{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F4MGJBXU27N65PGT3SJF4P4R3N","short_pith_number":"pith:F4MGJBXU","schema_version":"1.0","canonical_sha256":"2f186486f4d7dbeebcd3dc925e3f91db68b0b1662121c55f3eefd966275f28b2","source":{"kind":"arxiv","id":"2512.21651","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Naive output alignment fails in 1-bit LLM quantization because errors accumulate across layers and distort the representation space unevenly.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Cuong Pham, Dung Anh Hoang, Jianfei Cai, Thanh-Toan Do, Trung Le","submitted_at":"2025-12-25T12:39:36Z","abstract_excerpt":"Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression techniques have been proposed, including quantization, pruning, and knowledge distillation. Among these, post-training quantization (PTQ) is widely adopted for its efficiency, as it requires no retraining and only a small dataset for calibration, enabling low-cost deployment. Recent advances for post-training quantization have demonstrated that even near 4-bit met"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2512.21651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-25T12:39:36Z","cross_cats_sorted":[],"title_canon_sha256":"c96f8566f1bc3e12dbf3aa669a763aa8ce6b1dcd8fa9828b63e5c75139bdee0f","abstract_canon_sha256":"b7813dbbb929cfa9b34818e0ef81958d5bc03906d72ec113085f09350d188f7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.375753Z","signature_b64":"9u51UYruBykKpp/w6dtw5hLS8B8zljTgoJ/yaAbF9bycjJatI8cx/TP8wuzkCX1EqyGtre7dG/EClEaQj/DfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f186486f4d7dbeebcd3dc925e3f91db68b0b1662121c55f3eefd966275f28b2","last_reissued_at":"2026-05-17T23:39:00.375078Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.375078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Naive output alignment fails in 1-bit LLM quantization because errors accumulate across layers and distort the representation space unevenly.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Cuong Pham, Dung Anh Hoang, Jianfei Cai, Thanh-Toan Do, Trung Le","submitted_at":"2025-12-25T12:39:36Z","abstract_excerpt":"Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression techniques have been proposed, including quantization, pruning, and knowledge distillation. Among these, post-training quantization (PTQ) is widely adopted for its efficiency, as it requires no retraining and only a small dataset for calibration, enabling low-cost deployment. Recent advances for post-training quantization have demonstrated that even near 4-bit met"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we show that this failure arises from two fundamental issues: error accumulation across layers and, more critically, anisotropic distortion of the representation space. Based on these insights, we propose a novel PTQ method for 1-bit LLMs that explicitly addresses these issues while maintaining computational efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that correcting error accumulation and anisotropic distortion on a small calibration set will generalize to the full test distribution without introducing new distortions or requiring architecture-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A post-training 1-bit quantization method for LLMs that fixes error accumulation and anisotropic representation distortion to outperform prior weight-driven and naive output-driven baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Naive output alignment fails in 1-bit LLM quantization because errors accumulate across layers and distort the representation space unevenly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"224ff5bc432eafc18df120726120f86c4c3cd7b46daa7e979c46ced76a7fe856"},"source":{"id":"2512.21651","kind":"arxiv","version":2},"verdict":{"id":"8b19c048-9dd2-4c3b-ae39-a8155570b87f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T19:27:59.724906Z","strongest_claim":"we show that this failure arises from two fundamental issues: error accumulation across layers and, more critically, anisotropic distortion of the representation space. Based on these insights, we propose a novel PTQ method for 1-bit LLMs that explicitly addresses these issues while maintaining computational efficiency.","one_line_summary":"A post-training 1-bit quantization method for LLMs that fixes error accumulation and anisotropic representation distortion to outperform prior weight-driven and naive output-driven baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that correcting error accumulation and anisotropic distortion on a small calibration set will generalize to the full test distribution without introducing new distortions or requiring architecture-specific tuning.","pith_extraction_headline":"Naive output alignment fails in 1-bit LLM quantization because errors accumulate across layers and distort the representation space unevenly."},"references":{"count":22,"sample":[{"doi":"10.1609/aaai.v34i05.6239","year":2005,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","ref_index":1,"cited_arxiv_id":"2005.14165","is_internal_anchor":true},{"doi":"","year":null,"title":"Stbllm: Breaking the 1-bit barrier with structured binary llms","work_id":"f9cf4e8e-ce01-40e5-820a-ae805db27e12","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Network sketching: Exploiting bi- nary structure in deep cnns.2017 IEEE Conference on Computer Vision and Pattern Recog- nition (CVPR), pp","work_id":"18dc22c6-7aeb-46ba-8eab-94ca65110314","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","work_id":"d79f6a26-2d92-4f7c-aea0-8aabf3b668c8","ref_index":4,"cited_arxiv_id":"1510.00149","is_internal_anchor":true},{"doi":"","year":null,"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","ref_index":5,"cited_arxiv_id":"1503.02531","is_internal_anchor":true}],"resolved_work":22,"snapshot_sha256":"1b2bbe69b439b266218239681008d63b393781439a83862d6e51b0eaac1b81b6","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fa99115169d6e8517e200daa4364b1dcbb699592f7b4bc95a067dd42541b33e"},"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":"2512.21651","created_at":"2026-05-17T23:39:00.375180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.21651v2","created_at":"2026-05-17T23:39:00.375180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21651","created_at":"2026-05-17T23:39:00.375180+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4MGJBXU27N6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4MGJBXU27N65PGT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4MGJBXU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N","json":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N.json","graph_json":"https://pith.science/api/pith-number/F4MGJBXU27N65PGT3SJF4P4R3N/graph.json","events_json":"https://pith.science/api/pith-number/F4MGJBXU27N65PGT3SJF4P4R3N/events.json","paper":"https://pith.science/paper/F4MGJBXU"},"agent_actions":{"view_html":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N","download_json":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N.json","view_paper":"https://pith.science/paper/F4MGJBXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.21651&json=true","fetch_graph":"https://pith.science/api/pith-number/F4MGJBXU27N65PGT3SJF4P4R3N/graph.json","fetch_events":"https://pith.science/api/pith-number/F4MGJBXU27N65PGT3SJF4P4R3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N/action/storage_attestation","attest_author":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N/action/author_attestation","sign_citation":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N/action/citation_signature","submit_replication":"https://pith.science/pith/F4MGJBXU27N65PGT3SJF4P4R3N/action/replication_record"}},"created_at":"2026-05-17T23:39:00.375180+00:00","updated_at":"2026-05-17T23:39:00.375180+00:00"}