{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VIUUE3V7AD33DBH25QUXFTFFAF","short_pith_number":"pith:VIUUE3V7","schema_version":"1.0","canonical_sha256":"aa29426ebf00f7b184faec2972cca5016051e8624e9ad3f19d2b22c77a080f14","source":{"kind":"arxiv","id":"1712.06139","version":2},"attestation_state":"computed","paper":{"title":"TensorFlow-Serving: Flexible, High-Performance ML Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Christopher Olston, Fangwei Li, Jeremiah Harmsen, Jordan Soyke, Kiril Gorovoy, Li Lao, Noah Fiedel, Sukriti Ramesh, Vinu Rajashekhar","submitted_at":"2017-12-17T16:36:26Z","abstract_excerpt":"We describe TensorFlow-Serving, a system to serve machine learning models inside Google which is also available in the cloud and via open-source. It is extremely flexible in terms of the types of ML platforms it supports, and ways to integrate with systems that convey new models and updated versions from training to serving. At the same time, the core code paths around model lookup and inference have been carefully optimized to avoid performance pitfalls observed in naive implementations. Google uses it in many production deployments, including a multi-tenant model hosting service called TFS^2"},"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":"1712.06139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-12-17T16:36:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e935e82258341081c30522a67c18952fa981411df152bb07fe1f86df4ba208e","abstract_canon_sha256":"208c6f08d1faff16a86fe3d7265d8bd02808f2550ab27671cb7cf4f8a104c044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:08.894419Z","signature_b64":"9oCWtvawlb6URyYV+jNDse3etosN9dcbAknkeDycIE9iwOOCGW6V2Do8ad4h6rDUeTREOjOShqmnkBwDuuXWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa29426ebf00f7b184faec2972cca5016051e8624e9ad3f19d2b22c77a080f14","last_reissued_at":"2026-05-18T00:27:08.893858Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:08.893858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorFlow-Serving: Flexible, High-Performance ML Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Christopher Olston, Fangwei Li, Jeremiah Harmsen, Jordan Soyke, Kiril Gorovoy, Li Lao, Noah Fiedel, Sukriti Ramesh, Vinu Rajashekhar","submitted_at":"2017-12-17T16:36:26Z","abstract_excerpt":"We describe TensorFlow-Serving, a system to serve machine learning models inside Google which is also available in the cloud and via open-source. It is extremely flexible in terms of the types of ML platforms it supports, and ways to integrate with systems that convey new models and updated versions from training to serving. At the same time, the core code paths around model lookup and inference have been carefully optimized to avoid performance pitfalls observed in naive implementations. Google uses it in many production deployments, including a multi-tenant model hosting service called TFS^2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06139","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":""},"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":"1712.06139","created_at":"2026-05-18T00:27:08.893939+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.06139v2","created_at":"2026-05-18T00:27:08.893939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06139","created_at":"2026-05-18T00:27:08.893939+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIUUE3V7AD33","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIUUE3V7AD33DBH2","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIUUE3V7","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.11018","citing_title":"Integration of TensorFlow based Acoustic Model with Kaldi WFST Decoder","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13131","citing_title":"ERPPO: Entropy Regularization-based Proximal Policy Optimization","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2309.06180","citing_title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05527","citing_title":"EdgeServing: Deadline-Aware Multi-DNN Serving at the Edge","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF","json":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF.json","graph_json":"https://pith.science/api/pith-number/VIUUE3V7AD33DBH25QUXFTFFAF/graph.json","events_json":"https://pith.science/api/pith-number/VIUUE3V7AD33DBH25QUXFTFFAF/events.json","paper":"https://pith.science/paper/VIUUE3V7"},"agent_actions":{"view_html":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF","download_json":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF.json","view_paper":"https://pith.science/paper/VIUUE3V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.06139&json=true","fetch_graph":"https://pith.science/api/pith-number/VIUUE3V7AD33DBH25QUXFTFFAF/graph.json","fetch_events":"https://pith.science/api/pith-number/VIUUE3V7AD33DBH25QUXFTFFAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF/action/storage_attestation","attest_author":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF/action/author_attestation","sign_citation":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF/action/citation_signature","submit_replication":"https://pith.science/pith/VIUUE3V7AD33DBH25QUXFTFFAF/action/replication_record"}},"created_at":"2026-05-18T00:27:08.893939+00:00","updated_at":"2026-05-18T00:27:08.893939+00:00"}