{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JXGIG67RRRREMEADTRLHPFSJSI","short_pith_number":"pith:JXGIG67R","schema_version":"1.0","canonical_sha256":"4dcc837bf18c624610039c567796499237b3b0ff6021f19fb31f80649227b89f","source":{"kind":"arxiv","id":"2003.00146","version":2},"attestation_state":"computed","paper":{"title":"WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed T. Elthakeb, Charles-Alban Deledalle, FatemehSadat Mireshghallah, Hadi Esmaeilzadeh, Prannoy Pilligundla, Tarek Elgindi","submitted_at":"2020-02-29T01:19:55Z","abstract_excerpt":"As deep neural networks make their ways into different domains, their compute efficiency is becoming a first-order constraint. Deep quantization, which reduces the bitwidth of the operations (below 8 bits), offers a unique opportunity as it can reduce both the storage and compute requirements of the network super-linearly. However, if not employed with diligence, this can lead to significant accuracy loss. Due to the strong inter-dependence between layers and exhibiting different characteristics across the same network, choosing an optimal bitwidth per layer granularity is not a straight forwa"},"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":"2003.00146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-29T01:19:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ab77d7e09f3cf2c7d60b09ac22f782eb350193ea2be3ae04c364e692f3aa6e61","abstract_canon_sha256":"9ddb250e367e43fb8b990ae3513dabf7fdf22af11eabf620a490834253388aa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:52.419458Z","signature_b64":"xn2twWhR8l3L3h6zD2jHuDyyLD7gBxJ1v4iWrqrdJWibbDT9TF+/Aw9dNPetEpiZDdaKWFsIZGX1rF3HVNgsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dcc837bf18c624610039c567796499237b3b0ff6021f19fb31f80649227b89f","last_reissued_at":"2026-07-05T00:57:52.419046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:52.419046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed T. Elthakeb, Charles-Alban Deledalle, FatemehSadat Mireshghallah, Hadi Esmaeilzadeh, Prannoy Pilligundla, Tarek Elgindi","submitted_at":"2020-02-29T01:19:55Z","abstract_excerpt":"As deep neural networks make their ways into different domains, their compute efficiency is becoming a first-order constraint. Deep quantization, which reduces the bitwidth of the operations (below 8 bits), offers a unique opportunity as it can reduce both the storage and compute requirements of the network super-linearly. However, if not employed with diligence, this can lead to significant accuracy loss. Due to the strong inter-dependence between layers and exhibiting different characteristics across the same network, choosing an optimal bitwidth per layer granularity is not a straight forwa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00146","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.00146/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":"2003.00146","created_at":"2026-07-05T00:57:52.419103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.00146v2","created_at":"2026-07-05T00:57:52.419103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00146","created_at":"2026-07-05T00:57:52.419103+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXGIG67RRRRE","created_at":"2026-07-05T00:57:52.419103+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXGIG67RRRREMEAD","created_at":"2026-07-05T00:57:52.419103+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXGIG67R","created_at":"2026-07-05T00:57:52.419103+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/JXGIG67RRRREMEADTRLHPFSJSI","json":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI.json","graph_json":"https://pith.science/api/pith-number/JXGIG67RRRREMEADTRLHPFSJSI/graph.json","events_json":"https://pith.science/api/pith-number/JXGIG67RRRREMEADTRLHPFSJSI/events.json","paper":"https://pith.science/paper/JXGIG67R"},"agent_actions":{"view_html":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI","download_json":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI.json","view_paper":"https://pith.science/paper/JXGIG67R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.00146&json=true","fetch_graph":"https://pith.science/api/pith-number/JXGIG67RRRREMEADTRLHPFSJSI/graph.json","fetch_events":"https://pith.science/api/pith-number/JXGIG67RRRREMEADTRLHPFSJSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI/action/storage_attestation","attest_author":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI/action/author_attestation","sign_citation":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI/action/citation_signature","submit_replication":"https://pith.science/pith/JXGIG67RRRREMEADTRLHPFSJSI/action/replication_record"}},"created_at":"2026-07-05T00:57:52.419103+00:00","updated_at":"2026-07-05T00:57:52.419103+00:00"}