{"as_of":"2026-08-18T15:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ef21f80eb4c2e3e60c7bd521f7b4cf53bb5b3ea6bdfcb1c7aba40bd3c895d698","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:23:41.361418Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2508.12905/citation-record","integrity":"/paper/2508.12905/integrity","json":"/paper/2508.12905/citation-record.json","paper":"/paper/2508.12905"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.07511","last_updated":"2022-12-07T05:08:01Z","snapshot_observed_at":"2026-08-16T03:05:56.678791Z","submitted_at":"2021-07-15T17:59:50Z","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07511","snapshot_observed_at":"2026-08-15T17:23:40.774106Z","title":"Angelopoulos and Stephen Bates","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.774106Z"},"links":{"cited_paper":"/paper/2107.07511","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:b18b728c63a8a11b79b898a3efeffaab190bd5fd26df6d5fa5663289e72d393c","observation_id":"f8193d3a-7119-4ba9-a946-e15e4860c21b","resolution":{"observed_at":"2026-08-15T17:23:40.774106Z","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":"2026-08-15T17:23:41.519260Z","title":"Abstention budget adherence","venue":null,"work_id":"8c565405-d56d-45c8-a130-feceb1886200","year":2023},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.361418Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:7ecf6f9a8ed3f85b5fde0947a1752eb1af39a270bef194b23d2187c04574e5a1","observation_id":"536c9bf0-e64e-4f66-8807-671a04274b11","resolution":{"observed_at":"2026-08-15T17:23:41.574308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12599","last_updated":"2024-11-16T06:34:58Z","snapshot_observed_at":"2026-08-18T08:49:30.596645Z","submitted_at":"2024-04-19T03:06:50Z","title":"QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12599","snapshot_observed_at":"2026-08-15T17:23:40.789154Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.789154Z"},"links":{"cited_paper":"/paper/2404.12599","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:7e4f7dc58d51cfe83649ea1ba546aa4da9eeaecabe62ddd71e5f815902c78a95","observation_id":"08b8659e-ee71-4647-a341-e4a01e65283c","resolution":{"observed_at":"2026-08-15T17:23:40.789154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.00170","last_updated":"2021-10-28T17:04:20Z","snapshot_observed_at":"2026-08-17T14:56:53.253367Z","submitted_at":"2021-06-01T01:37:32Z","title":"Adaptive Conformal Inference Under Distribution Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.00170","snapshot_observed_at":"2026-08-15T17:23:40.845727Z","title":"org/abs/2106.00170","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.845727Z"},"links":{"cited_paper":"/paper/2106.00170","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:f8af3038b78db224bac1d2966953503219d2c1e2b09d42fe51a5c5fcdc4fb190","observation_id":"b06c0085-72a0-4d05-8125-96698d551bc3","resolution":{"observed_at":"2026-08-15T17:23:40.845727Z","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":"2026-08-15T17:23:41.099768Z","title":"Branchynet: Fast inference via early exiting from deep neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.099768Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:a6e713dc57f38d715df5096aa2b5653fee2847db039d8534910c5fa52f68e68d","observation_id":"6c47e2d6-2195-4987-89e6-cefaabef7e05","resolution":{"observed_at":"2026-08-15T17:23:41.099768Z","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":"2026-08-15T17:23:41.582901Z","title":"(2019) in our discussion but do not optimize for them","venue":null,"work_id":"2c83acd8-39f8-47a4-922f-2bc4c9b161d8","year":2019},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.356625Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:beadde3763657b99edae42fc9890fa1ce5957c640194eeb5c00fe428bbe8ebf8","observation_id":"c63b0b9c-a7fd-4777-afe8-ccd11add85e7","resolution":{"observed_at":"2026-08-15T17:23:41.586953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:42.197368Z","title":"Accessed: 2025-08-","venue":null,"work_id":"ad487c0d-556e-421a-9b04-a02b2781d25d","year":2025},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.094463Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:9ee3083758e303644e2f439cd4b2e7099bf017b38d150a937543e8eee4a24864","observation_id":"030815cc-dc2a-4600-8dd7-031520457c21","resolution":{"observed_at":"2026-08-15T17:23:42.207066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-15T17:23:41.112637Z","title":"Fashion-mnist: A novel image dataset for benchmark- ing machine learning algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.112637Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:fb79b0e6cc289a895864997c813d5ae7ed91cac5842dcb428e519dae0727d991","observation_id":"7ed230da-fd27-4c14-adf1-dd08fc3aa6ed","resolution":{"observed_at":"2026-08-15T17:23:41.112637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07128","last_updated":"2018-02-14T19:24:55Z","snapshot_observed_at":"2026-08-17T23:16:10.034718Z","submitted_at":"2017-11-20T03:19:03Z","title":"Hello Edge: Keyword Spotting on Microcontrollers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07128","snapshot_observed_at":"2026-08-15T17:23:41.116882Z","title":"Yue Zheng, Yuhao Chen, Bin Qian, Xiufang Shi, Yuanchao Shu, and Jiming