{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NSWFBHA3P7ONILKFWRIKBNX2RV","short_pith_number":"pith:NSWFBHA3","schema_version":"1.0","canonical_sha256":"6cac509c1b7fdcd42d45b450a0b6fa8d78c54ce9077044931c0d8b3bf90caf3e","source":{"kind":"arxiv","id":"2606.08891","version":1},"attestation_state":"computed","paper":{"title":"PALUTE: Processing-In-Memory Acceleration via Lookup Table for Edge LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.AR","authors_text":"Runyang Tian, Tajana \\v{S}imuni\\'c Rosing, Weihong Xu, Yanru Chen","submitted_at":"2026-06-08T00:33:44Z","abstract_excerpt":"Large language models are increasingly deployed on edge devices with tight power and area budgets. While mixed-precision GEMM reduces arithmetic complexity, quantized inference is often dominated by dequantization and nonlinear operators. Lookup Table (LUT)-based method mitigates these costs by precomputing outputs and replacing repeated arithmetic with table lookups, but existing designs incur significant capacity and lookup-latency overheads. This paper presents PALUTE, a LUT-based Processing-In-Memory accelerator built on Monolithic 3D DRAM for efficient edge LLM inference. PALUTE enables i"},"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":"2606.08891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-08T00:33:44Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"e2e181f1711f145c38fb77a01e990196f3209504d7ac1becfe069e9843f57807","abstract_canon_sha256":"5634e66bc7e356c5edc2a8e36c33609bd014026bd33a95d544e605a6926b2abf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:45.550910Z","signature_b64":"Pxxawd6kiW+A4Vc9if/NdJUUNttByVic/lhn2u7xq1ztu9w8GYEOPs2Vd3cZTkjzBI5jEsnANCpgE/eAKo3JAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cac509c1b7fdcd42d45b450a0b6fa8d78c54ce9077044931c0d8b3bf90caf3e","last_reissued_at":"2026-06-09T02:07:45.550047Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:45.550047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PALUTE: Processing-In-Memory Acceleration via Lookup Table for Edge LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.AR","authors_text":"Runyang Tian, Tajana \\v{S}imuni\\'c Rosing, Weihong Xu, Yanru Chen","submitted_at":"2026-06-08T00:33:44Z","abstract_excerpt":"Large language models are increasingly deployed on edge devices with tight power and area budgets. While mixed-precision GEMM reduces arithmetic complexity, quantized inference is often dominated by dequantization and nonlinear operators. Lookup Table (LUT)-based method mitigates these costs by precomputing outputs and replacing repeated arithmetic with table lookups, but existing designs incur significant capacity and lookup-latency overheads. This paper presents PALUTE, a LUT-based Processing-In-Memory accelerator built on Monolithic 3D DRAM for efficient edge LLM inference. PALUTE enables i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08891","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/2606.08891/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":"2606.08891","created_at":"2026-06-09T02:07:45.550184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08891v1","created_at":"2026-06-09T02:07:45.550184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08891","created_at":"2026-06-09T02:07:45.550184+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSWFBHA3P7ON","created_at":"2026-06-09T02:07:45.550184+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSWFBHA3P7ONILKF","created_at":"2026-06-09T02:07:45.550184+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSWFBHA3","created_at":"2026-06-09T02:07:45.550184+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/NSWFBHA3P7ONILKFWRIKBNX2RV","json":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV.json","graph_json":"https://pith.science/api/pith-number/NSWFBHA3P7ONILKFWRIKBNX2RV/graph.json","events_json":"https://pith.science/api/pith-number/NSWFBHA3P7ONILKFWRIKBNX2RV/events.json","paper":"https://pith.science/paper/NSWFBHA3"},"agent_actions":{"view_html":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV","download_json":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV.json","view_paper":"https://pith.science/paper/NSWFBHA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08891&json=true","fetch_graph":"https://pith.science/api/pith-number/NSWFBHA3P7ONILKFWRIKBNX2RV/graph.json","fetch_events":"https://pith.science/api/pith-number/NSWFBHA3P7ONILKFWRIKBNX2RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV/action/storage_attestation","attest_author":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV/action/author_attestation","sign_citation":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV/action/citation_signature","submit_replication":"https://pith.science/pith/NSWFBHA3P7ONILKFWRIKBNX2RV/action/replication_record"}},"created_at":"2026-06-09T02:07:45.550184+00:00","updated_at":"2026-06-09T02:07:45.550184+00:00"}