{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZD33ZP2TJRAQSRSPZHK35Q5QG","short_pith_number":"pith:CZD33ZP2","canonical_record":{"source":{"id":"2403.20041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T08:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"21fc1579d9debc444d64e1ed4b7943ad923bbd6db07090b06db83d9c994620ef","abstract_canon_sha256":"5d22ed8a55fc8bcb1a0ed7835b1074f87284cd6ded98969d8ea9c364dc711838"},"schema_version":"1.0"},"canonical_sha256":"1647bde5fa9a62084a327e4eadf61d81826c1005a43e5a677f4b297c6815f741","source":{"kind":"arxiv","id":"2403.20041","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZD33ZP2TJRAQSRSPZHK35Q5QG","target":"record","payload":{"canonical_record":{"source":{"id":"2403.20041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T08:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"21fc1579d9debc444d64e1ed4b7943ad923bbd6db07090b06db83d9c994620ef","abstract_canon_sha256":"5d22ed8a55fc8bcb1a0ed7835b1074f87284cd6ded98969d8ea9c364dc711838"},"schema_version":"1.0"},"canonical_sha256":"1647bde5fa9a62084a327e4eadf61d81826c1005a43e5a677f4b297c6815f741","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:15.754701Z","signature_b64":"fSUxYCXUbPxFgLct6WYzU64I9aCT3FkdeBjWQcck0FrigNAuVWB8oS2GHxqXhFdZcroOmlX707U3V65X31sUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1647bde5fa9a62084a327e4eadf61d81826c1005a43e5a677f4b297c6815f741","last_reissued_at":"2026-07-05T08:40:15.754195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:15.754195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.20041","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O14o3DhS0ai8gFAfSwsIaffp7LzAXG1OFycIUTbjBP16MG9FV5nfDxXChMk4Bu/QidjO8/42bv11LoD2jjduAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:22:43.889814Z"},"content_sha256":"7672be5954b741000b2d98dd82b8539f2ede62591eb80f693bff71b10adaf1b6","schema_version":"1.0","event_id":"sha256:7672be5954b741000b2d98dd82b8539f2ede62591eb80f693bff71b10adaf1b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZD33ZP2TJRAQSRSPZHK35Q5QG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Lu, Luchang Li, Lunxi Yuan, Qin Xie, Rui Wang, Sheng Qian","submitted_at":"2024-03-29T08:26:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20041","kind":"arxiv","version":3},"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/2403.20041/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKeHEaUlV7Pd04un7dfVnD6sjC/XFlXzFtib/7HRUcV8LbgnucMT+LOJkEuXwBJpiCJx/wjx7xv1ZFqaYHlzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:22:43.890114Z"},"content_sha256":"0602190e995fc23b59293d108f86fdae7909751a45595fe36d690ed26e3a19d7","schema_version":"1.0","event_id":"sha256:0602190e995fc23b59293d108f86fdae7909751a45595fe36d690ed26e3a19d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/bundle.json","state_url":"https://pith.science/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T12:22:43Z","links":{"resolver":"https://pith.science/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG","bundle":"https://pith.science/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/bundle.json","state":"https://pith.science/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZD33ZP2TJRAQSRSPZHK35Q5QG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1afxXWg6zKFZCsTxscSu7JzAwzZSHCP6ozaZpn+3GrH43Bw/eUwtS4D09EDE9lZ5dqB0uCkNfffFNrLPvOsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:22:43.892684Z","bundle_sha256":"2f4d70cd150c5c18e5a7e7c0953dc001d5b12d2692ed55268bf98237a2fe092e"}}