{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7BNOIXF4CTNOC5YNZCE7RBPORO","short_pith_number":"pith:7BNOIXF4","schema_version":"1.0","canonical_sha256":"f85ae45cbc14dae1770dc889f885ee8b807e943317af20ba2e7990d50189ca12","source":{"kind":"arxiv","id":"2606.02836","version":1},"attestation_state":"computed","paper":{"title":"Fast Transformer Inference on ARM-Based HMPSoCs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Anuj Pathania, Hang Xu, Thanassis Giannetsos, Yixian Shen","submitted_at":"2026-06-01T20:00:04Z","abstract_excerpt":"Transformer models have set new performance standards for machine learning (ML) tasks. However, their resource-intensive deployment on resource-constrained edge devices for cloud-free, on-chip transformer inference remains challenging. The ARM Compute Library (ARM-CL) framework provides low-latency CNN inference on ARM-based edge devices but lacks support for transformer inference. In this work, we implement several new transformer kernels in ARM-CL to support native transformer execution. Our extended ARM-CL achieves up to three times faster transformer inference compared to state-of-the-art "},"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":"2606.02836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-01T20:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"363a69ca1c78143c7ff40d61404dbd5a05d344125bfb9e4c3d6062eab0c997dd","abstract_canon_sha256":"fe3017b8dccd2df06c93aa7dac099cb886a98e73133ec49571fb2655c2aa38e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:24.219068Z","signature_b64":"ZSL1FXqjoIo6QwiTWcr88cHOwxmiufEzKMaeNnPyrnxb6IJ8epiFLy5RQh4jOjPguHmC9C9lC9R0XVPKdBqOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85ae45cbc14dae1770dc889f885ee8b807e943317af20ba2e7990d50189ca12","last_reissued_at":"2026-06-03T01:05:24.218696Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:24.218696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Transformer Inference on ARM-Based HMPSoCs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Anuj Pathania, Hang Xu, Thanassis Giannetsos, Yixian Shen","submitted_at":"2026-06-01T20:00:04Z","abstract_excerpt":"Transformer models have set new performance standards for machine learning (ML) tasks. However, their resource-intensive deployment on resource-constrained edge devices for cloud-free, on-chip transformer inference remains challenging. The ARM Compute Library (ARM-CL) framework provides low-latency CNN inference on ARM-based edge devices but lacks support for transformer inference. In this work, we implement several new transformer kernels in ARM-CL to support native transformer execution. Our extended ARM-CL achieves up to three times faster transformer inference compared to state-of-the-art "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02836","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/2606.02836/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":"2606.02836","created_at":"2026-06-03T01:05:24.218750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02836v1","created_at":"2026-06-03T01:05:24.218750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02836","created_at":"2026-06-03T01:05:24.218750+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BNOIXF4CTNO","created_at":"2026-06-03T01:05:24.218750+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BNOIXF4CTNOC5YN","created_at":"2026-06-03T01:05:24.218750+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BNOIXF4","created_at":"2026-06-03T01:05:24.218750+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/7BNOIXF4CTNOC5YNZCE7RBPORO","json":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO.json","graph_json":"https://pith.science/api/pith-number/7BNOIXF4CTNOC5YNZCE7RBPORO/graph.json","events_json":"https://pith.science/api/pith-number/7BNOIXF4CTNOC5YNZCE7RBPORO/events.json","paper":"https://pith.science/paper/7BNOIXF4"},"agent_actions":{"view_html":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO","download_json":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO.json","view_paper":"https://pith.science/paper/7BNOIXF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02836&json=true","fetch_graph":"https://pith.science/api/pith-number/7BNOIXF4CTNOC5YNZCE7RBPORO/graph.json","fetch_events":"https://pith.science/api/pith-number/7BNOIXF4CTNOC5YNZCE7RBPORO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO/action/storage_attestation","attest_author":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO/action/author_attestation","sign_citation":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO/action/citation_signature","submit_replication":"https://pith.science/pith/7BNOIXF4CTNOC5YNZCE7RBPORO/action/replication_record"}},"created_at":"2026-06-03T01:05:24.218750+00:00","updated_at":"2026-06-03T01:05:24.218750+00:00"}