{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZD33ZP2TJRAQSRSPZHK35Q5QG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5d22ed8a55fc8bcb1a0ed7835b1074f87284cd6ded98969d8ea9c364dc711838","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T08:26:53Z","title_canon_sha256":"21fc1579d9debc444d64e1ed4b7943ad923bbd6db07090b06db83d9c994620ef"},"schema_version":"1.0","source":{"id":"2403.20041","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20041","created_at":"2026-07-05T08:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20041v3","created_at":"2026-07-05T08:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20041","created_at":"2026-07-05T08:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"CZD33ZP2TJRA","created_at":"2026-07-05T08:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"CZD33ZP2TJRAQSRS","created_at":"2026-07-05T08:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"CZD33ZP2","created_at":"2026-07-05T08:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:0602190e995fc23b59293d108f86fdae7909751a45595fe36d690ed26e3a19d7","target":"graph","created_at":"2026-07-05T08:40:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.20041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow inference speed, which causes poor user experience. To facilitate high-efficiency LLM deployment on device GPUs, we propose four optimization techniques: (a) a symbolic expression-based approach to support dynamic shape model inference; (b) operator optimizations and execution priority setting to enhance inference speed and reduce phone lagging; (c) an FP4 quantiz","authors_text":"Jie Lu, Luchang Li, Lunxi Yuan, Qin Xie, Rui Wang, Sheng Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T08:26:53Z","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20041","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7672be5954b741000b2d98dd82b8539f2ede62591eb80f693bff71b10adaf1b6","target":"record","created_at":"2026-07-05T08:40:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5d22ed8a55fc8bcb1a0ed7835b1074f87284cd6ded98969d8ea9c364dc711838","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T08:26:53Z","title_canon_sha256":"21fc1579d9debc444d64e1ed4b7943ad923bbd6db07090b06db83d9c994620ef"},"schema_version":"1.0","source":{"id":"2403.20041","kind":"arxiv","version":3}},"canonical_sha256":"1647bde5fa9a62084a327e4eadf61d81826c1005a43e5a677f4b297c6815f741","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1647bde5fa9a62084a327e4eadf61d81826c1005a43e5a677f4b297c6815f741","first_computed_at":"2026-07-05T08:40:15.754195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:15.754195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fSUxYCXUbPxFgLct6WYzU64I9aCT3FkdeBjWQcck0FrigNAuVWB8oS2GHxqXhFdZcroOmlX707U3V65X31sUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:15.754701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.20041","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7672be5954b741000b2d98dd82b8539f2ede62591eb80f693bff71b10adaf1b6","sha256:0602190e995fc23b59293d108f86fdae7909751a45595fe36d690ed26e3a19d7"],"state_sha256":"4a068c954c7893d1e782fe3c26bec0d042d1917e68e28bcfef9b568c5fc0ecaa"}