{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MCJVAQRT4G7QHQWHWAX7ASV5RL","short_pith_number":"pith:MCJVAQRT","canonical_record":{"source":{"id":"2105.03608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-08T06:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"5948e211303825ba59e8629e555296264e253196acf03c288e68960e656291aa","abstract_canon_sha256":"9bd94984465260d0d0652c2378a2f26066374024670df3b20d5f6aabc0fce91c"},"schema_version":"1.0"},"canonical_sha256":"6093504233e1bf03c2c7b02ff04abd8af02c1b76637ee5e8ab141bb4a76359b6","source":{"kind":"arxiv","id":"2105.03608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03608","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03608v1","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03608","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"MCJVAQRT4G7Q","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"MCJVAQRT4G7QHQWH","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"MCJVAQRT","created_at":"2026-07-05T02:38:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MCJVAQRT4G7QHQWHWAX7ASV5RL","target":"record","payload":{"canonical_record":{"source":{"id":"2105.03608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-08T06:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"5948e211303825ba59e8629e555296264e253196acf03c288e68960e656291aa","abstract_canon_sha256":"9bd94984465260d0d0652c2378a2f26066374024670df3b20d5f6aabc0fce91c"},"schema_version":"1.0"},"canonical_sha256":"6093504233e1bf03c2c7b02ff04abd8af02c1b76637ee5e8ab141bb4a76359b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:37.244052Z","signature_b64":"oX8OQTTfjrTmAgIg35/7T4NI6A5lXGogbGpEXCsd0N5TDywB7ewSwTDWmeFOpfmj2iXS8TaFUQLyylRXMMscAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6093504233e1bf03c2c7b02ff04abd8af02c1b76637ee5e8ab141bb4a76359b6","last_reissued_at":"2026-07-05T02:38:37.243629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:37.243629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.03608","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":"2026-07-05T02:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8eVcCq0jC3+fxTdCI7nvBaFzcPwtBuBeRQv3Asq6nI5muzYh5V4quwZiSKkLOvhDW1tQLo6CAj7y47DFbn3bDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:09:34.298974Z"},"content_sha256":"b5bd5604b38a6fba8c970e9d4429b3d8c1a6bc5b604b398804b122bd7d4fa7ca","schema_version":"1.0","event_id":"sha256:b5bd5604b38a6fba8c970e9d4429b3d8c1a6bc5b604b398804b122bd7d4fa7ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MCJVAQRT4G7QHQWHWAX7ASV5RL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimising Resource Management for Embedded Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bashir M Al-Hashimi, Geoff V. Merrett, Lei Xun, Long Tran-Thanh","submitted_at":"2021-05-08T06:10:05Z","abstract_excerpt":"Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in heterogeneous multi-core systems and show how they can be applied to optimise the performance of machine learning workloads. Performance can be defined using platform-dependent (e.g. speed, energy) and platform-independent (accuracy, confidence) metrics. In particular, we show how a Deep Neural Network (DNN) can be dynamically scalable to trade-off these variou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03608","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/2105.03608/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":"2026-07-05T02:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALarANFjIXAGbjWQLCsvfCh6K0JcosAxGK5s/odOSFDlPm2TwQBdkqSOgKcKRwpdBR7JfgS5uiRvz7FIzJTJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:09:34.299347Z"},"content_sha256":"de5d9dbd3e901a0d2b8ac638bd0661b4e51ac81225f5c512a1ed674fa3511058","schema_version":"1.0","event_id":"sha256:de5d9dbd3e901a0d2b8ac638bd0661b4e51ac81225f5c512a1ed674fa3511058"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/bundle.json","state_url":"https://pith.science/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/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":"2026-07-07T13:09:34Z","links":{"resolver":"https://pith.science/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL","bundle":"https://pith.science/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/bundle.json","state":"https://pith.science/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCJVAQRT4G7QHQWHWAX7ASV5RL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MCJVAQRT4G7QHQWHWAX7ASV5RL","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":"9bd94984465260d0d0652c2378a2f26066374024670df3b20d5f6aabc0fce91c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-08T06:10:05Z","title_canon_sha256":"5948e211303825ba59e8629e555296264e253196acf03c288e68960e656291aa"},"schema_version":"1.0","source":{"id":"2105.03608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03608","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03608v1","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03608","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"MCJVAQRT4G7Q","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"MCJVAQRT4G7QHQWH","created_at":"2026-07-05T02:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"MCJVAQRT","created_at":"2026-07-05T02:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:de5d9dbd3e901a0d2b8ac638bd0661b4e51ac81225f5c512a1ed674fa3511058","target":"graph","created_at":"2026-07-05T02:38:37Z","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/2105.03608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in heterogeneous multi-core systems and show how they can be applied to optimise the performance of machine learning workloads. Performance can be defined using platform-dependent (e.g. speed, energy) and platform-independent (accuracy, confidence) metrics. In particular, we show how a Deep Neural Network (DNN) can be dynamically scalable to trade-off these variou","authors_text":"Bashir M Al-Hashimi, Geoff V. Merrett, Lei Xun, Long Tran-Thanh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-08T06:10:05Z","title":"Optimising Resource Management for Embedded Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03608","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:b5bd5604b38a6fba8c970e9d4429b3d8c1a6bc5b604b398804b122bd7d4fa7ca","target":"record","created_at":"2026-07-05T02:38:37Z","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":"9bd94984465260d0d0652c2378a2f26066374024670df3b20d5f6aabc0fce91c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-08T06:10:05Z","title_canon_sha256":"5948e211303825ba59e8629e555296264e253196acf03c288e68960e656291aa"},"schema_version":"1.0","source":{"id":"2105.03608","kind":"arxiv","version":1}},"canonical_sha256":"6093504233e1bf03c2c7b02ff04abd8af02c1b76637ee5e8ab141bb4a76359b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6093504233e1bf03c2c7b02ff04abd8af02c1b76637ee5e8ab141bb4a76359b6","first_computed_at":"2026-07-05T02:38:37.243629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:37.243629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oX8OQTTfjrTmAgIg35/7T4NI6A5lXGogbGpEXCsd0N5TDywB7ewSwTDWmeFOpfmj2iXS8TaFUQLyylRXMMscAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:37.244052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5bd5604b38a6fba8c970e9d4429b3d8c1a6bc5b604b398804b122bd7d4fa7ca","sha256:de5d9dbd3e901a0d2b8ac638bd0661b4e51ac81225f5c512a1ed674fa3511058"],"state_sha256":"4079d5d82488c00a054ce03a52393d338553c84c643c6c694140229a3a55fcc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PxC4sko4XqXBoLgUXlml8TYCpYm3c8be7FJVt1eILW4+bxGplmf71ouwP2VNutYXeKI4InKP2yWFAOYysYiGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:09:34.302307Z","bundle_sha256":"5a6a250fe50cb1c5ce8d202649ea4febb0531dd22d54f59ae9cd2a1cd2fb9e64"}}