{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XVAUXXEF5ASSIUY3UT7HOGUKB6","short_pith_number":"pith:XVAUXXEF","canonical_record":{"source":{"id":"2302.11665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T21:41:34Z","cross_cats_sorted":["cs.DC","cs.NI"],"title_canon_sha256":"23a6eccbcafdfda41e3e759b1cb62b300fc79db57b9d51bb1d4902a212b90078","abstract_canon_sha256":"b1932fa60a7d6117dded1ade57d5a2c124aa142e353fea75404db309a5901760"},"schema_version":"1.0"},"canonical_sha256":"bd414bdc85e82524531ba4fe771a8a0f93530b13299284c7ada5bc37469017e2","source":{"kind":"arxiv","id":"2302.11665","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11665","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11665v2","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11665","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"XVAUXXEF5ASS","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"XVAUXXEF5ASSIUY3","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"XVAUXXEF","created_at":"2026-07-05T06:32:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XVAUXXEF5ASSIUY3UT7HOGUKB6","target":"record","payload":{"canonical_record":{"source":{"id":"2302.11665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T21:41:34Z","cross_cats_sorted":["cs.DC","cs.NI"],"title_canon_sha256":"23a6eccbcafdfda41e3e759b1cb62b300fc79db57b9d51bb1d4902a212b90078","abstract_canon_sha256":"b1932fa60a7d6117dded1ade57d5a2c124aa142e353fea75404db309a5901760"},"schema_version":"1.0"},"canonical_sha256":"bd414bdc85e82524531ba4fe771a8a0f93530b13299284c7ada5bc37469017e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:36.912020Z","signature_b64":"e9gq4xeNbGukPuC66GkbtEADKa/xjwJ4bL2zc2VvrleEFGwtXjKZawzjU72t1qn+yfc263324KEpF6JSOBr8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd414bdc85e82524531ba4fe771a8a0f93530b13299284c7ada5bc37469017e2","last_reissued_at":"2026-07-05T06:32:36.911587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:36.911587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.11665","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gntvppLgHlioFNZafY/rexufNUqFK3J3iMOsmWaop6egrqRUgAgH5CZw21wEsq4IQXuNZA1p0BRmAHm5yDXqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:37:41.095266Z"},"content_sha256":"61de23a62758ef01aae485d14c31c9fe9b49ccc41369481b1c9aae54fafa6c68","schema_version":"1.0","event_id":"sha256:61de23a62758ef01aae485d14c31c9fe9b49ccc41369481b1c9aae54fafa6c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XVAUXXEF5ASSIUY3UT7HOGUKB6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.NI"],"primary_cat":"cs.LG","authors_text":"Hao Zhang, Ion Stoica, Joseph E. Gonzalez, Lianmin Zheng, Vincent Liu, Xin Jin, Yanping Huang, Ying Sheng, Yinmin Zhong, Zhifeng Chen, Zhuohan Li","submitted_at":"2023-02-22T21:41:34Z","abstract_excerpt":"Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device. In this paper, we demonstrate that model parallelism can be additionally used for the statistical multiplexing of multiple devices when serving multiple models, even when a single model can fit into a single device. Our work reveals a fundamental trade-off between the overhead introduced by model parallelism and the opportunity to exploit statistical multiplexing to reduce serving latency in the presence of bursty workloads. We explore the new trade-of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11665","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/2302.11665/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:32:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GYOHe9emQCPXGCuL64YjuFkmKvjKuxn3JphX8BfgxvOfeYk92+he9pwsQDm9q2RU6hNaDTFsxEj2FI4K/v7aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:37:41.095855Z"},"content_sha256":"6ace6ee0d60684f4c9757e79f7f4811d8827fa85858ac4b003e9095ab4bbcb59","schema_version":"1.0","event_id":"sha256:6ace6ee0d60684f4c9757e79f7f4811d8827fa85858ac4b003e9095ab4bbcb59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/bundle.json","state_url":"https://pith.science/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T15:37:41Z","links":{"resolver":"https://pith.science/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6","bundle":"https://pith.science/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/bundle.json","state":"https://pith.science/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVAUXXEF5ASSIUY3UT7HOGUKB6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XVAUXXEF5ASSIUY3UT7HOGUKB6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b1932fa60a7d6117dded1ade57d5a2c124aa142e353fea75404db309a5901760","cross_cats_sorted":["cs.DC","cs.NI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T21:41:34Z","title_canon_sha256":"23a6eccbcafdfda41e3e759b1cb62b300fc79db57b9d51bb1d4902a212b90078"},"schema_version":"1.0","source":{"id":"2302.11665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11665","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11665v2","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11665","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_12","alias_value":"XVAUXXEF5ASS","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_16","alias_value":"XVAUXXEF5ASSIUY3","created_at":"2026-07-05T06:32:36Z"},{"alias_kind":"pith_short_8","alias_value":"XVAUXXEF","created_at":"2026-07-05T06:32:36Z"}],"graph_snapshots":[{"event_id":"sha256:6ace6ee0d60684f4c9757e79f7f4811d8827fa85858ac4b003e9095ab4bbcb59","target":"graph","created_at":"2026-07-05T06:32:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.11665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device. In this paper, we demonstrate that model parallelism can be additionally used for the statistical multiplexing of multiple devices when serving multiple models, even when a single model can fit into a single device. Our work reveals a fundamental trade-off between the overhead introduced by model parallelism and the opportunity to exploit statistical multiplexing to reduce serving latency in the presence of bursty workloads. We explore the new trade-of","authors_text":"Hao Zhang, Ion Stoica, Joseph E. Gonzalez, Lianmin Zheng, Vincent Liu, Xin Jin, Yanping Huang, Ying Sheng, Yinmin Zhong, Zhifeng Chen, Zhuohan Li","cross_cats":["cs.DC","cs.NI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T21:41:34Z","title":"AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11665","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61de23a62758ef01aae485d14c31c9fe9b49ccc41369481b1c9aae54fafa6c68","target":"record","created_at":"2026-07-05T06:32:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b1932fa60a7d6117dded1ade57d5a2c124aa142e353fea75404db309a5901760","cross_cats_sorted":["cs.DC","cs.NI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T21:41:34Z","title_canon_sha256":"23a6eccbcafdfda41e3e759b1cb62b300fc79db57b9d51bb1d4902a212b90078"},"schema_version":"1.0","source":{"id":"2302.11665","kind":"arxiv","version":2}},"canonical_sha256":"bd414bdc85e82524531ba4fe771a8a0f93530b13299284c7ada5bc37469017e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd414bdc85e82524531ba4fe771a8a0f93530b13299284c7ada5bc37469017e2","first_computed_at":"2026-07-05T06:32:36.911587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:32:36.911587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9gq4xeNbGukPuC66GkbtEADKa/xjwJ4bL2zc2VvrleEFGwtXjKZawzjU72t1qn+yfc263324KEpF6JSOBr8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:32:36.912020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61de23a62758ef01aae485d14c31c9fe9b49ccc41369481b1c9aae54fafa6c68","sha256:6ace6ee0d60684f4c9757e79f7f4811d8827fa85858ac4b003e9095ab4bbcb59"],"state_sha256":"ca5655deecfab2f0b13234258631fe217c4d7927bd24a4b202319a3ba09ae438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r68dOM4LL9cAU1W5o/CPobsGUelqfDgjWzPhX9aOcwYns5PFH5JsEMKo4+eFOEsyJ+d59qs0awHQxre26h7kDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:37:41.110336Z","bundle_sha256":"9e2d190457d2935843b8c5f4c579258ac6d10fc8fcde664479743b0465aa390e"}}