{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HLWJZX7J3E4MUQIG6WJWKT7BAO","short_pith_number":"pith:HLWJZX7J","schema_version":"1.0","canonical_sha256":"3aec9cdfe9d938ca4106f593654fe103a75a68023af6aaa77290876c84cec6da","source":{"kind":"arxiv","id":"2103.08295","version":3},"attestation_state":"computed","paper":{"title":"TinyOL: TinyML with Online-Learning on Microcontrollers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Darko Anicic, Haoyu Ren, Thomas Runkler","submitted_at":"2021-03-15T11:39:41Z","abstract_excerpt":"Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved significant advancement in the last few years. However, the current TinyML solutions are based on batch/offline settings and support only the neural network's inference on MCUs. The neural network is first trained using a large amount of pre-collected data on a powerful machine and then flashed to MCUs. This results in a static model, hard to adapt to new data, and "},"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":"2103.08295","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T11:39:41Z","cross_cats_sorted":["cs.DC","cs.SY","eess.SY"],"title_canon_sha256":"7e68b2a49fadb0ac373a77b475e63127254503c46d3b35ae9df1190ebd0f4916","abstract_canon_sha256":"bf3873d78fb89f10a6916d2997fa8892e5866b630b26684ac1c1d9b9473db2cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:43.959546Z","signature_b64":"w8/VcF6XmcNPgHVsh575CbKsRz0tzQ4RrB/kGb2phtCLYSBrySs2VldlKaFKXMchtS/KzPTcddGZNanq9JxjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aec9cdfe9d938ca4106f593654fe103a75a68023af6aaa77290876c84cec6da","last_reissued_at":"2026-07-05T02:30:43.959049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:43.959049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyOL: TinyML with Online-Learning on Microcontrollers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Darko Anicic, Haoyu Ren, Thomas Runkler","submitted_at":"2021-03-15T11:39:41Z","abstract_excerpt":"Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved significant advancement in the last few years. However, the current TinyML solutions are based on batch/offline settings and support only the neural network's inference on MCUs. The neural network is first trained using a large amount of pre-collected data on a powerful machine and then flashed to MCUs. This results in a static model, hard to adapt to new data, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08295","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/2103.08295/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":"2103.08295","created_at":"2026-07-05T02:30:43.959102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.08295v3","created_at":"2026-07-05T02:30:43.959102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08295","created_at":"2026-07-05T02:30:43.959102+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLWJZX7J3E4M","created_at":"2026-07-05T02:30:43.959102+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLWJZX7J3E4MUQIG","created_at":"2026-07-05T02:30:43.959102+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLWJZX7J","created_at":"2026-07-05T02:30:43.959102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31226","citing_title":"What changes after deployment? A survey on On-device Learning in TinyML","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23012","citing_title":"On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO","json":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO.json","graph_json":"https://pith.science/api/pith-number/HLWJZX7J3E4MUQIG6WJWKT7BAO/graph.json","events_json":"https://pith.science/api/pith-number/HLWJZX7J3E4MUQIG6WJWKT7BAO/events.json","paper":"https://pith.science/paper/HLWJZX7J"},"agent_actions":{"view_html":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO","download_json":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO.json","view_paper":"https://pith.science/paper/HLWJZX7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.08295&json=true","fetch_graph":"https://pith.science/api/pith-number/HLWJZX7J3E4MUQIG6WJWKT7BAO/graph.json","fetch_events":"https://pith.science/api/pith-number/HLWJZX7J3E4MUQIG6WJWKT7BAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO/action/storage_attestation","attest_author":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO/action/author_attestation","sign_citation":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO/action/citation_signature","submit_replication":"https://pith.science/pith/HLWJZX7J3E4MUQIG6WJWKT7BAO/action/replication_record"}},"created_at":"2026-07-05T02:30:43.959102+00:00","updated_at":"2026-07-05T02:30:43.959102+00:00"}