{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPJ4X3IRH3JLZCBJHPXEQMQYKE","short_pith_number":"pith:EPJ4X3IR","schema_version":"1.0","canonical_sha256":"23d3cbed113ed2bc88293bee4832185116b7b984c7f5ad1a7fe49759a7ab8b07","source":{"kind":"arxiv","id":"2508.19087","version":1},"attestation_state":"computed","paper":{"title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.LG","authors_text":"Chao Fang, Haikuo Shao, Shaobo Ma, Zhongfeng Wang","submitted_at":"2025-08-26T14:48:29Z","abstract_excerpt":"Large language models (LLMs) have revolutionized AI applications, yet their enormous computational demands severely limit deployment and real-time performance. Quantization methods can help reduce computational costs, however, attaining the extreme efficiency associated with ultra-low-bit quantized LLMs at arbitrary precision presents challenges on GPUs. This is primarily due to the limited support for GPU Tensor Cores, inefficient memory management, and inflexible kernel optimizations. To tackle these challenges, we propose a comprehensive acceleration scheme for arbitrary precision LLMs, nam"},"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":"2508.19087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T14:48:29Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"be919e2d034ca88ec0b0c3932ab03098c33e9d22e1dd28ebee532d66251c3ad4","abstract_canon_sha256":"13e3d27d05e6f67f7752b6fd9bbde983aa52ce405b101e53de7c4fe792cc3793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:07.116886Z","signature_b64":"uiaCNZ8LBInjvchYa9uWERHUL5sSxCaq8E3V+/Dryz0IGbZDEUoPL0tmn17AF/nj+rJWpJ6hEbKeQ9sGF14AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d3cbed113ed2bc88293bee4832185116b7b984c7f5ad1a7fe49759a7ab8b07","last_reissued_at":"2026-07-05T12:02:07.116270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:07.116270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.LG","authors_text":"Chao Fang, Haikuo Shao, Shaobo Ma, Zhongfeng Wang","submitted_at":"2025-08-26T14:48:29Z","abstract_excerpt":"Large language models (LLMs) have revolutionized AI applications, yet their enormous computational demands severely limit deployment and real-time performance. Quantization methods can help reduce computational costs, however, attaining the extreme efficiency associated with ultra-low-bit quantized LLMs at arbitrary precision presents challenges on GPUs. This is primarily due to the limited support for GPU Tensor Cores, inefficient memory management, and inflexible kernel optimizations. To tackle these challenges, we propose a comprehensive acceleration scheme for arbitrary precision LLMs, nam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19087","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/2508.19087/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":"2508.19087","created_at":"2026-07-05T12:02:07.116366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19087v1","created_at":"2026-07-05T12:02:07.116366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19087","created_at":"2026-07-05T12:02:07.116366+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPJ4X3IRH3JL","created_at":"2026-07-05T12:02:07.116366+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPJ4X3IRH3JLZCBJ","created_at":"2026-07-05T12:02:07.116366+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPJ4X3IR","created_at":"2026-07-05T12:02:07.116366+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/EPJ4X3IRH3JLZCBJHPXEQMQYKE","json":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE.json","graph_json":"https://pith.science/api/pith-number/EPJ4X3IRH3JLZCBJHPXEQMQYKE/graph.json","events_json":"https://pith.science/api/pith-number/EPJ4X3IRH3JLZCBJHPXEQMQYKE/events.json","paper":"https://pith.science/paper/EPJ4X3IR"},"agent_actions":{"view_html":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE","download_json":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE.json","view_paper":"https://pith.science/paper/EPJ4X3IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19087&json=true","fetch_graph":"https://pith.science/api/pith-number/EPJ4X3IRH3JLZCBJHPXEQMQYKE/graph.json","fetch_events":"https://pith.science/api/pith-number/EPJ4X3IRH3JLZCBJHPXEQMQYKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE/action/storage_attestation","attest_author":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE/action/author_attestation","sign_citation":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE/action/citation_signature","submit_replication":"https://pith.science/pith/EPJ4X3IRH3JLZCBJHPXEQMQYKE/action/replication_record"}},"created_at":"2026-07-05T12:02:07.116366+00:00","updated_at":"2026-07-05T12:02:07.116366+00:00"}