{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZOZWF3TQSSRZWUKZBHGLUG4QED","short_pith_number":"pith:ZOZWF3TQ","canonical_record":{"source":{"id":"2505.06641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-10T13:23:48Z","cross_cats_sorted":[],"title_canon_sha256":"883b7217672ef5e5a2610d9541efac6507fbdda59dd1a9c39a2e23bc4e4eace3","abstract_canon_sha256":"b6254063cfe81c4f9f2f3fbaaac14850d68f591f7df3e403b6a466b1edf7da39"},"schema_version":"1.0"},"canonical_sha256":"cbb362ee7094a39b515909ccba1b9020ef42b749a2cd75c49e2418f8ac03dda2","source":{"kind":"arxiv","id":"2505.06641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06641","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06641v1","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06641","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZOZWF3TQSSRZ","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZOZWF3TQSSRZWUKZ","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZOZWF3TQ","created_at":"2026-07-05T11:01:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZOZWF3TQSSRZWUKZBHGLUG4QED","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-10T13:23:48Z","cross_cats_sorted":[],"title_canon_sha256":"883b7217672ef5e5a2610d9541efac6507fbdda59dd1a9c39a2e23bc4e4eace3","abstract_canon_sha256":"b6254063cfe81c4f9f2f3fbaaac14850d68f591f7df3e403b6a466b1edf7da39"},"schema_version":"1.0"},"canonical_sha256":"cbb362ee7094a39b515909ccba1b9020ef42b749a2cd75c49e2418f8ac03dda2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:13.589219Z","signature_b64":"/fzMpwJ6t8VOhvNQpBRf6qgtjqTYsqX/XW0kDVJwF0wkFiHiXtO/PNiWuKSbwmoUrNaubMvUb3161dM+o3MuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb362ee7094a39b515909ccba1b9020ef42b749a2cd75c49e2418f8ac03dda2","last_reissued_at":"2026-07-05T11:01:13.588769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:13.588769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06641","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJG3npn2rLta23D2RUUlB2AvY59ngXvufXhsEHWRiypH7Q6OugxW5niCe6xkqemMU81b5QEDPMU7WEneGYDKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:40:54.790067Z"},"content_sha256":"307d26af22a82cac6cda80a9669faa2f1c266da084c348ca98d21c6dff68d5db","schema_version":"1.0","event_id":"sha256:307d26af22a82cac6cda80a9669faa2f1c266da084c348ca98d21c6dff68d5db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZOZWF3TQSSRZWUKZBHGLUG4QED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SneakPeek: Data-Aware Model Selection and Scheduling for Inference Serving on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Abhishek Chandra, Daniel Frink, Joel Wolfrath","submitted_at":"2025-05-10T13:23:48Z","abstract_excerpt":"Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many applications cannot rely on hardware scaling when deployed at the edge or other resource-constrained environments. In this work, we propose a model selection and scheduling algorithm that implements accuracy scaling to increase efficiency for these more constrained deployments. We show that existing schedulers that make decisions using profiled model accuracy are b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06641","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/2505.06641/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":"2026-07-05T11:01:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eF5MjgOMn/irwul3m5Wxw1rTIYaKM/oCTwqsEER7NroBGrTj1SU5Hy/mRH+k4qWJ9qWnvgwKnJXXLuGFcgbiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:40:54.790559Z"},"content_sha256":"bd8c365c5ad84949bab3c3aae62b04c7e9a06a332c26465e8da1959e25daa554","schema_version":"1.0","event_id":"sha256:bd8c365c5ad84949bab3c3aae62b04c7e9a06a332c26465e8da1959e25daa554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/bundle.json","state_url":"https://pith.science/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/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":"2026-08-17T15:40:54Z","links":{"resolver":"https://pith.science/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED","bundle":"https://pith.science/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/bundle.json","state":"https://pith.science/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOZWF3TQSSRZWUKZBHGLUG4QED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZOZWF3TQSSRZWUKZBHGLUG4QED","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":"b6254063cfe81c4f9f2f3fbaaac14850d68f591f7df3e403b6a466b1edf7da39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-10T13:23:48Z","title_canon_sha256":"883b7217672ef5e5a2610d9541efac6507fbdda59dd1a9c39a2e23bc4e4eace3"},"schema_version":"1.0","source":{"id":"2505.06641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06641","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06641v1","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06641","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZOZWF3TQSSRZ","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZOZWF3TQSSRZWUKZ","created_at":"2026-07-05T11:01:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZOZWF3TQ","created_at":"2026-07-05T11:01:13Z"}],"graph_snapshots":[{"event_id":"sha256:bd8c365c5ad84949bab3c3aae62b04c7e9a06a332c26465e8da1959e25daa554","target":"graph","created_at":"2026-07-05T11:01:13Z","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/2505.06641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many applications cannot rely on hardware scaling when deployed at the edge or other resource-constrained environments. In this work, we propose a model selection and scheduling algorithm that implements accuracy scaling to increase efficiency for these more constrained deployments. We show that existing schedulers that make decisions using profiled model accuracy are b","authors_text":"Abhishek Chandra, Daniel Frink, Joel Wolfrath","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-10T13:23:48Z","title":"SneakPeek: Data-Aware Model Selection and Scheduling for Inference Serving on the Edge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06641","kind":"arxiv","version":1},"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":"sha256:307d26af22a82cac6cda80a9669faa2f1c266da084c348ca98d21c6dff68d5db","target":"record","created_at":"2026-07-05T11:01:13Z","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":"b6254063cfe81c4f9f2f3fbaaac14850d68f591f7df3e403b6a466b1edf7da39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-10T13:23:48Z","title_canon_sha256":"883b7217672ef5e5a2610d9541efac6507fbdda59dd1a9c39a2e23bc4e4eace3"},"schema_version":"1.0","source":{"id":"2505.06641","kind":"arxiv","version":1}},"canonical_sha256":"cbb362ee7094a39b515909ccba1b9020ef42b749a2cd75c49e2418f8ac03dda2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb362ee7094a39b515909ccba1b9020ef42b749a2cd75c49e2418f8ac03dda2","first_computed_at":"2026-07-05T11:01:13.588769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:13.588769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/fzMpwJ6t8VOhvNQpBRf6qgtjqTYsqX/XW0kDVJwF0wkFiHiXtO/PNiWuKSbwmoUrNaubMvUb3161dM+o3MuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:13.589219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:307d26af22a82cac6cda80a9669faa2f1c266da084c348ca98d21c6dff68d5db","sha256:bd8c365c5ad84949bab3c3aae62b04c7e9a06a332c26465e8da1959e25daa554"],"state_sha256":"c10d5aa14351d0ed6cf6508d1c718e96c0d1e49e1b95e26369decc441e82cfe4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3KPuvk2NTtNun9qUe/9Idxz0OCXx3P3d/1ATcKa0MLFwjOa3HRrBKd2g9AtU5nOby4DsgOgywQjBtMvXitzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:40:54.794756Z","bundle_sha256":"9596bdf70f75a432f50d22c57301720d09c5c497ca0835b2afc66a221076fc74"}}