d4f0d6e","observation_id":"c91588d5-6564-40dc-b1d4-029c513de987","resolution":{"observed_at":"2026-08-06T18:31:34.089515Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.067343Z","title":null,"venue":null,"work_id":"3b00998f-b1a9-462e-a237-0476241925e0","year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.815698Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:33b7a774acad4b2f6b288bf7ef361b6aa4dbe0ce960c04f521225d1014892bee","observation_id":"040c5fa6-be72-409a-a46e-71d93daa198a","resolution":{"observed_at":"2026-08-06T18:31:34.073429Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.047809Z","title":null,"venue":null,"work_id":"17a6d269-8323-459c-b94c-e18c59f7922a","year":2024},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.823084Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:bfe7f838dd61236eb1a391c2046d300a267c1044bc61fedcfc0215616470da5e","observation_id":"d555d97d-e30a-4ad9-b91e-93acd9750768","resolution":{"observed_at":"2026-08-06T18:31:34.053321Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.028925Z","title":null,"venue":null,"work_id":"34442d54-7b14-4074-b1bf-09a9b76d1dac","year":2022},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.829583Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:d4ac4ad521b8fc633203eb16906b67fbc45a6508288538651d8c2da1cd7799bd","observation_id":"30a4c5f5-d83e-4558-a32e-b690e827770a","resolution":{"observed_at":"2026-08-06T18:31:34.034699Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.003359Z","title":null,"venue":null,"work_id":"e6ef1779-df53-4359-b3f6-d0fdc63141b3","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.836249Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:86c28d110872c431d6ceabd6b11797168a09991eb8f2f2f4348c00dce54e130f","observation_id":"0e99bd62-e036-47f9-86d7-b3af7967b2a8","resolution":{"observed_at":"2026-08-06T18:31:34.015298Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.154865Z","title":"In Proceedings of the 26th ACM international conference on Multimedia","venue":null,"work_id":"fa2f1c5b-7271-4ff6-aefa-768caec01a55","year":null},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.790405Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:df08441877ca4356355539b571ff771f8a9dcc2498079e1b691d6b9b11c08e26","observation_id":"681ebc06-cecc-4198-aeec-6472703f6c50","resolution":{"observed_at":"2026-08-06T18:31:34.161939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:31:34.514053Z","title":"Neural Computing and Applications 33 (2021), 13705–13722","venue":null,"work_id":"b09996c8-e524-42fa-8811-12a99cb679d6","year":2021},"citing_paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T18:31:33.664790Z"},"links":{"citing_paper":"/paper/2507.07949"},"observation_digest":"sha256:8f098a936f57825d481886518010c2187b126758534bfeff6a889fdf869415e6","observation_id":"3d8642b4-5a09-4651-bbdc-08efd4b964fc","resolution":{"observed_at":"2026-08-06T18:31:34.520768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07949","last_updated":"2025-07-10T17:33:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T18:26:08.238716Z","submitted_at":"2025-07-10T17:33:52Z","title":"TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":0,"verified_fuzzy":16},"total_outbound_references":54},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 1 inbound Pith citation observation for arXiv:2507.07949."}