{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J66YEY4X3BDX3GBUZ2RQSKQFOS","short_pith_number":"pith:J66YEY4X","schema_version":"1.0","canonical_sha256":"4fbd826397d8477d9834cea3092a0574b3e903ff7c7d1040673d404d6604cfd2","source":{"kind":"arxiv","id":"1810.00861","version":3},"attestation_state":"computed","paper":{"title":"ProxQuant: Quantized Neural Networks via Proximal Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edo Liberty, Yu Bai, Yu-Xiang Wang","submitted_at":"2018-10-01T17:57:02Z","abstract_excerpt":"To make deep neural networks feasible in resource-constrained environments (such as mobile devices), it is beneficial to quantize models by using low-precision weights. One common technique for quantizing neural networks is the straight-through gradient method, which enables back-propagation through the quantization mapping. Despite its empirical success, little is understood about why the straight-through gradient method works.\n  Building upon a novel observation that the straight-through gradient method is in fact identical to the well-known Nesterov's dual-averaging algorithm on a quantizat"},"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":"1810.00861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:57:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8de4010ba96c2e30c252dfba540954b6674993da7ea4be9169d7897c5edec630","abstract_canon_sha256":"bd7473f8b2cc0936586016513fa72d370e2421b877ce6f068d4c79590c71feee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:05.027689Z","signature_b64":"/1RVepgwu9v1LlS8vVoJSjJCnFHNvlVnzmLxCrYknqWH0Ufa4fgFFz0sZnXVwr3hZ0+IsUcBcFsSaq87H5mDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fbd826397d8477d9834cea3092a0574b3e903ff7c7d1040673d404d6604cfd2","last_reissued_at":"2026-05-17T23:52:05.027257Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:05.027257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProxQuant: Quantized Neural Networks via Proximal Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edo Liberty, Yu Bai, Yu-Xiang Wang","submitted_at":"2018-10-01T17:57:02Z","abstract_excerpt":"To make deep neural networks feasible in resource-constrained environments (such as mobile devices), it is beneficial to quantize models by using low-precision weights. One common technique for quantizing neural networks is the straight-through gradient method, which enables back-propagation through the quantization mapping. Despite its empirical success, little is understood about why the straight-through gradient method works.\n  Building upon a novel observation that the straight-through gradient method is in fact identical to the well-known Nesterov's dual-averaging algorithm on a quantizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00861","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":""},"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":"1810.00861","created_at":"2026-05-17T23:52:05.027334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.00861v3","created_at":"2026-05-17T23:52:05.027334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00861","created_at":"2026-05-17T23:52:05.027334+00:00"},{"alias_kind":"pith_short_12","alias_value":"J66YEY4X3BDX","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J66YEY4X3BDX3GBU","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J66YEY4X","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27759","citing_title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS","json":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS.json","graph_json":"https://pith.science/api/pith-number/J66YEY4X3BDX3GBUZ2RQSKQFOS/graph.json","events_json":"https://pith.science/api/pith-number/J66YEY4X3BDX3GBUZ2RQSKQFOS/events.json","paper":"https://pith.science/paper/J66YEY4X"},"agent_actions":{"view_html":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS","download_json":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS.json","view_paper":"https://pith.science/paper/J66YEY4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.00861&json=true","fetch_graph":"https://pith.science/api/pith-number/J66YEY4X3BDX3GBUZ2RQSKQFOS/graph.json","fetch_events":"https://pith.science/api/pith-number/J66YEY4X3BDX3GBUZ2RQSKQFOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS/action/storage_attestation","attest_author":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS/action/author_attestation","sign_citation":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS/action/citation_signature","submit_replication":"https://pith.science/pith/J66YEY4X3BDX3GBUZ2RQSKQFOS/action/replication_record"}},"created_at":"2026-05-17T23:52:05.027334+00:00","updated_at":"2026-05-17T23:52:05.027334+00:00"}