{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2Q2MATGTWNNSQOYHPEDLLV7WKT","short_pith_number":"pith:2Q2MATGT","schema_version":"1.0","canonical_sha256":"d434c04cd3b35b283b077906b5d7f654ec9e07b134c5eb8cc1f9fa16c488bb05","source":{"kind":"arxiv","id":"1905.01416","version":3},"attestation_state":"computed","paper":{"title":"SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed T. Elthakeb, Hadi Esmaeilzadeh, Prannoy Pilligundla","submitted_at":"2019-05-04T03:13:46Z","abstract_excerpt":"Deep quantization of neural networks (below eight bits) offers significant promise in reducing their compute and storage cost. Albeit alluring, without special techniques for training and optimization, deep quantization results in significant accuracy loss. To further mitigate this loss, we propose a novel sinusoidal regularization, called SinReQ1, for deep quantized training. SinReQ adds a periodic term to the original objective function of the underlying training algorithm. SinReQ exploits the periodicity, differentiability, and the desired convexity profile in sinusoidal functions to automa"},"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":"1905.01416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T03:13:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8a08a9cfd9cdf4bba9657990008601d1b010aa6a35dac9408d30c458fab9a314","abstract_canon_sha256":"67374c856e223761ea5c69cb7092a5a48d4122c32593b703a18c5c1ef89ed500"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:04.679556Z","signature_b64":"TaoJMSzBUBhXaIwuTJGIlIJ62Vz/KeoAUN/uvhfts6PjGVTP3ncR7Ghq9QdXLjV4z5vG48RHIQYaqpC4uYNXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d434c04cd3b35b283b077906b5d7f654ec9e07b134c5eb8cc1f9fa16c488bb05","last_reissued_at":"2026-07-05T00:23:04.679122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:04.679122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed T. Elthakeb, Hadi Esmaeilzadeh, Prannoy Pilligundla","submitted_at":"2019-05-04T03:13:46Z","abstract_excerpt":"Deep quantization of neural networks (below eight bits) offers significant promise in reducing their compute and storage cost. Albeit alluring, without special techniques for training and optimization, deep quantization results in significant accuracy loss. To further mitigate this loss, we propose a novel sinusoidal regularization, called SinReQ1, for deep quantized training. SinReQ adds a periodic term to the original objective function of the underlying training algorithm. SinReQ exploits the periodicity, differentiability, and the desired convexity profile in sinusoidal functions to automa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01416","kind":"arxiv","version":3},"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/1905.01416/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":"1905.01416","created_at":"2026-07-05T00:23:04.679192+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.01416v3","created_at":"2026-07-05T00:23:04.679192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01416","created_at":"2026-07-05T00:23:04.679192+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q2MATGTWNNS","created_at":"2026-07-05T00:23:04.679192+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q2MATGTWNNSQOYH","created_at":"2026-07-05T00:23:04.679192+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q2MATGT","created_at":"2026-07-05T00:23:04.679192+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/2Q2MATGTWNNSQOYHPEDLLV7WKT","json":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT.json","graph_json":"https://pith.science/api/pith-number/2Q2MATGTWNNSQOYHPEDLLV7WKT/graph.json","events_json":"https://pith.science/api/pith-number/2Q2MATGTWNNSQOYHPEDLLV7WKT/events.json","paper":"https://pith.science/paper/2Q2MATGT"},"agent_actions":{"view_html":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT","download_json":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT.json","view_paper":"https://pith.science/paper/2Q2MATGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.01416&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q2MATGTWNNSQOYHPEDLLV7WKT/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q2MATGTWNNSQOYHPEDLLV7WKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT/action/storage_attestation","attest_author":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT/action/author_attestation","sign_citation":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT/action/citation_signature","submit_replication":"https://pith.science/pith/2Q2MATGTWNNSQOYHPEDLLV7WKT/action/replication_record"}},"created_at":"2026-07-05T00:23:04.679192+00:00","updated_at":"2026-07-05T00:23:04.679192+00:00"}