{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YSYCUIVAZGE5VC6VXQTYGVMSI6","short_pith_number":"pith:YSYCUIVA","schema_version":"1.0","canonical_sha256":"c4b02a22a0c989da8bd5bc27835592479e8c604f452c4a5dda3f1af2b51ff1f1","source":{"kind":"arxiv","id":"2606.13054","version":1},"attestation_state":"computed","paper":{"title":"TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dawei Yang, Xing Hu, Zhe Jiang, Zhixiong Zhao, Zhixuan Chen, Zukang Xu","submitted_at":"2026-06-11T08:37:20Z","abstract_excerpt":"Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression "},"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":"2606.13054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T08:37:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1637952d6a8f58405b7765a55b0356ec889c501e6ede1a699832825b1026eb4a","abstract_canon_sha256":"8ac780b40a19d2a049e8fbdcd37ec4bb1c5dc7c3645d812139486a8c6226857b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:38.627537Z","signature_b64":"VUjEC9L+SJ7Fe4UNHdju1wFaiWORj/780wqrgq72N0Muu40RQvPgqXDJgL2DpFuXrvZwGL+WgMo5Ev6hL/1eDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4b02a22a0c989da8bd5bc27835592479e8c604f452c4a5dda3f1af2b51ff1f1","last_reissued_at":"2026-06-12T01:09:38.627004Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:38.627004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dawei Yang, Xing Hu, Zhe Jiang, Zhixiong Zhao, Zhixuan Chen, Zukang Xu","submitted_at":"2026-06-11T08:37:20Z","abstract_excerpt":"Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13054","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/2606.13054/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":"2606.13054","created_at":"2026-06-12T01:09:38.627058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13054v1","created_at":"2026-06-12T01:09:38.627058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13054","created_at":"2026-06-12T01:09:38.627058+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSYCUIVAZGE5","created_at":"2026-06-12T01:09:38.627058+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSYCUIVAZGE5VC6V","created_at":"2026-06-12T01:09:38.627058+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSYCUIVA","created_at":"2026-06-12T01:09:38.627058+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/YSYCUIVAZGE5VC6VXQTYGVMSI6","json":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6.json","graph_json":"https://pith.science/api/pith-number/YSYCUIVAZGE5VC6VXQTYGVMSI6/graph.json","events_json":"https://pith.science/api/pith-number/YSYCUIVAZGE5VC6VXQTYGVMSI6/events.json","paper":"https://pith.science/paper/YSYCUIVA"},"agent_actions":{"view_html":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6","download_json":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6.json","view_paper":"https://pith.science/paper/YSYCUIVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13054&json=true","fetch_graph":"https://pith.science/api/pith-number/YSYCUIVAZGE5VC6VXQTYGVMSI6/graph.json","fetch_events":"https://pith.science/api/pith-number/YSYCUIVAZGE5VC6VXQTYGVMSI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6/action/storage_attestation","attest_author":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6/action/author_attestation","sign_citation":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6/action/citation_signature","submit_replication":"https://pith.science/pith/YSYCUIVAZGE5VC6VXQTYGVMSI6/action/replication_record"}},"created_at":"2026-06-12T01:09:38.627058+00:00","updated_at":"2026-06-12T01:09:38.627058+00:00"}