{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X3AIZBQKXXQZSCZ6RCGABAFFA6","short_pith_number":"pith:X3AIZBQK","schema_version":"1.0","canonical_sha256":"bec08c860abde1990b3e888c0080a507b9938ff5e64783cb99af9ca2fdb625ae","source":{"kind":"arxiv","id":"2505.08981","version":1},"attestation_state":"computed","paper":{"title":"ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Christos-Savvas Bouganis, Keran Zheng, Yinting Huang, Zhewen Yu","submitted_at":"2025-05-13T21:46:56Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities as their scale expands to billions of parameters. Deploying these large-scale models on resource-constrained platforms presents significant challenges, with post-training fixed-point quantization often used as a model compression technique. However, quantization-only methods typically lead to significant accuracy degradation in LLMs when precision falls below 8 bits. This paper addresses this challenge through a software-hardware co-design framework, ITERA-LLM, which integrates sub-8-bit quantization "},"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":"2505.08981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2025-05-13T21:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"a9201314ba49df491938e68fc7259ae9917b57068aebada29a03545dd804a36b","abstract_canon_sha256":"fde5f95422c218657705fa241aac40203af4f279ff24e993347ed5c3658bbb49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:48.231484Z","signature_b64":"XgbCxZUg5gV6E8b6o9XFwnbMpm9cvUEkjPOmk9tgTdUSKSoyQiB7Zz/b3dQ4BsWSjfZoF3B6eVAdjhj7o1XpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bec08c860abde1990b3e888c0080a507b9938ff5e64783cb99af9ca2fdb625ae","last_reissued_at":"2026-07-05T11:02:48.231007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:48.231007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Christos-Savvas Bouganis, Keran Zheng, Yinting Huang, Zhewen Yu","submitted_at":"2025-05-13T21:46:56Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities as their scale expands to billions of parameters. Deploying these large-scale models on resource-constrained platforms presents significant challenges, with post-training fixed-point quantization often used as a model compression technique. However, quantization-only methods typically lead to significant accuracy degradation in LLMs when precision falls below 8 bits. This paper addresses this challenge through a software-hardware co-design framework, ITERA-LLM, which integrates sub-8-bit quantization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08981","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/2505.08981/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":"2505.08981","created_at":"2026-07-05T11:02:48.231066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08981v1","created_at":"2026-07-05T11:02:48.231066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08981","created_at":"2026-07-05T11:02:48.231066+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3AIZBQKXXQZ","created_at":"2026-07-05T11:02:48.231066+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3AIZBQKXXQZSCZ6","created_at":"2026-07-05T11:02:48.231066+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3AIZBQK","created_at":"2026-07-05T11:02:48.231066+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/X3AIZBQKXXQZSCZ6RCGABAFFA6","json":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6.json","graph_json":"https://pith.science/api/pith-number/X3AIZBQKXXQZSCZ6RCGABAFFA6/graph.json","events_json":"https://pith.science/api/pith-number/X3AIZBQKXXQZSCZ6RCGABAFFA6/events.json","paper":"https://pith.science/paper/X3AIZBQK"},"agent_actions":{"view_html":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6","download_json":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6.json","view_paper":"https://pith.science/paper/X3AIZBQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08981&json=true","fetch_graph":"https://pith.science/api/pith-number/X3AIZBQKXXQZSCZ6RCGABAFFA6/graph.json","fetch_events":"https://pith.science/api/pith-number/X3AIZBQKXXQZSCZ6RCGABAFFA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6/action/storage_attestation","attest_author":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6/action/author_attestation","sign_citation":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6/action/citation_signature","submit_replication":"https://pith.science/pith/X3AIZBQKXXQZSCZ6RCGABAFFA6/action/replication_record"}},"created_at":"2026-07-05T11:02:48.231066+00:00","updated_at":"2026-07-05T11:02:48.231066+00:00"}