{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VAZS6CE2YJ5MAVCNWRL4YS5RY4","short_pith_number":"pith:VAZS6CE2","schema_version":"1.0","canonical_sha256":"a8332f089ac27ac0544db457cc4bb1c71c032ddd85cb1a2f5ede709541307687","source":{"kind":"arxiv","id":"1802.04799","version":3},"attestation_state":"computed","paper":{"title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Arvind Krishnamurthy, Carlos Guestrin, Eddie Yan, Haichen Shen, Leyuan Wang, Lianmin Zheng, Luis Ceze, Meghan Cowan, Thierry Moreau, Tianqi Chen, Yuwei Hu, Ziheng Jiang","submitted_at":"2018-02-12T20:49:34Z","abstract_excerpt":"There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms -- such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) -- requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to de"},"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":"1802.04799","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T20:49:34Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"f05045be7268dc968407a575f1c54abdcbd4fcc4292ae726d51508f22454276b","abstract_canon_sha256":"7e2c47822b71df682d61f44a8dd366cd03cf351069586c2224b99ef1361bb3f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:00.416927Z","signature_b64":"2DcTpfHi1D79/EJ3JSSRyp8qtBqMDg0Nv7emkimVcq57wJlqP6ZCf2aD6zw8VCH+ROaKAAyVOFQL8oPYFhHoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8332f089ac27ac0544db457cc4bb1c71c032ddd85cb1a2f5ede709541307687","last_reissued_at":"2026-05-18T00:04:00.415687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:00.415687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Arvind Krishnamurthy, Carlos Guestrin, Eddie Yan, Haichen Shen, Leyuan Wang, Lianmin Zheng, Luis Ceze, Meghan Cowan, Thierry Moreau, Tianqi Chen, Yuwei Hu, Ziheng Jiang","submitted_at":"2018-02-12T20:49:34Z","abstract_excerpt":"There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms -- such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) -- requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04799","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.04799","created_at":"2026-05-18T00:04:00.415798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04799v3","created_at":"2026-05-18T00:04:00.415798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04799","created_at":"2026-05-18T00:04:00.415798+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAZS6CE2YJ5M","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAZS6CE2YJ5MAVCN","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAZS6CE2","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.08726","citing_title":"Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11109","citing_title":"Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14825","citing_title":"Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15272","citing_title":"Prism: Symbolic Superoptimization of Tensor Programs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16113","citing_title":"Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4","json":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4.json","graph_json":"https://pith.science/api/pith-number/VAZS6CE2YJ5MAVCNWRL4YS5RY4/graph.json","events_json":"https://pith.science/api/pith-number/VAZS6CE2YJ5MAVCNWRL4YS5RY4/events.json","paper":"https://pith.science/paper/VAZS6CE2"},"agent_actions":{"view_html":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4","download_json":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4.json","view_paper":"https://pith.science/paper/VAZS6CE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04799&json=true","fetch_graph":"https://pith.science/api/pith-number/VAZS6CE2YJ5MAVCNWRL4YS5RY4/graph.json","fetch_events":"https://pith.science/api/pith-number/VAZS6CE2YJ5MAVCNWRL4YS5RY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4/action/storage_attestation","attest_author":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4/action/author_attestation","sign_citation":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4/action/citation_signature","submit_replication":"https://pith.science/pith/VAZS6CE2YJ5MAVCNWRL4YS5RY4/action/replication_record"}},"created_at":"2026-05-18T00:04:00.415798+00:00","updated_at":"2026-05-18T00:04:00.415798+00:00"}