{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:FEWM7NYPDFZDEYZFLWFAR2J2UO","short_pith_number":"pith:FEWM7NYP","schema_version":"1.0","canonical_sha256":"292ccfb70f19723263255d8a08e93aa3911d4a360e3c90bba014cb442a8708d0","source":{"kind":"arxiv","id":"1511.00175","version":2},"attestation_state":"computed","paper":{"title":"FireCaffe: near-linear acceleration of deep neural network training on compute clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Forrest N. Iandola, Khalid Ashraf, Kurt Keutzer, Matthew W. Moskewicz","submitted_at":"2015-10-31T21:13:30Z","abstract_excerpt":"Long training times for high-accuracy deep neural networks (DNNs) impede research into new DNN architectures and slow the development of high-accuracy DNNs. In this paper we present FireCaffe, which successfully scales deep neural network training across a cluster of GPUs. We also present a number of best practices to aid in comparing advancements in methods for scaling and accelerating the training of deep neural networks. The speed and scalability of distributed algorithms is almost always limited by the overhead of communicating between servers; DNN training is not an exception to this rule"},"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":"1511.00175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-10-31T21:13:30Z","cross_cats_sorted":[],"title_canon_sha256":"2e055b5653279e35c6c3dfae9cadea731af07eac66c721046e226d155077848f","abstract_canon_sha256":"59ec888da5749d413003d3d74b408173c0cf8f3703c8e73c58ce6ca66adbf7a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:11.871973Z","signature_b64":"RPI4tFuiKP5vler0Z/nNg2ZxJzbbU2FV0rPPZ5q57jyfMuFWcoBhHTDxrKOZreZNzD+V4EiXIaW5oc4B+D2XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292ccfb70f19723263255d8a08e93aa3911d4a360e3c90bba014cb442a8708d0","last_reissued_at":"2026-05-18T01:23:11.871475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:11.871475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireCaffe: near-linear acceleration of deep neural network training on compute clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Forrest N. Iandola, Khalid Ashraf, Kurt Keutzer, Matthew W. Moskewicz","submitted_at":"2015-10-31T21:13:30Z","abstract_excerpt":"Long training times for high-accuracy deep neural networks (DNNs) impede research into new DNN architectures and slow the development of high-accuracy DNNs. In this paper we present FireCaffe, which successfully scales deep neural network training across a cluster of GPUs. We also present a number of best practices to aid in comparing advancements in methods for scaling and accelerating the training of deep neural networks. The speed and scalability of distributed algorithms is almost always limited by the overhead of communicating between servers; DNN training is not an exception to this rule"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.00175","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1511.00175","created_at":"2026-05-18T01:23:11.871553+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.00175v2","created_at":"2026-05-18T01:23:11.871553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.00175","created_at":"2026-05-18T01:23:11.871553+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEWM7NYPDFZD","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEWM7NYPDFZDEYZF","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEWM7NYP","created_at":"2026-05-18T12:29:19.899920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10822","citing_title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO","json":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO.json","graph_json":"https://pith.science/api/pith-number/FEWM7NYPDFZDEYZFLWFAR2J2UO/graph.json","events_json":"https://pith.science/api/pith-number/FEWM7NYPDFZDEYZFLWFAR2J2UO/events.json","paper":"https://pith.science/paper/FEWM7NYP"},"agent_actions":{"view_html":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO","download_json":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO.json","view_paper":"https://pith.science/paper/FEWM7NYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.00175&json=true","fetch_graph":"https://pith.science/api/pith-number/FEWM7NYPDFZDEYZFLWFAR2J2UO/graph.json","fetch_events":"https://pith.science/api/pith-number/FEWM7NYPDFZDEYZFLWFAR2J2UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO/action/storage_attestation","attest_author":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO/action/author_attestation","sign_citation":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO/action/citation_signature","submit_replication":"https://pith.science/pith/FEWM7NYPDFZDEYZFLWFAR2J2UO/action/replication_record"}},"created_at":"2026-05-18T01:23:11.871553+00:00","updated_at":"2026-05-18T01:23:11.871553+00:00"}