{"paper":{"title":"Restoring CFAR Validity for Single-Channel IoT Sensor Streams: A Monte Carlo Comparison of Five Detectors under Cortex-M0+ Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The Temporal Spectral Noise-Floor Adaptation detector achieves high detection rate, 100% precision, and low bandwidth where classical CFAR methods fail in IoT sensor streams.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Lars Thomsen, Sergii Makovetskyi","submitted_at":"2026-05-15T16:39:30Z","abstract_excerpt":"Real-time event detection in IoT mesh sensor networks must balance sensitivity against false-positive load on a constrained mesh radio. We present a Monte Carlo comparison of the Temporal Spectral Noise-Floor Adaptation (TSNFA) detector against four classical comparators drawn from the radar Constant False Alarm Rate (CFAR) family and from sequential change detection: the Lipski FFT energy detector, Cell-Averaging CFAR (CA-CFAR), Ordered-Statistic CFAR (OS-CFAR), and state-machine Cumulative Sum (CUSUM). All five detectors are implemented to fit a Cortex-M0+ class envelope, process a 1-D 100 H"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TSNFA is the only algorithm tested that simultaneously achieves high detection rate, high precision, and low per-node bandwidth.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The factorial Monte Carlo configurations (10/50 nodes, 12/18 dB SNR, 24-hour runs repeated five times) sufficiently represent the statistical properties of real single-channel IoT sensor streams under Cortex-M0+ constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Monte Carlo evaluation shows TSNFA detector achieves 99.97-100% detection rate, 100% precision, and zero false-positive clusters per node while classical CFAR and CUSUM variants each fail on at least one performance dimension under Cortex-M0+ constraints.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Temporal Spectral Noise-Floor Adaptation detector achieves high detection rate, 100% precision, and low bandwidth where classical CFAR methods fail in IoT sensor streams.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"413f28cbfe847ff51db828877b1b2a73bbc50597cbb7a1868ae77afd64d20632"},"source":{"id":"2605.16159","kind":"arxiv","version":1},"verdict":{"id":"1961b5f0-cc7e-43a6-928e-762604f37674","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:21:50.803775Z","strongest_claim":"TSNFA is the only algorithm tested that simultaneously achieves high detection rate, high precision, and low per-node bandwidth.","one_line_summary":"Monte Carlo evaluation shows TSNFA detector achieves 99.97-100% detection rate, 100% precision, and zero false-positive clusters per node while classical CFAR and CUSUM variants each fail on at least one performance dimension under Cortex-M0+ constraints.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The factorial Monte Carlo configurations (10/50 nodes, 12/18 dB SNR, 24-hour runs repeated five times) sufficiently represent the statistical properties of real single-channel IoT sensor streams under Cortex-M0+ constraints.","pith_extraction_headline":"The Temporal Spectral Noise-Floor Adaptation detector achieves high detection rate, 100% precision, and low bandwidth where classical CFAR methods fail in IoT sensor streams."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16159/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.748723Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:31:12.057142Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T18:22:01.996121Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.037876Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:48.221298Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.438532Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"686321dc00c5c7b11c194ccf8799f93075d6ac94e5e1160e1c8ef27db9e45116"},"references":{"count":23,"sample":[{"doi":"","year":2000,"title":"with the Tartakovsky linear-quadratic instantaneous log- likelihood ratio [6] as the per-sample increment. A third class, TinyML autoencoder anomaly detection [7], is excluded from the present compari","work_id":"fd4cd6ec-152f-4307-a91b-719e9c9e0988","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"X[k] <- FFT(x) for k in K = {1,...,6}","work_id":"da57c301-5087-488e-8401-51fde0af554d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"|X_k| <- sqrt(Re(X_k)^2 + Im(X_k)^2)","work_id":"640ea23f-2b22-4217-90b7-adc9d512d745","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"for each bin k in K do:","work_id":"da5610e9-186a-4772-b859-868988cc66a4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"insert |X_k| into B_d,k","work_id":"3c1bbc40-e47f-4724-94f9-8232457dd037","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"8caddcf08f052ebc443e05530faa2a2623dcfc44359763f8e57c5d0d0e42c6a9","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}