Chen","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.116882Z"},"links":{"cited_paper":"/paper/1711.07128","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:ea979490a7105176de7a7a34934219f661e4749410b4538e0ce5e7216b14b083","observation_id":"a7d7e9ce-40ea-4a3d-9847-4f9a53bad4c7","resolution":{"observed_at":"2026-08-15T17:23:41.116882Z","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":"2026-08-15T17:23:42.076568Z","title":null,"venue":null,"work_id":"be3a5579-6386-4b87-b717-a8b9a8cadbb8","year":2020},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.124398Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:494940a0c464d9b897ba4af0596c16bd2c1def0759df3c480496b6778266a8c7","observation_id":"b4cc2f8c-0c9a-48d4-be95-d124e1e93194","resolution":{"observed_at":"2026-08-15T17:23:42.080490Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.936938Z","title":"14 Preprint A.2 D ATASETS We evaluate TCUQ and all baseline methods on four in-distribution datasets spanning both vision and audio, following standard TinyML evaluation practice","venue":null,"work_id":"b8b09e2a-c9d2-445c-827c-b19bfd7a7526","year":2018},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.127988Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:d31a699faf0552ed663b0bb3e65e9c096ee379a112a63159abbcbaea92c4b32c","observation_id":"5c168994-7a5e-4607-b697-7f8b5733e01c","resolution":{"observed_at":"2026-08-15T17:23:42.005186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.925492Z","title":"For SpeechCmd, we convert raw WA V to Mel spectrograms (49×10×1) using a fixed front end; for vision datasets we apply standard per-dataset normalization","venue":null,"work_id":"728a6bd7-a51a-49ae-97ab-e98f001a22f0","year":2017},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.131624Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:d7543995e74aba44e1108feae252283e03bf1c3f1b7bea2ed07a92fa3d1829f7","observation_id":"535de6bf-253c-49cd-b33c-b9e40f1ad255","resolution":{"observed_at":"2026-08-15T17:23:41.929279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.857739Z","title":"While TS can improve calibration in static settings, it does not exploit temporal structure, streaming adaptation, or feature-level consistency, which are central to TCUQ","venue":null,"work_id":"6d21e822-7257-49b0-a5a4-095158cc48b4","year":2021},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.135800Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:6af488d170830c432936158af6704f0f38d64f0a8768cc9bf9d6159dee156309","observation_id":"b34b21c4-36d1-4e5c-b822-f0e678d66c47","resolution":{"observed_at":"2026-08-15T17:23:41.917012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.788637Z","title":"Recent approaches such as Meronen et al","venue":null,"work_id":"10b2b686-4553-416c-a1e7-691fa08a2863","year":2024},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.139716Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:365fde53a90698c49078134f15e0ebbb93a8cb899b9eb41930953c35d4d194df","observation_id":"f164f0bd-1c45-492a-b09c-d9f4813e4175","resolution":{"observed_at":"2026-08-15T17:23:41.793493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.765799Z","title":"PostN employs normalizing flows to model a predictive distribution for each input without increasing runtime memory requirements","venue":null,"work_id":"dbaba8ce-e2c6-4710-8887-deb8cad3257e","year":2020},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.144192Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:30c89032151f43a14e2d23add20ebc48a7203cbbdf143e915260e493fa831584","observation_id":"025d3649-a9b5-44f9-959b-df679f264ff0","resolution":{"observed_at":"2026-08-15T17:23:41.778987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.712776Z","title":null,"venue":null,"work_id":"2d1816ab-55e4-402c-8c10-25ad86b60dbf","year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.148735Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:758202766d6488d538df5ee5431843c38b5bfe0809a5fa368112c15e669fb6db","observation_id":"0c88c918-8ce3-409d-b51f-363f59a3ea39","resolution":{"observed_at":"2026-08-15T17:23:41.716887Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.699683Z","title":"wait for more context","venue":null,"work_id":"cef12e9e-4b2f-4379-a064-dd2cd6d7d155","year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.174438Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:0902f237d252076511b562778e1e0ad065fc8c1e74ded1e48211bc2652a4bdef","observation_id":"de63658b-44ef-4a18-87e6-2ab4efafb43c","resolution":{"observed_at":"2026-08-15T17:23:41.704055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.595573Z","title":"Let the prediction confidence be c(x) = maxℓpϕ(y =ℓ| x)","venue":null,"work_id":"7a8c2971-e480-4da2-897a-4693684ae1a6","year":2019},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.275978Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:c614700421a7e7e8d8605d0f7291e6e9f15ee7b930a0de15547abf96f51f9ad7","observation_id":"85400bc9-9c17-482f-92da-f15933d93621","resolution":{"observed_at":"2026-08-15T17:23:41.648469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:23:41.079341Z","title":"Shiyu Liang, Yixuan Li, and