{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GZ3OEI4JYPZPS66UULEGJKFYJU","short_pith_number":"pith:GZ3OEI4J","schema_version":"1.0","canonical_sha256":"3676e22389c3f2f97bd4a2c864a8b84d06ce871c4d4de2448d2816ffe519e193","source":{"kind":"arxiv","id":"2311.03687","version":2},"attestation_state":"computed","paper":{"title":"Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.PF","authors_text":"Longteng Zhang, Peijie Dong, Qiong Luo, Ruibo Fan, Rui Guo, Shaohuai Shi, Xiang Liu, Xiaowen Chu, Xinglin Pan, Xin Wang, Zeyu Li","submitted_at":"2023-11-07T03:25:56Z","abstract_excerpt":"Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and deploying LLMs are expensive as it requires considerable computing resources and memory, hence many efficient approaches have been developed for improving system pipelines as well as operators. However, the runtime performance can vary significantly across hardware and software stacks, which makes it difficult to choose the best configuration. In this work, we"},"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":"2311.03687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2023-11-07T03:25:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b12e0b5f7fdcfd660538b789e01c5020528a990f4eeb178b15306eb92ef44d49","abstract_canon_sha256":"ddc40e16b3c2f3da1b04306b742fea08cf85ab2b72ad60f917b7f51554d64a98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:02.131053Z","signature_b64":"10EojKz5LFTr+6Tyiz0x0hWx3K005Sr9GeiD27dl1bcOKoAO4l0FSxOUAU2PibbQKX69rJLzXTRcbYHRebT8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3676e22389c3f2f97bd4a2c864a8b84d06ce871c4d4de2448d2816ffe519e193","last_reissued_at":"2026-07-05T07:19:02.130456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:02.130456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.PF","authors_text":"Longteng Zhang, Peijie Dong, Qiong Luo, Ruibo Fan, Rui Guo, Shaohuai Shi, Xiang Liu, Xiaowen Chu, Xinglin Pan, Xin Wang, Zeyu Li","submitted_at":"2023-11-07T03:25:56Z","abstract_excerpt":"Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and deploying LLMs are expensive as it requires considerable computing resources and memory, hence many efficient approaches have been developed for improving system pipelines as well as operators. However, the runtime performance can vary significantly across hardware and software stacks, which makes it difficult to choose the best configuration. In this work, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03687","kind":"arxiv","version":2},"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/2311.03687/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":"2311.03687","created_at":"2026-07-05T07:19:02.130546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03687v2","created_at":"2026-07-05T07:19:02.130546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03687","created_at":"2026-07-05T07:19:02.130546+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZ3OEI4JYPZP","created_at":"2026-07-05T07:19:02.130546+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZ3OEI4JYPZPS66U","created_at":"2026-07-05T07:19:02.130546+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZ3OEI4J","created_at":"2026-07-05T07:19:02.130546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23071","citing_title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23071","citing_title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11733","citing_title":"Position: LLM Inference Should Be Evaluated as Energy-to-Token Production","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU","json":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU.json","graph_json":"https://pith.science/api/pith-number/GZ3OEI4JYPZPS66UULEGJKFYJU/graph.json","events_json":"https://pith.science/api/pith-number/GZ3OEI4JYPZPS66UULEGJKFYJU/events.json","paper":"https://pith.science/paper/GZ3OEI4J"},"agent_actions":{"view_html":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU","download_json":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU.json","view_paper":"https://pith.science/paper/GZ3OEI4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03687&json=true","fetch_graph":"https://pith.science/api/pith-number/GZ3OEI4JYPZPS66UULEGJKFYJU/graph.json","fetch_events":"https://pith.science/api/pith-number/GZ3OEI4JYPZPS66UULEGJKFYJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU/action/storage_attestation","attest_author":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU/action/author_attestation","sign_citation":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU/action/citation_signature","submit_replication":"https://pith.science/pith/GZ3OEI4JYPZPS66UULEGJKFYJU/action/replication_record"}},"created_at":"2026-07-05T07:19:02.130546+00:00","updated_at":"2026-07-05T07:19:02.130546+00:00"}