{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L3YCA6VKDPVX7CI3SFEXKHSM4P","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":"2f83b57a16dcd7c0ef98997571ed766601457a9450c3413b10aadc68b6e29fa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-02T16:45:25Z","title_canon_sha256":"3d1148657bf480dd32690a305f0116648b4982bc4287f4c18321684ebc872104"},"schema_version":"1.0","source":{"id":"2512.02924","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02924","created_at":"2026-07-21T01:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02924v3","created_at":"2026-07-21T01:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02924","created_at":"2026-07-21T01:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"L3YCA6VKDPVX","created_at":"2026-07-21T01:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"L3YCA6VKDPVX7CI3","created_at":"2026-07-21T01:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"L3YCA6VK","created_at":"2026-07-21T01:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:936a08c4ff2abf905e3f4e00b1959920b53780fefbe93cf0041b54e158be53ef","target":"graph","created_at":"2026-07-21T01:21:41Z","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/2512.02924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileN","authors_text":"Han Yang, Liangmin Wu, Lingyue Zhu, Luoyi Liang, Qiang Tang, Wei Chen, Yicheng Qian, Yunhai Hu, Zhen Liu, Zhipeng Hu, Zhiyuan Cheng, Zhiyuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-02T16:45:25Z","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02924","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":"sha256:88e971aba77ebebf5b2e4009859db55bfa192e604dfee180b7751f53128f7956","target":"record","created_at":"2026-07-21T01:21:41Z","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":"2f83b57a16dcd7c0ef98997571ed766601457a9450c3413b10aadc68b6e29fa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-02T16:45:25Z","title_canon_sha256":"3d1148657bf480dd32690a305f0116648b4982bc4287f4c18321684ebc872104"},"schema_version":"1.0","source":{"id":"2512.02924","kind":"arxiv","version":3}},"canonical_sha256":"5ef0207aaa1beb7f891b9149751e4ce3f55d2af2a85272d5a37e51a5e054e5bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ef0207aaa1beb7f891b9149751e4ce3f55d2af2a85272d5a37e51a5e054e5bb","first_computed_at":"2026-07-21T01:21:41.085272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:41.085272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n/PfG6hUPacqdB/jEgctj8Wf145DbhH1LhvSyvl2GBwc0dcTpzxnGen7iuODSmCtD89T9y4fRTjFUq8RR/aOCw==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:41.086197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02924","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88e971aba77ebebf5b2e4009859db55bfa192e604dfee180b7751f53128f7956","sha256:936a08c4ff2abf905e3f4e00b1959920b53780fefbe93cf0041b54e158be53ef"],"state_sha256":"80ff4478d6264035fd350bc20d4589d7da01b8ae430ceb904a3a4ed119766fe3"}