{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GB4PPGH4JA4WRQZNYHEDJ7R2DJ","short_pith_number":"pith:GB4PPGH4","schema_version":"1.0","canonical_sha256":"3078f798fc483968c32dc1c834fe3a1a52be1885576c03377364665062f844fe","source":{"kind":"arxiv","id":"2605.23294","version":1},"attestation_state":"computed","paper":{"title":"NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Dongxue Zhao, Ling Liang, Meng Li, Qianqian Huang, Ru Huang, Shuzhang Zhong, Tianyang Luo, Weikai Xu, Yimao Cai, Zongwei Wang","submitted_at":"2026-05-22T07:10:57Z","abstract_excerpt":"The Mixture-of-Experts (MoE) models have emerged as the state-of-the-art paradigm for scaling up large language models (LLMs) without proportionally increased computational cost. However, its on-device deployment faces a critical challenge due to the large memory requirement for storing all expert parameters. 3D NAND-based computing-in-memory (CIM) architectures uniquely offer high storage capacity and reduced data movement, while they are ill-suited for MoE models with dynamically sparse expert activation, leading to a degradation of effective computational parallelism, along with underutiliz"},"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":"2605.23294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-05-22T07:10:57Z","cross_cats_sorted":[],"title_canon_sha256":"64b3e2149a62ae7ac99890e54dd264a3526cf2ec672ab75bed74c8f913b98138","abstract_canon_sha256":"940726c4f95f6cb60a6bdc099e897b4b0ab1823a9f6636b1bb7cea3654ebc3b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:47.626822Z","signature_b64":"8npz5JZBiS12EZvxA0VJnD4EBeUbcn6vSoN8qpWsAdpQz5Ahc+eEMQASaRu8efzyh6WnlRg5S6NNhrd7/fcuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3078f798fc483968c32dc1c834fe3a1a52be1885576c03377364665062f844fe","last_reissued_at":"2026-05-25T02:01:47.626206Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:47.626206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Dongxue Zhao, Ling Liang, Meng Li, Qianqian Huang, Ru Huang, Shuzhang Zhong, Tianyang Luo, Weikai Xu, Yimao Cai, Zongwei Wang","submitted_at":"2026-05-22T07:10:57Z","abstract_excerpt":"The Mixture-of-Experts (MoE) models have emerged as the state-of-the-art paradigm for scaling up large language models (LLMs) without proportionally increased computational cost. However, its on-device deployment faces a critical challenge due to the large memory requirement for storing all expert parameters. 3D NAND-based computing-in-memory (CIM) architectures uniquely offer high storage capacity and reduced data movement, while they are ill-suited for MoE models with dynamically sparse expert activation, leading to a degradation of effective computational parallelism, along with underutiliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23294","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/2605.23294/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":"2605.23294","created_at":"2026-05-25T02:01:47.626324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23294v1","created_at":"2026-05-25T02:01:47.626324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23294","created_at":"2026-05-25T02:01:47.626324+00:00"},{"alias_kind":"pith_short_12","alias_value":"GB4PPGH4JA4W","created_at":"2026-05-25T02:01:47.626324+00:00"},{"alias_kind":"pith_short_16","alias_value":"GB4PPGH4JA4WRQZN","created_at":"2026-05-25T02:01:47.626324+00:00"},{"alias_kind":"pith_short_8","alias_value":"GB4PPGH4","created_at":"2026-05-25T02:01:47.626324+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/GB4PPGH4JA4WRQZNYHEDJ7R2DJ","json":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ.json","graph_json":"https://pith.science/api/pith-number/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/graph.json","events_json":"https://pith.science/api/pith-number/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/events.json","paper":"https://pith.science/paper/GB4PPGH4"},"agent_actions":{"view_html":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ","download_json":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ.json","view_paper":"https://pith.science/paper/GB4PPGH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23294&json=true","fetch_graph":"https://pith.science/api/pith-number/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/action/storage_attestation","attest_author":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/action/author_attestation","sign_citation":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/action/citation_signature","submit_replication":"https://pith.science/pith/GB4PPGH4JA4WRQZNYHEDJ7R2DJ/action/replication_record"}},"created_at":"2026-05-25T02:01:47.626324+00:00","updated_at":"2026-05-25T02:01:47.626324+00:00"}