{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NJR46X7ERZHLRIAP6CLRDONWRO","short_pith_number":"pith:NJR46X7E","schema_version":"1.0","canonical_sha256":"6a63cf5fe48e4eb8a00ff09711b9b68bb940625da495d9beaf861e86e8c8d83a","source":{"kind":"arxiv","id":"2203.12925","version":1},"attestation_state":"computed","paper":{"title":"TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Dequino, Alessio Burrello, Daniele Jahier Pagliari, Enrico Macii, Francesco Conti, Luca Benini, Marcello Zanghieri, Massimo Poncino","submitted_at":"2022-03-24T08:15:17Z","abstract_excerpt":"Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Learning models for Time Series analysis. We introduce an automated exploration approach and a library of optimized kernels to map TCNs on Parallel Ultra-Low Power (PULP) microcontrollers. Our approach minimizes latency and energy by exploiting a layer tiling optimizer to jointly find the tiling dimensions and select among alternative implementations of the causal and dilated 1D-convolution operations at the core of TCNs. We benchmark our approach on a commercial PULP device, achieving up to 103X lower latency and 20.3X lower"},"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":"2203.12925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-24T08:15:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26afdd2a2429f364dffdb63b53604ec280bd8aa50a51f69e9452804bd7854e12","abstract_canon_sha256":"84e17c0bcdc450b4641e654ce081d83025c9e4132b23bfce3265f73540370c8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:40.035138Z","signature_b64":"aKwHO1fLMBNf3LjA4KlGqCc1GA/ypo0hncAazzuOlbEPB9do2Y8ARbL1xdyoHZzxC26nXgkyQViNUkLOXTH5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a63cf5fe48e4eb8a00ff09711b9b68bb940625da495d9beaf861e86e8c8d83a","last_reissued_at":"2026-07-05T04:12:40.034784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:40.034784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Dequino, Alessio Burrello, Daniele Jahier Pagliari, Enrico Macii, Francesco Conti, Luca Benini, Marcello Zanghieri, Massimo Poncino","submitted_at":"2022-03-24T08:15:17Z","abstract_excerpt":"Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Learning models for Time Series analysis. We introduce an automated exploration approach and a library of optimized kernels to map TCNs on Parallel Ultra-Low Power (PULP) microcontrollers. Our approach minimizes latency and energy by exploiting a layer tiling optimizer to jointly find the tiling dimensions and select among alternative implementations of the causal and dilated 1D-convolution operations at the core of TCNs. We benchmark our approach on a commercial PULP device, achieving up to 103X lower latency and 20.3X lower"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12925","kind":"arxiv","version":1},"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/2203.12925/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":"2203.12925","created_at":"2026-07-05T04:12:40.034833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12925v1","created_at":"2026-07-05T04:12:40.034833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12925","created_at":"2026-07-05T04:12:40.034833+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJR46X7ERZHL","created_at":"2026-07-05T04:12:40.034833+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJR46X7ERZHLRIAP","created_at":"2026-07-05T04:12:40.034833+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJR46X7E","created_at":"2026-07-05T04:12:40.034833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO","json":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO.json","graph_json":"https://pith.science/api/pith-number/NJR46X7ERZHLRIAP6CLRDONWRO/graph.json","events_json":"https://pith.science/api/pith-number/NJR46X7ERZHLRIAP6CLRDONWRO/events.json","paper":"https://pith.science/paper/NJR46X7E"},"agent_actions":{"view_html":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO","download_json":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO.json","view_paper":"https://pith.science/paper/NJR46X7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12925&json=true","fetch_graph":"https://pith.science/api/pith-number/NJR46X7ERZHLRIAP6CLRDONWRO/graph.json","fetch_events":"https://pith.science/api/pith-number/NJR46X7ERZHLRIAP6CLRDONWRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO/action/storage_attestation","attest_author":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO/action/author_attestation","sign_citation":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO/action/citation_signature","submit_replication":"https://pith.science/pith/NJR46X7ERZHLRIAP6CLRDONWRO/action/replication_record"}},"created_at":"2026-07-05T04:12:40.034833+00:00","updated_at":"2026-07-05T04:12:40.034833+00:00"}