{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:P3V6JET7X4DOJP2IMPXBDSG5WZ","short_pith_number":"pith:P3V6JET7","schema_version":"1.0","canonical_sha256":"7eebe4927fbf06e4bf4863ee11c8ddb6731e95bc6b1b69fbbce3b633d4cdc3d3","source":{"kind":"arxiv","id":"1901.06414","version":2},"attestation_state":"computed","paper":{"title":"Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eyy\\\"ub Sari, Mouloud Belbahri, Sajad Darabi, Vahid Partovi Nia","submitted_at":"2019-01-18T20:39:12Z","abstract_excerpt":"Deep neural networks (DNNs) have demonstrated success for many supervised learning tasks, ranging from voice recognition, object detection, to image classification. However, their increasing complexity might yield poor generalization error that make them hard to be deployed on edge devices. Quantization is an effective approach to compress DNNs in order to meet these constraints. Using a quasiconvex base function in order to construct a binary quantizer helps training binary neural networks (BNNs) and adding noise to the input data or using a concrete regularization function helps to improve g"},"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":"1901.06414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-18T20:39:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d0a233c3c614d87108e2225c8dbadae5240ed13f87226c6fb8c0cecc6af2c259","abstract_canon_sha256":"f45a4aa8fee81ce1531bf4ebb14944e296723e924326d32b5348920df3573ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:20.348839Z","signature_b64":"dbfvvsmowK07cWXMI7MhHwIs24mY7Z0aaKMr7wG6TiFuQ7E5O5Dhl0y9jP27+bQtuCHC9F1IAPKBSqwtzTD/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eebe4927fbf06e4bf4863ee11c8ddb6731e95bc6b1b69fbbce3b633d4cdc3d3","last_reissued_at":"2026-05-17T23:45:20.348155Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:20.348155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eyy\\\"ub Sari, Mouloud Belbahri, Sajad Darabi, Vahid Partovi Nia","submitted_at":"2019-01-18T20:39:12Z","abstract_excerpt":"Deep neural networks (DNNs) have demonstrated success for many supervised learning tasks, ranging from voice recognition, object detection, to image classification. However, their increasing complexity might yield poor generalization error that make them hard to be deployed on edge devices. Quantization is an effective approach to compress DNNs in order to meet these constraints. Using a quasiconvex base function in order to construct a binary quantizer helps training binary neural networks (BNNs) and adding noise to the input data or using a concrete regularization function helps to improve g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06414","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":"1901.06414","created_at":"2026-05-17T23:45:20.348243+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.06414v2","created_at":"2026-05-17T23:45:20.348243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06414","created_at":"2026-05-17T23:45:20.348243+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3V6JET7X4DO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3V6JET7X4DOJP2I","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3V6JET7","created_at":"2026-05-18T12:33:24.271573+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/P3V6JET7X4DOJP2IMPXBDSG5WZ","json":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ.json","graph_json":"https://pith.science/api/pith-number/P3V6JET7X4DOJP2IMPXBDSG5WZ/graph.json","events_json":"https://pith.science/api/pith-number/P3V6JET7X4DOJP2IMPXBDSG5WZ/events.json","paper":"https://pith.science/paper/P3V6JET7"},"agent_actions":{"view_html":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ","download_json":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ.json","view_paper":"https://pith.science/paper/P3V6JET7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.06414&json=true","fetch_graph":"https://pith.science/api/pith-number/P3V6JET7X4DOJP2IMPXBDSG5WZ/graph.json","fetch_events":"https://pith.science/api/pith-number/P3V6JET7X4DOJP2IMPXBDSG5WZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ/action/storage_attestation","attest_author":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ/action/author_attestation","sign_citation":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ/action/citation_signature","submit_replication":"https://pith.science/pith/P3V6JET7X4DOJP2IMPXBDSG5WZ/action/replication_record"}},"created_at":"2026-05-17T23:45:20.348243+00:00","updated_at":"2026-05-17T23:45:20.348243+00:00"}