{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RFHA6EANOKRKIKZILMZ6LAF3C5","short_pith_number":"pith:RFHA6EAN","schema_version":"1.0","canonical_sha256":"894e0f100d72a2a42b285b33e580bb174189b29332c784ea4d0826ad9cc35e71","source":{"kind":"arxiv","id":"2010.08678","version":3},"attestation_state":"computed","paper":{"title":"TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Advait Jain, Ian Nappier, Jared Duke, Jian Li, Meghna Natraj, Nat Jeffries, Nick Kreeger, Pete Warden, Robert David, Rocky Rhodes, Shlomi Regev, Tiezhen Wang, Vijay Janapa Reddi","submitted_at":"2020-10-17T00:44:30Z","abstract_excerpt":"Deep learning inference on embedded devices is a burgeoning field with myriad applications because tiny embedded devices are omnipresent. But we must overcome major challenges before we can benefit from this opportunity. Embedded processors are severely resource constrained. Their nearest mobile counterparts exhibit at least a 100 -- 1,000x difference in compute capability, memory availability, and power consumption. As a result, the machine-learning (ML) models and associated ML inference framework must not only execute efficiently but also operate in a few kilobytes of memory. Also, the embe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.08678","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T00:44:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"999078c37cb17074bbe89f7620be2b9b757e427b7487445453ad115ca1585143","abstract_canon_sha256":"4722e23e17910aea52516377b6cd2624c45fb05f35ca5caef24c9794092fb8fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:38.764592Z","signature_b64":"tFTWXYy9IfaDzZgrv3SaN7BOcoR6N8L7K4MIPRdWcEmqokKp49C6PZ28pXgRyUuOjl7hXILlr4KWkdHKozqdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894e0f100d72a2a42b285b33e580bb174189b29332c784ea4d0826ad9cc35e71","last_reissued_at":"2026-07-05T02:22:38.764044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:38.764044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Advait Jain, Ian Nappier, Jared Duke, Jian Li, Meghna Natraj, Nat Jeffries, Nick Kreeger, Pete Warden, Robert David, Rocky Rhodes, Shlomi Regev, Tiezhen Wang, Vijay Janapa Reddi","submitted_at":"2020-10-17T00:44:30Z","abstract_excerpt":"Deep learning inference on embedded devices is a burgeoning field with myriad applications because tiny embedded devices are omnipresent. But we must overcome major challenges before we can benefit from this opportunity. Embedded processors are severely resource constrained. Their nearest mobile counterparts exhibit at least a 100 -- 1,000x difference in compute capability, memory availability, and power consumption. As a result, the machine-learning (ML) models and associated ML inference framework must not only execute efficiently but also operate in a few kilobytes of memory. Also, the embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08678","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.08678/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.08678","created_at":"2026-07-05T02:22:38.764124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08678v3","created_at":"2026-07-05T02:22:38.764124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08678","created_at":"2026-07-05T02:22:38.764124+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFHA6EANOKRK","created_at":"2026-07-05T02:22:38.764124+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFHA6EANOKRKIKZI","created_at":"2026-07-05T02:22:38.764124+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFHA6EAN","created_at":"2026-07-05T02:22:38.764124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07431","citing_title":"OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21421","citing_title":"AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06528","citing_title":"Quantized AI Inference on Constrained Embedded Platforms for Small-Satellite Settings","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21421","citing_title":"AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07059","citing_title":"Production-Ready Automated ECU Calibration using Residual Reinforcement Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18067","citing_title":"Towards Real-Time ECG and EMG Modeling on $\\mu$NPUs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5","json":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5.json","graph_json":"https://pith.science/api/pith-number/RFHA6EANOKRKIKZILMZ6LAF3C5/graph.json","events_json":"https://pith.science/api/pith-number/RFHA6EANOKRKIKZILMZ6LAF3C5/events.json","paper":"https://pith.science/paper/RFHA6EAN"},"agent_actions":{"view_html":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5","download_json":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5.json","view_paper":"https://pith.science/paper/RFHA6EAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08678&json=true","fetch_graph":"https://pith.science/api/pith-number/RFHA6EANOKRKIKZILMZ6LAF3C5/graph.json","fetch_events":"https://pith.science/api/pith-number/RFHA6EANOKRKIKZILMZ6LAF3C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5/action/storage_attestation","attest_author":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5/action/author_attestation","sign_citation":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5/action/citation_signature","submit_replication":"https://pith.science/pith/RFHA6EANOKRKIKZILMZ6LAF3C5/action/replication_record"}},"created_at":"2026-07-05T02:22:38.764124+00:00","updated_at":"2026-07-05T02:22:38.764124+00:00"}