{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQBYZKMGFFJN63SZHHP3XCKQC3","short_pith_number":"pith:RQBYZKMG","schema_version":"1.0","canonical_sha256":"8c038ca9862952df6e5939dfbb895016d6091f7360a444900d6c73ed4ebe01e3","source":{"kind":"arxiv","id":"2508.21493","version":1},"attestation_state":"computed","paper":{"title":"SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Charalampos Bezaitis, Christoph Berganski, Felix Jentzsch, Ian Colbert, Jakoba Petri-Koenig, Magnus Sjalander, Michaela Blott, Michal Danilowicz, Thomas Preusser, Tomasz Kryjak, Yaman Umuroglu","submitted_at":"2025-08-29T10:19:06Z","abstract_excerpt":"While neural network quantization effectively reduces the cost of matrix multiplications, aggressive quantization can expose non-matrix-multiply operations as significant performance and resource bottlenecks on embedded systems. Addressing such bottlenecks requires a comprehensive approach to tailoring the precision across operations in the inference computation. To this end, we introduce scaled-integer range analysis (SIRA), a static analysis technique employing interval arithmetic to determine the range, scale, and bias for tensors in quantized neural networks. We show how this information c"},"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":"2508.21493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-08-29T10:19:06Z","cross_cats_sorted":[],"title_canon_sha256":"e324d864033793b3d0f058be5c32327eae8434fa7f12db49c56931e7c29e48c8","abstract_canon_sha256":"96a7cfc639bfad25c000b36cbad03120e2353228006b32ac2f7501aee2c75b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:35.654726Z","signature_b64":"aaK2mDlHbMXUQ879E+E0eXE6NplD/e6Zzp4DfUe02VB1S+VeLM0vgLqTD8DHVTrGe9+gMKUJ++IWd1I/X97GDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c038ca9862952df6e5939dfbb895016d6091f7360a444900d6c73ed4ebe01e3","last_reissued_at":"2026-07-05T12:01:35.654229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:35.654229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Charalampos Bezaitis, Christoph Berganski, Felix Jentzsch, Ian Colbert, Jakoba Petri-Koenig, Magnus Sjalander, Michaela Blott, Michal Danilowicz, Thomas Preusser, Tomasz Kryjak, Yaman Umuroglu","submitted_at":"2025-08-29T10:19:06Z","abstract_excerpt":"While neural network quantization effectively reduces the cost of matrix multiplications, aggressive quantization can expose non-matrix-multiply operations as significant performance and resource bottlenecks on embedded systems. Addressing such bottlenecks requires a comprehensive approach to tailoring the precision across operations in the inference computation. To this end, we introduce scaled-integer range analysis (SIRA), a static analysis technique employing interval arithmetic to determine the range, scale, and bias for tensors in quantized neural networks. We show how this information c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21493","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/2508.21493/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":"2508.21493","created_at":"2026-07-05T12:01:35.654284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21493v1","created_at":"2026-07-05T12:01:35.654284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21493","created_at":"2026-07-05T12:01:35.654284+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQBYZKMGFFJN","created_at":"2026-07-05T12:01:35.654284+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQBYZKMGFFJN63SZ","created_at":"2026-07-05T12:01:35.654284+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQBYZKMG","created_at":"2026-07-05T12:01:35.654284+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/RQBYZKMGFFJN63SZHHP3XCKQC3","json":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3.json","graph_json":"https://pith.science/api/pith-number/RQBYZKMGFFJN63SZHHP3XCKQC3/graph.json","events_json":"https://pith.science/api/pith-number/RQBYZKMGFFJN63SZHHP3XCKQC3/events.json","paper":"https://pith.science/paper/RQBYZKMG"},"agent_actions":{"view_html":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3","download_json":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3.json","view_paper":"https://pith.science/paper/RQBYZKMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21493&json=true","fetch_graph":"https://pith.science/api/pith-number/RQBYZKMGFFJN63SZHHP3XCKQC3/graph.json","fetch_events":"https://pith.science/api/pith-number/RQBYZKMGFFJN63SZHHP3XCKQC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3/action/storage_attestation","attest_author":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3/action/author_attestation","sign_citation":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3/action/citation_signature","submit_replication":"https://pith.science/pith/RQBYZKMGFFJN63SZHHP3XCKQC3/action/replication_record"}},"created_at":"2026-07-05T12:01:35.654284+00:00","updated_at":"2026-07-05T12:01:35.654284+00:00"}