{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2Y35YDIXAYMZES2GIBCELXWZJG","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":"c4c87543611bf809733577a59f79a47aeaee38ee22ec1757ec48ee6546ff0844","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T10:48:35Z","title_canon_sha256":"1b523a981d156acb7b166ff90c25b02f0c0e655e7b3bddf54f6d061c05d30df9"},"schema_version":"1.0","source":{"id":"2605.20295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20295","created_at":"2026-05-21T00:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20295v1","created_at":"2026-05-21T00:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20295","created_at":"2026-05-21T00:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"2Y35YDIXAYMZ","created_at":"2026-05-21T00:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"2Y35YDIXAYMZES2G","created_at":"2026-05-21T00:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"2Y35YDIX","created_at":"2026-05-21T00:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:5b184f97c73fbfa20f3db7149ba63282cf7069d041bcae64e776b1097db34770","target":"graph","created_at":"2026-05-21T00:04:24Z","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/2605.20295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ) methods predominantly rely on dynamic activation quantization, rendering them incompatible with NPU hardware constraints. To bridge the gap between high-fidelity PTQ and NPU-constrained inference, we propose Quant.npu, a integer-only fully static quantization framework. It incorporates learnable quantization parameters and rotation matrices, enabling low-bit activ","authors_text":"Chenghua Wang, Daliang Xu, Gang Huang, Jinghe Zhang, Mengwei Xu, Tao Qi, Weikai Xie, Yun Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T10:48:35Z","title":"Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20295","kind":"arxiv","version":1},"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":"sha256:6614a3e47f18526a735f980c85df19db8a99559c1691f0e87b462dcda62195e0","target":"record","created_at":"2026-05-21T00:04:24Z","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":"c4c87543611bf809733577a59f79a47aeaee38ee22ec1757ec48ee6546ff0844","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T10:48:35Z","title_canon_sha256":"1b523a981d156acb7b166ff90c25b02f0c0e655e7b3bddf54f6d061c05d30df9"},"schema_version":"1.0","source":{"id":"2605.20295","kind":"arxiv","version":1}},"canonical_sha256":"d637dc0d170619924b46404445ded949a63e9de0d2f2405a0b6f7fcced92d32d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d637dc0d170619924b46404445ded949a63e9de0d2f2405a0b6f7fcced92d32d","first_computed_at":"2026-05-21T00:04:24.359516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:24.359516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mHIiupu53H6Oo+Bh8dy5d8LnaDaKCHGloh6oXfQCmOjQPBC7rublL7eLLnM3ItOJ4ScwOlnnHvIcXz4uxlZ7AQ==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:24.360161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6614a3e47f18526a735f980c85df19db8a99559c1691f0e87b462dcda62195e0","sha256:5b184f97c73fbfa20f3db7149ba63282cf7069d041bcae64e776b1097db34770"],"state_sha256":"33d31cc333774a4b94df686ece2dc2f1843f6231e52efaa84e8e68ed943a64c2"}