{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KJO6RBIS6ZSBRTX4FEBVFQWBYJ","short_pith_number":"pith:KJO6RBIS","schema_version":"1.0","canonical_sha256":"525de88512f66418cefc290352c2c1c26666a1e30beab9c3c4c5f706d76ab913","source":{"kind":"arxiv","id":"2405.19065","version":1},"attestation_state":"computed","paper":{"title":"xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Georg Rutishauser, Joan Mihali, Luca Benini, Moritz Scherer","submitted_at":"2024-05-29T13:16:46Z","abstract_excerpt":"Ternary neural networks (TNNs) offer a superior accuracy-energy trade-off compared to binary neural networks. However, until now, they have required specialized accelerators to realize their efficiency potential, which has hindered widespread adoption. To address this, we present xTern, a lightweight extension of the RISC-V instruction set architecture (ISA) targeted at accelerating TNN inference on general-purpose cores. To complement the ISA extension, we developed a set of optimized kernels leveraging xTern, achieving 67% higher throughput than their 2-bit equivalents. Power consumption is "},"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":"2405.19065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2024-05-29T13:16:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"45bb4ed7aa4e2a0f4aab6c4eaa41080965fa1d1dd586560a0fe9de643f2f26fd","abstract_canon_sha256":"57f745f38e128168aa87e7e93923e77e35fc185f6870e1993589821615637156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:47.347443Z","signature_b64":"iSjg09eOtNiD7m8EM0jl7v+D/OW4KN3eNef1Jl1Hi+XByVgvPVQLo5KwJMIEGmfehtuR9xvBuj3Yl014m6EBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"525de88512f66418cefc290352c2c1c26666a1e30beab9c3c4c5f706d76ab913","last_reissued_at":"2026-07-05T08:24:47.346963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:47.346963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Georg Rutishauser, Joan Mihali, Luca Benini, Moritz Scherer","submitted_at":"2024-05-29T13:16:46Z","abstract_excerpt":"Ternary neural networks (TNNs) offer a superior accuracy-energy trade-off compared to binary neural networks. However, until now, they have required specialized accelerators to realize their efficiency potential, which has hindered widespread adoption. To address this, we present xTern, a lightweight extension of the RISC-V instruction set architecture (ISA) targeted at accelerating TNN inference on general-purpose cores. To complement the ISA extension, we developed a set of optimized kernels leveraging xTern, achieving 67% higher throughput than their 2-bit equivalents. Power consumption is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19065","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/2405.19065/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":"2405.19065","created_at":"2026-07-05T08:24:47.347023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19065v1","created_at":"2026-07-05T08:24:47.347023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19065","created_at":"2026-07-05T08:24:47.347023+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJO6RBIS6ZSB","created_at":"2026-07-05T08:24:47.347023+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJO6RBIS6ZSBRTX4","created_at":"2026-07-05T08:24:47.347023+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJO6RBIS","created_at":"2026-07-05T08:24:47.347023+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/KJO6RBIS6ZSBRTX4FEBVFQWBYJ","json":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ.json","graph_json":"https://pith.science/api/pith-number/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/graph.json","events_json":"https://pith.science/api/pith-number/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/events.json","paper":"https://pith.science/paper/KJO6RBIS"},"agent_actions":{"view_html":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ","download_json":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ.json","view_paper":"https://pith.science/paper/KJO6RBIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19065&json=true","fetch_graph":"https://pith.science/api/pith-number/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/action/storage_attestation","attest_author":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/action/author_attestation","sign_citation":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/action/citation_signature","submit_replication":"https://pith.science/pith/KJO6RBIS6ZSBRTX4FEBVFQWBYJ/action/replication_record"}},"created_at":"2026-07-05T08:24:47.347023+00:00","updated_at":"2026-07-05T08:24:47.347023+00:00"}