{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IWGOA56TWVOIGQEFXXL5ADGP7X","short_pith_number":"pith:IWGOA56T","schema_version":"1.0","canonical_sha256":"458ce077d3b55c834085bdd7d00ccffdf6aaa498d180b244dca59e10fa199390","source":{"kind":"arxiv","id":"2509.06362","version":1},"attestation_state":"computed","paper":{"title":"MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Mo Xuan, Wu Weigang, Zhang Yue","submitted_at":"2025-09-08T06:23:09Z","abstract_excerpt":"Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency. On the other hand, an LLM instance, when configured with different parallelism strategies and inference batch sizes, exhibits distinct performance characteristics and can thus be used to serve different SLO requirements. However, current LLM inference systems typically deploy instances of the same model with identical configurations, lacking mechanisms to le"},"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":"2509.06362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-09-08T06:23:09Z","cross_cats_sorted":[],"title_canon_sha256":"7599431d9fdf3ecbcfcdde5a7a722418f5a5f32eec1c2510ba80936c0bcec0c7","abstract_canon_sha256":"ccdb1b9beb3f5d4adf526d05b7c3c5cbc5cdd2850d1121af196f3e45e9f62a37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:34.366295Z","signature_b64":"2bwPiRbntHoWbhBME0N8zG0/SYkDM1O0h4Lv8CzyzczQNl15n9lHZ2YZEOlNTbTR+Z+OsCiFsom9pvZUmYfBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"458ce077d3b55c834085bdd7d00ccffdf6aaa498d180b244dca59e10fa199390","last_reissued_at":"2026-07-05T12:06:34.365809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:34.365809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Mo Xuan, Wu Weigang, Zhang Yue","submitted_at":"2025-09-08T06:23:09Z","abstract_excerpt":"Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency. On the other hand, an LLM instance, when configured with different parallelism strategies and inference batch sizes, exhibits distinct performance characteristics and can thus be used to serve different SLO requirements. However, current LLM inference systems typically deploy instances of the same model with identical configurations, lacking mechanisms to le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06362","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/2509.06362/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":"2509.06362","created_at":"2026-07-05T12:06:34.365866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06362v1","created_at":"2026-07-05T12:06:34.365866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06362","created_at":"2026-07-05T12:06:34.365866+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWGOA56TWVOI","created_at":"2026-07-05T12:06:34.365866+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWGOA56TWVOIGQEF","created_at":"2026-07-05T12:06:34.365866+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWGOA56T","created_at":"2026-07-05T12:06:34.365866+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/IWGOA56TWVOIGQEFXXL5ADGP7X","json":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X.json","graph_json":"https://pith.science/api/pith-number/IWGOA56TWVOIGQEFXXL5ADGP7X/graph.json","events_json":"https://pith.science/api/pith-number/IWGOA56TWVOIGQEFXXL5ADGP7X/events.json","paper":"https://pith.science/paper/IWGOA56T"},"agent_actions":{"view_html":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X","download_json":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X.json","view_paper":"https://pith.science/paper/IWGOA56T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06362&json=true","fetch_graph":"https://pith.science/api/pith-number/IWGOA56TWVOIGQEFXXL5ADGP7X/graph.json","fetch_events":"https://pith.science/api/pith-number/IWGOA56TWVOIGQEFXXL5ADGP7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X/action/storage_attestation","attest_author":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X/action/author_attestation","sign_citation":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X/action/citation_signature","submit_replication":"https://pith.science/pith/IWGOA56TWVOIGQEFXXL5ADGP7X/action/replication_record"}},"created_at":"2026-07-05T12:06:34.365866+00:00","updated_at":"2026-07-05T12:06:34.365866+00:00"}