R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.079341Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:f2a8ea40be3627f0d912c3cf293e258700d33cd3729b89487fd198aecf591fca","observation_id":"dbdd8811-fa03-48b3-819e-65b6fb64b18c","resolution":{"observed_at":"2026-08-15T17:23:41.079341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04694","last_updated":"2021-03-19T11:25:46Z","snapshot_observed_at":"2026-08-14T07:45:28.686579Z","submitted_at":"2020-01-14T10:13:52Z","title":"Hydra: Preserving Ensemble Diversity for Model Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.04694","snapshot_observed_at":"2026-08-15T17:23:41.104754Z","title":"Hydra: Preserving ensemble diversity for model distillation","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.104754Z"},"links":{"cited_paper":"/paper/2001.04694","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:29f6105da6eecae280b07d60016d3549b82eb1ad0d03a4ea8cbc1894e2a6706c","observation_id":"8ce848f2-1fd9-4603-9a1c-c5f10a63f3c3","resolution":{"observed_at":"2026-08-15T17:23:41.104754Z","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":"2026-08-15T17:23:41.014877Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.014877Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:568bb33d7a1b48dbbd36223dd6fa9d708b0e41f7d277a8d9c2933b7bbe9c3e48","observation_id":"e343966b-4383-475e-891f-2c9932558816","resolution":{"observed_at":"2026-08-15T17:23:41.014877Z","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":"2026-08-15T17:23:42.289673Z","title":"Accessed: 2025-08-","venue":null,"work_id":"5dde9216-ad7e-4e6d-a5a8-a95b1c48c1e2","year":2025},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.090110Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:f08ce158c6926642c6ca73f72cc0929a7c559df9319b85f5655bff1207996fae","observation_id":"501a1a1e-a052-4c23-b832-f6657edd6db6","resolution":{"observed_at":"2026-08-15T17:23:42.305566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-15T17:23:40.942849Z","title":"Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.942849Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:b1d8aa6e73b4418cd1ec5bff5cb626d59caf490c1fa677abb8f475c5c3eb24cd","observation_id":"fcaad608-e1e4-497f-817a-868c17c7f2f1","resolution":{"observed_at":"2026-08-15T17:23:40.942849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-08-15T16:28:51.252929Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-15T17:23:41.108323Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.108323Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:2f5c68c8e90e515051c48de6bcde1e928d0fd53f73d980314cb5602dd90a682c","observation_id":"e9db4fe8-1c6f-4465-914e-7b98702413b9","resolution":{"observed_at":"2026-08-15T17:23:41.108323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.06848","last_updated":"2021-03-18T11:26:59Z","snapshot_observed_at":"2026-08-17T16:58:08.665315Z","submitted_at":"2020-06-11T21:53:15Z","title":"Getting a CLUE: A Method for Explaining Uncertainty Estimates","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.06848","snapshot_observed_at":"2026-08-15T17:23:40.779011Z","title":"arXiv:2006.06848","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.779011Z"},"links":{"cited_paper":"/paper/2006.06848","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:2060365c2ad8ca28ddc5317bce046b72ec897d3a50e8407f48faddd20aecd7eb","observation_id":"b8b1abc1-ec61-4699-8b99-c115607f010c","resolution":{"observed_at":"2026-08-15T17:23:40.779011Z","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":"2026-08-15T17:23:40.784814Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:40.784814Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:7ee03b06956533e91699148b22ff390871a4473f262b1143296a53b896339561","observation_id":"ba7e2312-e135-44b7-aa2b-3c261a5544ea","resolution":{"observed_at":"2026-08-15T17:23:40.784814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02337","last_updated":"2019-06-05T22:23:43Z","snapshot_observed_at":"2026-08-14T16:20:09.671705Z","submitted_at":"2019-06-05T22:23:43Z","title":"MNIST-C: A Robustness Benchmark for Computer Vision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02337","snapshot_observed_at":"2026-08-15T17:23:41.083891Z","title":"Mnist-c: A robustness benchmark for computer vision","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.083891Z"},"links":{"cited_paper":"/paper/1906.02337","citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:00ba64f42299fb1b129929c5a69615e7a387150a719e838810045ee129960e7c","observation_id":"fba876e8-c4c8-407d-a16e-e8aaeda9a531","resolution":{"observed_at":"2026-08-15T17:23:41.083891Z","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":"2026-08-15T17:23:42.089794Z","title":null,"venue":null,"work_id":"b98c3931-1bf2-4472-aaa8-92c49900488b","year":2016},"citing_paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T17:23:41.120728Z"},"links":{"citing_paper":"/paper/2508.12905"},"observation_digest":"sha256:88e2bab4d3cfb5ba295cec21d45c8b02a886351f05c67f1c811cb523d54e580a","observation_id":"f5700d28-c554-4d94-8da9-50e629c10815","resolution":{"observed_at":"2026-08-15T17:23:42.160273Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.12905","last_updated":"2025-08-18T13:12:14Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T16:58:53.406493Z","submitted_at":"2025-08-18T13:12:14Z","title":"TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":28},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2508.12905."}