{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZJGNCVTYEZ7ZALD76SQL4UA3W","short_pith_number":"pith:TZJGNCVT","schema_version":"1.0","canonical_sha256":"9e52668ab3c133fc8163ffa505f280ddae6be5e0feb19439127d88ff17d951d3","source":{"kind":"arxiv","id":"2410.16144","version":2},"attestation_state":"computed","paper":{"title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hansong Zhou, Hongyu Wang, Jinheng Wang, Shaoguang Mao, Shuming Ma, Ting Song, Yan Xia","submitted_at":"2024-10-21T16:14:57Z","abstract_excerpt":"Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1.58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption. These developments also enable local LLM deployment across a broad range of devices. In this work, we introduce bitnet.cpp, a tailored software stack designed to unlock the full potential of 1-bit LLMs. Specifically, we develop a set of kernels to support fast and lossless inference of ternary BitNet b1.58 LLMs on CPUs. Extensive experiments demonstrate that bitnet.cpp achieves significant speedups, ra"},"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":"2410.16144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"44ab726b48bd7406de20046d14bdc661e8dbfd761f2b799c1c967c8ad0eb0db0","abstract_canon_sha256":"51a9a0e77d6f897881965c72617bdff9254c1699bfa38ac404c645e28d6f8878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:39.900231Z","signature_b64":"4cZuKG82y1ifEQdVg7GhEZQxBFX1K/R9wsYILlNrBu6wXnJUnnVN6HH0ccsBKQS+A5GoI+czFX3Br0MHwFZjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e52668ab3c133fc8163ffa505f280ddae6be5e0feb19439127d88ff17d951d3","last_reissued_at":"2026-07-05T09:24:39.899649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:39.899649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hansong Zhou, Hongyu Wang, Jinheng Wang, Shaoguang Mao, Shuming Ma, Ting Song, Yan Xia","submitted_at":"2024-10-21T16:14:57Z","abstract_excerpt":"Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1.58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption. These developments also enable local LLM deployment across a broad range of devices. In this work, we introduce bitnet.cpp, a tailored software stack designed to unlock the full potential of 1-bit LLMs. Specifically, we develop a set of kernels to support fast and lossless inference of ternary BitNet b1.58 LLMs on CPUs. Extensive experiments demonstrate that bitnet.cpp achieves significant speedups, ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16144","kind":"arxiv","version":2},"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/2410.16144/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":"2410.16144","created_at":"2026-07-05T09:24:39.899716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16144v2","created_at":"2026-07-05T09:24:39.899716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16144","created_at":"2026-07-05T09:24:39.899716+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZJGNCVTYEZ7","created_at":"2026-07-05T09:24:39.899716+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZJGNCVTYEZ7ZALD","created_at":"2026-07-05T09:24:39.899716+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZJGNCVT","created_at":"2026-07-05T09:24:39.899716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.06252","citing_title":"D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27396","citing_title":"VitaLLM: A Versatile, Ultra-Compact Ternary LLM Accelerator with Dependency-Aware Scheduling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04523","citing_title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W","json":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W.json","graph_json":"https://pith.science/api/pith-number/TZJGNCVTYEZ7ZALD76SQL4UA3W/graph.json","events_json":"https://pith.science/api/pith-number/TZJGNCVTYEZ7ZALD76SQL4UA3W/events.json","paper":"https://pith.science/paper/TZJGNCVT"},"agent_actions":{"view_html":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W","download_json":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W.json","view_paper":"https://pith.science/paper/TZJGNCVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16144&json=true","fetch_graph":"https://pith.science/api/pith-number/TZJGNCVTYEZ7ZALD76SQL4UA3W/graph.json","fetch_events":"https://pith.science/api/pith-number/TZJGNCVTYEZ7ZALD76SQL4UA3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W/action/storage_attestation","attest_author":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W/action/author_attestation","sign_citation":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W/action/citation_signature","submit_replication":"https://pith.science/pith/TZJGNCVTYEZ7ZALD76SQL4UA3W/action/replication_record"}},"created_at":"2026-07-05T09:24:39.899716+00:00","updated_at":"2026-07-05T09:24:39.899716+00:00"}