{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCJA3GXKDNWGJDVWVUBHPSNSZN","short_pith_number":"pith:YCJA3GXK","schema_version":"1.0","canonical_sha256":"c0920d9aea1b6c648eb6ad0277c9b2cb537f670306c1bab803e3b82f2d6a8c96","source":{"kind":"arxiv","id":"2506.23934","version":1},"attestation_state":"computed","paper":{"title":"QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.DC","authors_text":"Bo Ji, Deepu John, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Saeid Ghafouri, Xiangchen Li","submitted_at":"2025-06-30T15:03:35Z","abstract_excerpt":"As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future inference queries across diverse edge devices, we argue that planning an inference pattern with a request-specific model tailored to the device's computational capacity, accuracy requirements, and time constraints is more cost-efficient and robust to diverse scenarios. To this end, we propose an accuracy-aware and workload-balanced inference system that integrates "},"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":"2506.23934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-06-30T15:03:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"218e01f74a50308c08e9a4c7830ab13762f53f56f3e0bc21d6169e2994b07667","abstract_canon_sha256":"74e2925fb5005be7e01f75fef09c742e4a3179cc2cce5cfbf44e7f55fb9dcbce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:30.345070Z","signature_b64":"OdHTSaA5AK6ODatWArH8dy2yMKBtaQ8RUzrLnCL0rqD8CRR8eBTK8cSGkPTOJtdGZ6JLhRDkhC8MEL0Vk1j+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0920d9aea1b6c648eb6ad0277c9b2cb537f670306c1bab803e3b82f2d6a8c96","last_reissued_at":"2026-07-05T11:29:30.344480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:30.344480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.DC","authors_text":"Bo Ji, Deepu John, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Saeid Ghafouri, Xiangchen Li","submitted_at":"2025-06-30T15:03:35Z","abstract_excerpt":"As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future inference queries across diverse edge devices, we argue that planning an inference pattern with a request-specific model tailored to the device's computational capacity, accuracy requirements, and time constraints is more cost-efficient and robust to diverse scenarios. To this end, we propose an accuracy-aware and workload-balanced inference system that integrates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23934","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/2506.23934/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":"2506.23934","created_at":"2026-07-05T11:29:30.344557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23934v1","created_at":"2026-07-05T11:29:30.344557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23934","created_at":"2026-07-05T11:29:30.344557+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCJA3GXKDNWG","created_at":"2026-07-05T11:29:30.344557+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCJA3GXKDNWGJDVW","created_at":"2026-07-05T11:29:30.344557+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCJA3GXK","created_at":"2026-07-05T11:29:30.344557+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/YCJA3GXKDNWGJDVWVUBHPSNSZN","json":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN.json","graph_json":"https://pith.science/api/pith-number/YCJA3GXKDNWGJDVWVUBHPSNSZN/graph.json","events_json":"https://pith.science/api/pith-number/YCJA3GXKDNWGJDVWVUBHPSNSZN/events.json","paper":"https://pith.science/paper/YCJA3GXK"},"agent_actions":{"view_html":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN","download_json":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN.json","view_paper":"https://pith.science/paper/YCJA3GXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23934&json=true","fetch_graph":"https://pith.science/api/pith-number/YCJA3GXKDNWGJDVWVUBHPSNSZN/graph.json","fetch_events":"https://pith.science/api/pith-number/YCJA3GXKDNWGJDVWVUBHPSNSZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN/action/storage_attestation","attest_author":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN/action/author_attestation","sign_citation":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN/action/citation_signature","submit_replication":"https://pith.science/pith/YCJA3GXKDNWGJDVWVUBHPSNSZN/action/replication_record"}},"created_at":"2026-07-05T11:29:30.344557+00:00","updated_at":"2026-07-05T11:29:30.344557+00:00"}