{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:44LO573FK32P3YCI2PEWFK5FEJ","short_pith_number":"pith:44LO573F","schema_version":"1.0","canonical_sha256":"e716eeff6556f4fde048d3c962aba52252064eccd740bcb46983cb7927f7c45b","source":{"kind":"arxiv","id":"2410.08855","version":1},"attestation_state":"computed","paper":{"title":"MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Alessio Burrello, Arne Symons, Daniele Jahier Pagliari, Francesco Daghero, Giuseppe Maria Sarda, Josse Van Delm, Luca Benini, Marian Verhelst, Mohamed Amine Hamdi","submitted_at":"2024-10-11T14:32:06Z","abstract_excerpt":"Streamlining the deployment of Deep Neural Networks (DNNs) on heterogeneous edge platforms, coupling within the same micro-controller unit (MCU) instruction processors and hardware accelerators for tensor computations, is becoming one of the crucial challenges of the TinyML field.\n  The best-performing DNN compilation toolchains are usually deeply customized for a single MCU family, and porting to a different heterogeneous MCU family implies labor-intensive re-development of almost the entire compiler. On the opposite side, retargetable toolchains, such as TVM, fail to exploit the capabilities"},"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":"2410.08855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-10-11T14:32:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76171c0bc14957e40e380ca068d9b742a724a986aa22754527aef2392c3cfafb","abstract_canon_sha256":"7886a6246dcf1ddc88fa2caa9ef974da8e36b9bfec029a4caf640e742110898a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:18.659132Z","signature_b64":"ftrLcCI9uO+qOG2DCaT65hrxKixoqLNWTbKHvx7P00mH/QJCC8qTFOD/clkB/eJTP7Oe+2mKuJl5XKbyCxdiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e716eeff6556f4fde048d3c962aba52252064eccd740bcb46983cb7927f7c45b","last_reissued_at":"2026-07-05T09:19:18.658649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:18.658649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Alessio Burrello, Arne Symons, Daniele Jahier Pagliari, Francesco Daghero, Giuseppe Maria Sarda, Josse Van Delm, Luca Benini, Marian Verhelst, Mohamed Amine Hamdi","submitted_at":"2024-10-11T14:32:06Z","abstract_excerpt":"Streamlining the deployment of Deep Neural Networks (DNNs) on heterogeneous edge platforms, coupling within the same micro-controller unit (MCU) instruction processors and hardware accelerators for tensor computations, is becoming one of the crucial challenges of the TinyML field.\n  The best-performing DNN compilation toolchains are usually deeply customized for a single MCU family, and porting to a different heterogeneous MCU family implies labor-intensive re-development of almost the entire compiler. On the opposite side, retargetable toolchains, such as TVM, fail to exploit the capabilities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08855","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/2410.08855/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":"2410.08855","created_at":"2026-07-05T09:19:18.658707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08855v1","created_at":"2026-07-05T09:19:18.658707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08855","created_at":"2026-07-05T09:19:18.658707+00:00"},{"alias_kind":"pith_short_12","alias_value":"44LO573FK32P","created_at":"2026-07-05T09:19:18.658707+00:00"},{"alias_kind":"pith_short_16","alias_value":"44LO573FK32P3YCI","created_at":"2026-07-05T09:19:18.658707+00:00"},{"alias_kind":"pith_short_8","alias_value":"44LO573F","created_at":"2026-07-05T09:19:18.658707+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/44LO573FK32P3YCI2PEWFK5FEJ","json":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ.json","graph_json":"https://pith.science/api/pith-number/44LO573FK32P3YCI2PEWFK5FEJ/graph.json","events_json":"https://pith.science/api/pith-number/44LO573FK32P3YCI2PEWFK5FEJ/events.json","paper":"https://pith.science/paper/44LO573F"},"agent_actions":{"view_html":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ","download_json":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ.json","view_paper":"https://pith.science/paper/44LO573F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08855&json=true","fetch_graph":"https://pith.science/api/pith-number/44LO573FK32P3YCI2PEWFK5FEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/44LO573FK32P3YCI2PEWFK5FEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ/action/storage_attestation","attest_author":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ/action/author_attestation","sign_citation":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ/action/citation_signature","submit_replication":"https://pith.science/pith/44LO573FK32P3YCI2PEWFK5FEJ/action/replication_record"}},"created_at":"2026-07-05T09:19:18.658707+00:00","updated_at":"2026-07-05T09:19:18.658707+00:00"}