{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KVUHFLEHGPUBNNGXV3W6P7W4EN","short_pith_number":"pith:KVUHFLEH","schema_version":"1.0","canonical_sha256":"556872ac8733e816b4d7aeede7fedc236687be2629e9e6198a52dc5bdedc37e3","source":{"kind":"arxiv","id":"2207.08820","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Hoffman, Ehsan Saboori, MohammadHossein AskariHemmat, Olivier Mastropietro, Saad Ashfaq, Sudhakar Sah","submitted_at":"2022-07-18T15:05:17Z","abstract_excerpt":"Deep Learning has been one of the most disruptive technological advancements in recent times. The high performance of deep learning models comes at the expense of high computational, storage and power requirements. Sensing the immediate need for accelerating and compressing these models to improve on-device performance, we introduce Deeplite Neutrino for production-ready optimization of the models and Deeplite Runtime for deployment of ultra-low bit quantized models on Arm-based platforms. We implement low-level quantization kernels for Armv7 and Armv8 architectures enabling deployment on the "},"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":"2207.08820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-18T15:05:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"304eb4e863114cb9325165068d2a7b33e4dc89f16d0a60bd63379b4a18f9723c","abstract_canon_sha256":"1f6f09659663d949d14ae5007dc3504760ff484e68e16a157149a64130370d91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:13.951293Z","signature_b64":"sYgRVdStHi9JgpgHQHvFiEqz/5G6GaxB1aBsKQbb/N5lHc8ScLiVwZUBEAoUQ+mer2Wml1uoPamAJrm/AFKTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"556872ac8733e816b4d7aeede7fedc236687be2629e9e6198a52dc5bdedc37e3","last_reissued_at":"2026-07-05T04:41:13.950829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:13.950829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Hoffman, Ehsan Saboori, MohammadHossein AskariHemmat, Olivier Mastropietro, Saad Ashfaq, Sudhakar Sah","submitted_at":"2022-07-18T15:05:17Z","abstract_excerpt":"Deep Learning has been one of the most disruptive technological advancements in recent times. The high performance of deep learning models comes at the expense of high computational, storage and power requirements. Sensing the immediate need for accelerating and compressing these models to improve on-device performance, we introduce Deeplite Neutrino for production-ready optimization of the models and Deeplite Runtime for deployment of ultra-low bit quantized models on Arm-based platforms. We implement low-level quantization kernels for Armv7 and Armv8 architectures enabling deployment on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08820","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/2207.08820/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":"2207.08820","created_at":"2026-07-05T04:41:13.950889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08820v1","created_at":"2026-07-05T04:41:13.950889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08820","created_at":"2026-07-05T04:41:13.950889+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVUHFLEHGPUB","created_at":"2026-07-05T04:41:13.950889+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVUHFLEHGPUBNNGX","created_at":"2026-07-05T04:41:13.950889+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVUHFLEH","created_at":"2026-07-05T04:41:13.950889+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/KVUHFLEHGPUBNNGXV3W6P7W4EN","json":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN.json","graph_json":"https://pith.science/api/pith-number/KVUHFLEHGPUBNNGXV3W6P7W4EN/graph.json","events_json":"https://pith.science/api/pith-number/KVUHFLEHGPUBNNGXV3W6P7W4EN/events.json","paper":"https://pith.science/paper/KVUHFLEH"},"agent_actions":{"view_html":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN","download_json":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN.json","view_paper":"https://pith.science/paper/KVUHFLEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08820&json=true","fetch_graph":"https://pith.science/api/pith-number/KVUHFLEHGPUBNNGXV3W6P7W4EN/graph.json","fetch_events":"https://pith.science/api/pith-number/KVUHFLEHGPUBNNGXV3W6P7W4EN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN/action/storage_attestation","attest_author":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN/action/author_attestation","sign_citation":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN/action/citation_signature","submit_replication":"https://pith.science/pith/KVUHFLEHGPUBNNGXV3W6P7W4EN/action/replication_record"}},"created_at":"2026-07-05T04:41:13.950889+00:00","updated_at":"2026-07-05T04:41:13.950889+00:00"}