{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5ZRJRFPHGAOU6KDUNIL37Y66YQ","short_pith_number":"pith:5ZRJRFPH","schema_version":"1.0","canonical_sha256":"ee629895e7301d4f28746a17bfe3dec405884c06bce406b6f1aa493bb1ea69a1","source":{"kind":"arxiv","id":"2112.06126","version":2},"attestation_state":"computed","paper":{"title":"Neural Network Quantization for Efficient Inference: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Olivia Weng","submitted_at":"2021-12-08T22:49:39Z","abstract_excerpt":"As neural networks have become more powerful, there has been a rising desire to deploy them in the real world; however, the power and accuracy of neural networks is largely due to their depth and complexity, making them difficult to deploy, especially in resource-constrained devices. Neural network quantization has recently arisen to meet this demand of reducing the size and complexity of neural networks by reducing the precision of a network. With smaller and simpler networks, it becomes possible to run neural networks within the constraints of their target hardware. This paper surveys the ma"},"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":"2112.06126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-08T22:49:39Z","cross_cats_sorted":[],"title_canon_sha256":"351e8dae3d4465d25a1a715d3f13a3a792f0c96236d04a74f52c6d65401d9cfd","abstract_canon_sha256":"e8e07e1aea6f64f81489365fc160544f3227317be6ad91004562901048d65edb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:59.213587Z","signature_b64":"XVilCsKJW3pCby7los4TIMskOpRKqbbPjjGgJ2OeakpbXlz2RIvSuWHwtLMBoXZbR7yUos0ErSc9zYw4scCvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee629895e7301d4f28746a17bfe3dec405884c06bce406b6f1aa493bb1ea69a1","last_reissued_at":"2026-07-05T05:33:59.213127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:59.213127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Quantization for Efficient Inference: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Olivia Weng","submitted_at":"2021-12-08T22:49:39Z","abstract_excerpt":"As neural networks have become more powerful, there has been a rising desire to deploy them in the real world; however, the power and accuracy of neural networks is largely due to their depth and complexity, making them difficult to deploy, especially in resource-constrained devices. Neural network quantization has recently arisen to meet this demand of reducing the size and complexity of neural networks by reducing the precision of a network. With smaller and simpler networks, it becomes possible to run neural networks within the constraints of their target hardware. This paper surveys the ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06126","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/2112.06126/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":"2112.06126","created_at":"2026-07-05T05:33:59.213191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06126v2","created_at":"2026-07-05T05:33:59.213191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06126","created_at":"2026-07-05T05:33:59.213191+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZRJRFPHGAOU","created_at":"2026-07-05T05:33:59.213191+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZRJRFPHGAOU6KDU","created_at":"2026-07-05T05:33:59.213191+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZRJRFPH","created_at":"2026-07-05T05:33:59.213191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16138","citing_title":"SNAC-Pack 2.0: Scaled-Out Surrogate Neural Architecture Codesign","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09696","citing_title":"Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ","json":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ.json","graph_json":"https://pith.science/api/pith-number/5ZRJRFPHGAOU6KDUNIL37Y66YQ/graph.json","events_json":"https://pith.science/api/pith-number/5ZRJRFPHGAOU6KDUNIL37Y66YQ/events.json","paper":"https://pith.science/paper/5ZRJRFPH"},"agent_actions":{"view_html":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ","download_json":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ.json","view_paper":"https://pith.science/paper/5ZRJRFPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06126&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZRJRFPHGAOU6KDUNIL37Y66YQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZRJRFPHGAOU6KDUNIL37Y66YQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ/action/storage_attestation","attest_author":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ/action/author_attestation","sign_citation":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ/action/citation_signature","submit_replication":"https://pith.science/pith/5ZRJRFPHGAOU6KDUNIL37Y66YQ/action/replication_record"}},"created_at":"2026-07-05T05:33:59.213191+00:00","updated_at":"2026-07-05T05:33:59.213191+00:00"}