{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WDXYMYFQT7GL4W4FQBPI74QKAY","short_pith_number":"pith:WDXYMYFQ","schema_version":"1.0","canonical_sha256":"b0ef8660b09fccbe5b85805e8ff20a0608209e47d001da6aa3ab70440c57c815","source":{"kind":"arxiv","id":"2601.07600","version":3},"attestation_state":"computed","paper":{"title":"Performance Isolation for Inference Processes in Edge GPU Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.OS","authors_text":"Carles Hern\\'andez, Jos\\'e Flich, Juan Jos\\'e Mart\\'in","submitted_at":"2026-01-12T14:49:52Z","abstract_excerpt":"This work analyzes the main isolation mechanisms available in modern NVIDIA GPUs: MPS, MIG, and the recent Green Contexts, to ensure predictable inference time in safety-critical applications using deep learning models. The experimental methodology includes performance tests, evaluation of partitioning impact, and analysis of temporal isolation between processes, considering both the NVIDIA A100 and Jetson Orin platforms. It is observed that MIG provides a high level of isolation. At the same time, Green Contexts represent a promising alternative for edge devices by enabling fine-grained SM al"},"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":"2601.07600","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-01-12T14:49:52Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"1b96eed8ecb9c8fc95b076226d9ef6865d73f75b37ee754f180d1ec42465d36a","abstract_canon_sha256":"76ff7ec2e8725fa4ba5c69f942bded4cb1712ff4e569909cf049f5a725417de2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:03.247913Z","signature_b64":"4WtZaFOYm4vgpthCISLJPGxuhcnFc6uYnrjjUy96QrdrtlH+FYJsL2MZwUR+3KA44KE6PG6I3K4fGPSxAqRICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0ef8660b09fccbe5b85805e8ff20a0608209e47d001da6aa3ab70440c57c815","last_reissued_at":"2026-07-14T01:22:03.246956Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:03.246956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Isolation for Inference Processes in Edge GPU Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.OS","authors_text":"Carles Hern\\'andez, Jos\\'e Flich, Juan Jos\\'e Mart\\'in","submitted_at":"2026-01-12T14:49:52Z","abstract_excerpt":"This work analyzes the main isolation mechanisms available in modern NVIDIA GPUs: MPS, MIG, and the recent Green Contexts, to ensure predictable inference time in safety-critical applications using deep learning models. The experimental methodology includes performance tests, evaluation of partitioning impact, and analysis of temporal isolation between processes, considering both the NVIDIA A100 and Jetson Orin platforms. It is observed that MIG provides a high level of isolation. At the same time, Green Contexts represent a promising alternative for edge devices by enabling fine-grained SM al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07600","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.07600/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":"2601.07600","created_at":"2026-07-14T01:22:03.247422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.07600v3","created_at":"2026-07-14T01:22:03.247422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07600","created_at":"2026-07-14T01:22:03.247422+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDXYMYFQT7GL","created_at":"2026-07-14T01:22:03.247422+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDXYMYFQT7GL4W4F","created_at":"2026-07-14T01:22:03.247422+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDXYMYFQ","created_at":"2026-07-14T01:22:03.247422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.23831","citing_title":"Architectural Isolation as a Timing Safety Primitive for Edge AI Medical Devices: Controlled Experimental Evidence on a Shared-Silicon Platform","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY","json":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY.json","graph_json":"https://pith.science/api/pith-number/WDXYMYFQT7GL4W4FQBPI74QKAY/graph.json","events_json":"https://pith.science/api/pith-number/WDXYMYFQT7GL4W4FQBPI74QKAY/events.json","paper":"https://pith.science/paper/WDXYMYFQ"},"agent_actions":{"view_html":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY","download_json":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY.json","view_paper":"https://pith.science/paper/WDXYMYFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.07600&json=true","fetch_graph":"https://pith.science/api/pith-number/WDXYMYFQT7GL4W4FQBPI74QKAY/graph.json","fetch_events":"https://pith.science/api/pith-number/WDXYMYFQT7GL4W4FQBPI74QKAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY/action/storage_attestation","attest_author":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY/action/author_attestation","sign_citation":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY/action/citation_signature","submit_replication":"https://pith.science/pith/WDXYMYFQT7GL4W4FQBPI74QKAY/action/replication_record"}},"created_at":"2026-07-14T01:22:03.247422+00:00","updated_at":"2026-07-14T01:22:03.247422+00:00"}