{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QV55I6IMFP3BPTY5FSDQGKHX2F","short_pith_number":"pith:QV55I6IM","schema_version":"1.0","canonical_sha256":"857bd4790c2bf617cf1d2c870328f7d14418bfcfead6d08d40cd940d8d105c87","source":{"kind":"arxiv","id":"1908.06724","version":1},"attestation_state":"computed","paper":{"title":"Automatic Compiler Based FPGA Accelerator for CNN Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","eess.SP"],"primary_cat":"cs.LG","authors_text":"Aravind Dasu, Eriko Nurvithadhi, Jae-sun Seo, Shihui Yin, Shreyas Kolala Venkataramanaiah, Yu Cao, Yufei Ma","submitted_at":"2019-08-15T18:49:38Z","abstract_excerpt":"Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days. Designing flexible training hard-ware is much more challenging than inference hardware, due to design complexity and large computation/memory requirement. In this work, we present an automatic compiler-based FPGA accelerator with 16-bit fixed-point precision for complete CNNtraining, including Forward Pass (FP), Backward Pass (BP) and Weight Update (WU). We implemented an optimized RTL library to perform training-specific tasks and developed an RTL com"},"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":"1908.06724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T18:49:38Z","cross_cats_sorted":["cs.NE","eess.SP"],"title_canon_sha256":"5d61e18fd4eae7d7bc7d36ab307110f408c481d8f4e83d2ff7e62cc76e2bef04","abstract_canon_sha256":"490897a1319ba537ca5cce98abd2eb7f3bf8debae40a1ce76fbb392f9b1dc0e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:18.863672Z","signature_b64":"SHPSV0yr0UE/jLAwId3SK48T3/a4I+OltekMD9JUKR4vaTLgL2AQFbzlc6+/exflkb8AqvICOLfw0RnVnxZ9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"857bd4790c2bf617cf1d2c870328f7d14418bfcfead6d08d40cd940d8d105c87","last_reissued_at":"2026-07-04T23:58:18.863275Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:18.863275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Compiler Based FPGA Accelerator for CNN Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","eess.SP"],"primary_cat":"cs.LG","authors_text":"Aravind Dasu, Eriko Nurvithadhi, Jae-sun Seo, Shihui Yin, Shreyas Kolala Venkataramanaiah, Yu Cao, Yufei Ma","submitted_at":"2019-08-15T18:49:38Z","abstract_excerpt":"Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days. Designing flexible training hard-ware is much more challenging than inference hardware, due to design complexity and large computation/memory requirement. In this work, we present an automatic compiler-based FPGA accelerator with 16-bit fixed-point precision for complete CNNtraining, including Forward Pass (FP), Backward Pass (BP) and Weight Update (WU). We implemented an optimized RTL library to perform training-specific tasks and developed an RTL com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06724","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/1908.06724/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":"1908.06724","created_at":"2026-07-04T23:58:18.863337+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06724v1","created_at":"2026-07-04T23:58:18.863337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06724","created_at":"2026-07-04T23:58:18.863337+00:00"},{"alias_kind":"pith_short_12","alias_value":"QV55I6IMFP3B","created_at":"2026-07-04T23:58:18.863337+00:00"},{"alias_kind":"pith_short_16","alias_value":"QV55I6IMFP3BPTY5","created_at":"2026-07-04T23:58:18.863337+00:00"},{"alias_kind":"pith_short_8","alias_value":"QV55I6IM","created_at":"2026-07-04T23:58:18.863337+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/QV55I6IMFP3BPTY5FSDQGKHX2F","json":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F.json","graph_json":"https://pith.science/api/pith-number/QV55I6IMFP3BPTY5FSDQGKHX2F/graph.json","events_json":"https://pith.science/api/pith-number/QV55I6IMFP3BPTY5FSDQGKHX2F/events.json","paper":"https://pith.science/paper/QV55I6IM"},"agent_actions":{"view_html":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F","download_json":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F.json","view_paper":"https://pith.science/paper/QV55I6IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06724&json=true","fetch_graph":"https://pith.science/api/pith-number/QV55I6IMFP3BPTY5FSDQGKHX2F/graph.json","fetch_events":"https://pith.science/api/pith-number/QV55I6IMFP3BPTY5FSDQGKHX2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F/action/storage_attestation","attest_author":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F/action/author_attestation","sign_citation":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F/action/citation_signature","submit_replication":"https://pith.science/pith/QV55I6IMFP3BPTY5FSDQGKHX2F/action/replication_record"}},"created_at":"2026-07-04T23:58:18.863337+00:00","updated_at":"2026-07-04T23:58:18.863337+00:00"}