{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QVOD6WIHEUDTURNFOJM4JNFZGD","short_pith_number":"pith:QVOD6WIH","schema_version":"1.0","canonical_sha256":"855c3f590725073a45a57259c4b4b930fe09bd4e762d86c75268702ca90f46d9","source":{"kind":"arxiv","id":"2205.12781","version":1},"attestation_state":"computed","paper":{"title":"Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Alessio Burrello, Andrea Calimera, Chen Xie, Daniele Jahier Pagliari, Enrico Macii, Francesco Daghero, Luca Gandolfi, Marco Castellano, Massimo Poncino","submitted_at":"2022-05-25T13:52:35Z","abstract_excerpt":"Human Activity Recognition (HAR) is a relevant inference task in many mobile applications. State-of-the-art HAR at the edge is typically achieved with lightweight machine learning models such as decision trees and Random Forests (RFs), whereas deep learning is less common due to its high computational complexity. In this work, we propose a novel implementation of HAR based on deep neural networks, and precisely on Binary Neural Networks (BNNs), targeting low-power general purpose processors with a RISC-V instruction set. BNNs yield very small memory footprints and low inference complexity, tha"},"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":"2205.12781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T13:52:35Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"803735ee7525bd590f36069c02c4ecef70b1477c53cdd39bee39ca15c76960af","abstract_canon_sha256":"3b8098bb78cf956dc4067d98556327866b659d38715ada6247270b335b23677c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:29.912097Z","signature_b64":"x+a3ZNR/fMtn/7iMP64KfjoV0HwZKb5K4Wd7x5JGJYKiPrNNNCrdcYaEUrmXSaS1fYLucFBMket8pTasoPW9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"855c3f590725073a45a57259c4b4b930fe09bd4e762d86c75268702ca90f46d9","last_reissued_at":"2026-07-05T04:26:29.911709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:29.911709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Alessio Burrello, Andrea Calimera, Chen Xie, Daniele Jahier Pagliari, Enrico Macii, Francesco Daghero, Luca Gandolfi, Marco Castellano, Massimo Poncino","submitted_at":"2022-05-25T13:52:35Z","abstract_excerpt":"Human Activity Recognition (HAR) is a relevant inference task in many mobile applications. State-of-the-art HAR at the edge is typically achieved with lightweight machine learning models such as decision trees and Random Forests (RFs), whereas deep learning is less common due to its high computational complexity. In this work, we propose a novel implementation of HAR based on deep neural networks, and precisely on Binary Neural Networks (BNNs), targeting low-power general purpose processors with a RISC-V instruction set. BNNs yield very small memory footprints and low inference complexity, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12781","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/2205.12781/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":"2205.12781","created_at":"2026-07-05T04:26:29.911765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12781v1","created_at":"2026-07-05T04:26:29.911765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12781","created_at":"2026-07-05T04:26:29.911765+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVOD6WIHEUDT","created_at":"2026-07-05T04:26:29.911765+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVOD6WIHEUDTURNF","created_at":"2026-07-05T04:26:29.911765+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVOD6WIH","created_at":"2026-07-05T04:26:29.911765+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/QVOD6WIHEUDTURNFOJM4JNFZGD","json":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD.json","graph_json":"https://pith.science/api/pith-number/QVOD6WIHEUDTURNFOJM4JNFZGD/graph.json","events_json":"https://pith.science/api/pith-number/QVOD6WIHEUDTURNFOJM4JNFZGD/events.json","paper":"https://pith.science/paper/QVOD6WIH"},"agent_actions":{"view_html":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD","download_json":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD.json","view_paper":"https://pith.science/paper/QVOD6WIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12781&json=true","fetch_graph":"https://pith.science/api/pith-number/QVOD6WIHEUDTURNFOJM4JNFZGD/graph.json","fetch_events":"https://pith.science/api/pith-number/QVOD6WIHEUDTURNFOJM4JNFZGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD/action/storage_attestation","attest_author":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD/action/author_attestation","sign_citation":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD/action/citation_signature","submit_replication":"https://pith.science/pith/QVOD6WIHEUDTURNFOJM4JNFZGD/action/replication_record"}},"created_at":"2026-07-05T04:26:29.911765+00:00","updated_at":"2026-07-05T04:26:29.911765+00:00"}