{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FRJFN64XZKMGABTCJVNFYSTZWW","short_pith_number":"pith:FRJFN64X","schema_version":"1.0","canonical_sha256":"2c5256fb97ca986006624d5a5c4a79b5b19b3b8e149615568b36552de4c7819b","source":{"kind":"arxiv","id":"2405.15346","version":1},"attestation_state":"computed","paper":{"title":"BiSup: Bidirectional Quantization Error Suppression for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Minghui Zou, Ronghui Guo, Sai Zhang, Xiaowang Zhang, Zhiyong Feng","submitted_at":"2024-05-24T08:39:27Z","abstract_excerpt":"As the size and context length of Large Language Models (LLMs) grow, weight-activation quantization has emerged as a crucial technique for efficient deployment of LLMs. Compared to weight-only quantization, weight-activation quantization presents greater challenges due to the presence of outliers in activations. Existing methods have made significant progress by exploring mixed-precision quantization and outlier suppression. However, these methods primarily focus on optimizing the results of single matrix multiplication, neglecting the bidirectional propagation of quantization errors in LLMs. "},"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":"2405.15346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T08:39:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2afc5b93ad01aa605b7d74e23ebe17e0d13517c4f973e4621b421cd0ee046bae","abstract_canon_sha256":"49111d244fc82c9786ab84d9f69bc9ecd15c03c32044c3c9b30bb786e3a74818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:48.220153Z","signature_b64":"0HqnsR/n4/7w88yyE9mxMDT+aCe1y+BKkz/+/IyVLrnuMzgBP8+U0Wbddfo5IW5rdO2mMcTmPysQyAlPJdCNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c5256fb97ca986006624d5a5c4a79b5b19b3b8e149615568b36552de4c7819b","last_reissued_at":"2026-07-05T08:22:48.219656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:48.219656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiSup: Bidirectional Quantization Error Suppression for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Minghui Zou, Ronghui Guo, Sai Zhang, Xiaowang Zhang, Zhiyong Feng","submitted_at":"2024-05-24T08:39:27Z","abstract_excerpt":"As the size and context length of Large Language Models (LLMs) grow, weight-activation quantization has emerged as a crucial technique for efficient deployment of LLMs. Compared to weight-only quantization, weight-activation quantization presents greater challenges due to the presence of outliers in activations. Existing methods have made significant progress by exploring mixed-precision quantization and outlier suppression. However, these methods primarily focus on optimizing the results of single matrix multiplication, neglecting the bidirectional propagation of quantization errors in LLMs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15346","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/2405.15346/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":"2405.15346","created_at":"2026-07-05T08:22:48.219717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15346v1","created_at":"2026-07-05T08:22:48.219717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15346","created_at":"2026-07-05T08:22:48.219717+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRJFN64XZKMG","created_at":"2026-07-05T08:22:48.219717+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRJFN64XZKMGABTC","created_at":"2026-07-05T08:22:48.219717+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRJFN64X","created_at":"2026-07-05T08:22:48.219717+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/FRJFN64XZKMGABTCJVNFYSTZWW","json":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW.json","graph_json":"https://pith.science/api/pith-number/FRJFN64XZKMGABTCJVNFYSTZWW/graph.json","events_json":"https://pith.science/api/pith-number/FRJFN64XZKMGABTCJVNFYSTZWW/events.json","paper":"https://pith.science/paper/FRJFN64X"},"agent_actions":{"view_html":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW","download_json":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW.json","view_paper":"https://pith.science/paper/FRJFN64X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15346&json=true","fetch_graph":"https://pith.science/api/pith-number/FRJFN64XZKMGABTCJVNFYSTZWW/graph.json","fetch_events":"https://pith.science/api/pith-number/FRJFN64XZKMGABTCJVNFYSTZWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW/action/storage_attestation","attest_author":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW/action/author_attestation","sign_citation":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW/action/citation_signature","submit_replication":"https://pith.science/pith/FRJFN64XZKMGABTCJVNFYSTZWW/action/replication_record"}},"created_at":"2026-07-05T08:22:48.219717+00:00","updated_at":"2026-07-05T08:22:48.219717+00:00"}