{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BVXQBROPIY2WAGVJFX5B26R672","short_pith_number":"pith:BVXQBROP","schema_version":"1.0","canonical_sha256":"0d6f00c5cf4635601aa92dfa1d7a3efe8c0a0a532472fbf989469084b01dd9ab","source":{"kind":"arxiv","id":"2310.00034","version":2},"attestation_state":"computed","paper":{"title":"PB-LLM: Partially Binarized Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qiang Wu, Yuzhang Shang, Zhen Dong, Zhihang Yuan","submitted_at":"2023-09-29T14:35:27Z","abstract_excerpt":"This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collapsing LLMs, we propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs. Specifically, our exploration first uncovers the ineffectiveness of naive applications of existing binarization algorithms and highlights the imperative role of salient weights in achieving"},"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":"2310.00034","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T14:35:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"915f745ed3fef476f9396dfd14ec330b39e9ce5dd78e7cc224afd4bc737e6f2a","abstract_canon_sha256":"f7ffebd5ad0a77c505db0038e49c320cbf645c42e96e1f06d4acaf6be1a2086d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:28.676912Z","signature_b64":"MQgRy/BGbm7Wd2psjCsSUyzK8ijiybydi+2rvk92Wy8b9/HlR6w71QvS2ql0H3r70zXw8iOnxYzx9CqHylc4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d6f00c5cf4635601aa92dfa1d7a3efe8c0a0a532472fbf989469084b01dd9ab","last_reissued_at":"2026-07-05T07:10:28.676416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:28.676416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PB-LLM: Partially Binarized Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qiang Wu, Yuzhang Shang, Zhen Dong, Zhihang Yuan","submitted_at":"2023-09-29T14:35:27Z","abstract_excerpt":"This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collapsing LLMs, we propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs. Specifically, our exploration first uncovers the ineffectiveness of naive applications of existing binarization algorithms and highlights the imperative role of salient weights in achieving"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00034","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/2310.00034/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":"2310.00034","created_at":"2026-07-05T07:10:28.676471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00034v2","created_at":"2026-07-05T07:10:28.676471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00034","created_at":"2026-07-05T07:10:28.676471+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVXQBROPIY2W","created_at":"2026-07-05T07:10:28.676471+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVXQBROPIY2WAGVJ","created_at":"2026-07-05T07:10:28.676471+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVXQBROP","created_at":"2026-07-05T07:10:28.676471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13054","citing_title":"TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05429","citing_title":"Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06974","citing_title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17985","citing_title":"SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18475","citing_title":"GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18556","citing_title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03957","citing_title":"BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19167","citing_title":"LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18556","citing_title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672","json":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672.json","graph_json":"https://pith.science/api/pith-number/BVXQBROPIY2WAGVJFX5B26R672/graph.json","events_json":"https://pith.science/api/pith-number/BVXQBROPIY2WAGVJFX5B26R672/events.json","paper":"https://pith.science/paper/BVXQBROP"},"agent_actions":{"view_html":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672","download_json":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672.json","view_paper":"https://pith.science/paper/BVXQBROP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00034&json=true","fetch_graph":"https://pith.science/api/pith-number/BVXQBROPIY2WAGVJFX5B26R672/graph.json","fetch_events":"https://pith.science/api/pith-number/BVXQBROPIY2WAGVJFX5B26R672/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672/action/storage_attestation","attest_author":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672/action/author_attestation","sign_citation":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672/action/citation_signature","submit_replication":"https://pith.science/pith/BVXQBROPIY2WAGVJFX5B26R672/action/replication_record"}},"created_at":"2026-07-05T07:10:28.676471+00:00","updated_at":"2026-07-05T07:10:28.676471+00:00"}