{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4FRWERRYJFDTTKL6ILZ24KR4LZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b41e1ac4e50b9c18a4b516f21ea057eae9c978954984f211bf6a769a5358c633","cross_cats_sorted":["cs.AI","eess.IV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T21:13:56Z","title_canon_sha256":"9a8b912843987b034c5ca861ddec9bbecc940db33e27dafd3079589d9008adf4"},"schema_version":"1.0","source":{"id":"2605.15423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15423","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15423v1","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15423","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"4FRWERRYJFDT","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"4FRWERRYJFDTTKL6","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"4FRWERRY","created_at":"2026-05-20T00:00:57Z"}],"graph_snapshots":[{"event_id":"sha256:20e275b736e0374124b5d61e0eee4642fb5df21bdaac06780df2dcbdb4be5f6a","target":"graph","created_at":"2026-05-20T00:00:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our method yields up to 55% energy savings compared to processing only full-resolution images, enabling the first real-time Transformer-based VOD on an MCU-class embedded vision node."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The Rescore algorithm, which applies probability union rules to aggregate detection confidence scores across frames, can reliably correct misclassifications from low-resolution inferences without degrading overall performance."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MR2-ByteTrack maintains high accuracy in video object detection on MCUs by combining multi-resolution processing, ByteTrack for frame linking, and Rescore for confidence aggregation, achieving up to 55% energy savings and real-time performance for both CNN and Transformer models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MR2-ByteTrack enables video object detection with up to 55% energy savings on microcontroller-based vision sensors by alternating resolutions and rescoring detections."}],"snapshot_sha256":"2180dee21ad4a78081f79ac03e737ebfab3b0c4aa68bb52c8ee46d54dc925f64"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"e2c1c1298ab6d1159b1d591e913997ca449f043b96af8393d1df7bdd8dcc02bb"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T16:21:58.911783Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T15:50:40.754606Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.785083Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:30:42.762899Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.139672Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.701953Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15423/integrity.json","findings":[],"snapshot_sha256":"dc27aab67f5779495d37343b22b2db1cd84271c81e276179a306c6e055cdb9a3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern smart vision sensors need on-device intelligence to process video streams, as cloud computing is often impractical due to bandwidth, latency, and privacy constraints. However, these sensory systems typically rely on ultra-low-power microcontrollers (MCUs) with limited memory and compute, making conventional video object detection methods, which require feature storage or multi-frame buffering, unfeasible. To address this challenge, we introduce Multi-Resolution Rescored ByteTrack (MR2-ByteTrack), a Video Object Detection (VOD) method tailored for MCU-based embedded vision nodes. MR2-Byt","authors_text":"Daniele Palossi, Francesco Conti, Luca Benini, Luca Bompani, Manuele Rusci","cross_cats":["cs.AI","eess.IV"],"headline":"MR2-ByteTrack enables video object detection with up to 55% energy savings on microcontroller-based vision sensors by alternating resolutions and rescoring detections.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T21:13:56Z","title":"MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes"},"references":{"count":70,"internal_anchors":7,"resolved_work":70,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"S. C. Mukhopadhyay, S. K. S. Tyagi, N. K. Suryadevara, V . Piuri, F. Scotti, and S. Zeadally, ‘‘Artificial intelligence-based sensors for next generation iot applications: A review,’’IEEE Sensors Jour","work_id":"5496f742-a5df-49d2-8961-291fa140d355","year":2021},{"cited_arxiv_id":"","doi":"10.1007/s10462-022-10141-4","is_internal_anchor":false,"ref_index":2,"title":"W. Su, L. Li, F. Liu, M. He, and X. Liang, ‘‘Ai on the edge: a comprehensive review,’’Artif. Intell. Rev., vol. 55, no. 8, p. 6125–6183, Dec. 2022. [Online]. Available: https://doi.org/10.1007/s10462-","work_id":"725f0cdd-f1f3-4bfb-b1d9-f7f1c60e21b3","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"W. Y u, F. Liang, X. He, W. G. Hatcher, C. Lu, J. Lin, and X. Y ang, ‘‘A survey on the edge computing for the internet of things,’’IEEE Access, vol. 6, pp. 6900–6919, 2018","work_id":"569827dc-1a1f-4389-9b95-5f67fbaff3c5","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"K. S. Patle, R. Saini, A. Kumar, and V . S. Palaparthy, ‘‘Field evaluation of smart sensor system for plant disease prediction using lstm network,’’ IEEE Sensors Journal, vol. 22, no. 4, pp. 3715–3725","work_id":"0c21bad2-bcdf-4f7a-ad83-e35275c434d0","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A. Sabato, S. Dabetwar, N. N. Kulkarni, and G. Fortino, ‘‘Noncontact sensing techniques for ai-aided structural health monitoring: A systematic review,’’IEEE Sensors Journal, vol. 23, no. 5, pp. 4672–","work_id":"b7740639-464a-4ad2-8e56-992b276b9230","year":2023}],"snapshot_sha256":"7ba3bd85a010425eb1b8c9d8d73464aeb01d85e22bd23eb46a9e5c50ea838de7"},"source":{"id":"2605.15423","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:20:15.327680Z","id":"d1fb2793-35f1-42dc-a929-722e7972751c","model_set":{"reader":"grok-4.3"},"one_line_summary":"MR2-ByteTrack maintains high accuracy in video object detection on MCUs by combining multi-resolution processing, ByteTrack for frame linking, and Rescore for confidence aggregation, achieving up to 55% energy savings and real-time performance for both CNN and Transformer models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MR2-ByteTrack enables video object detection with up to 55% energy savings on microcontroller-based vision sensors by alternating resolutions and rescoring detections.","strongest_claim":"our method yields up to 55% energy savings compared to processing only full-resolution images, enabling the first real-time Transformer-based VOD on an MCU-class embedded vision node.","weakest_assumption":"The Rescore algorithm, which applies probability union rules to aggregate detection confidence scores across frames, can reliably correct misclassifications from low-resolution inferences without degrading overall performance."}},"verdict_id":"d1fb2793-35f1-42dc-a929-722e7972751c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b4a07007a9639a859bc53ce8126ee49aa3ee797b20b3bb21a885e133000c1968","target":"record","created_at":"2026-05-20T00:00:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b41e1ac4e50b9c18a4b516f21ea057eae9c978954984f211bf6a769a5358c633","cross_cats_sorted":["cs.AI","eess.IV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T21:13:56Z","title_canon_sha256":"9a8b912843987b034c5ca861ddec9bbecc940db33e27dafd3079589d9008adf4"},"schema_version":"1.0","source":{"id":"2605.15423","kind":"arxiv","version":1}},"canonical_sha256":"e163624638494739a97e42f3ae2a3c5e5bee0c6a099dde5c501a5eb1c80ffb92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e163624638494739a97e42f3ae2a3c5e5bee0c6a099dde5c501a5eb1c80ffb92","first_computed_at":"2026-05-20T00:00:57.844623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:57.844623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vb/s01+iUzCAFjo6WJwENp37BMUim60Dt7clx16MTTeXmeWRRdQgl+bNV1/rBSnneIIlM6Xo3k51Z4gky1/IDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:57.845439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4a07007a9639a859bc53ce8126ee49aa3ee797b20b3bb21a885e133000c1968","sha256:20e275b736e0374124b5d61e0eee4642fb5df21bdaac06780df2dcbdb4be5f6a"],"state_sha256":"a3e3155d02b1aed1688890dfa2aa45e45765cdf5ae208cf1febf6d9cc7999c50"}