{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OPNEFYOGFHM3A5QZG4L2MZMDTX","short_pith_number":"pith:OPNEFYOG","schema_version":"1.0","canonical_sha256":"73da42e1c629d9b076193717a665839de6607e6393f67b4c95f39e557139ebd7","source":{"kind":"arxiv","id":"1810.13329","version":1},"attestation_state":"computed","paper":{"title":"Convolutional Neural Network Quantization using Generalized Gamma Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Changgwun Lee, Doyun Kim, Han Young Yim, Inyup Kang, Sanghyuck Ha","submitted_at":"2018-10-31T15:17:05Z","abstract_excerpt":"As edge applications using convolutional neural networks (CNN) models grow, it is becoming necessary to introduce dedicated hardware accelerators in which network parameters and feature-map data are represented with limited precision. In this paper we propose a novel quantization algorithm for energy-efficient deployment of the hardware accelerators. For weights and biases, the optimal bit length of the fractional part is determined so that the quantization error is minimized over their distribution. For feature-map data, meanwhile, their sample distribution is well approximated with the gener"},"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":"1810.13329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-31T15:17:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58395ce3a6484f627b13e37d26e6318fb18c914f00eab027c0269eb5e097f664","abstract_canon_sha256":"fd93f2bd8a54b973d32bfe0541d93a579adfd8aeddfd43449dc4376244174591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:49.669983Z","signature_b64":"Yt0gPgUYq2TWUef2+PPT8FxpFIopGGnrhd69jcsncVBoKy0KBs3eXpPzv4uzJ+cQQoYEVNcfgPJaexDcDwBhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73da42e1c629d9b076193717a665839de6607e6393f67b4c95f39e557139ebd7","last_reissued_at":"2026-05-18T00:01:49.669457Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:49.669457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Neural Network Quantization using Generalized Gamma Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Changgwun Lee, Doyun Kim, Han Young Yim, Inyup Kang, Sanghyuck Ha","submitted_at":"2018-10-31T15:17:05Z","abstract_excerpt":"As edge applications using convolutional neural networks (CNN) models grow, it is becoming necessary to introduce dedicated hardware accelerators in which network parameters and feature-map data are represented with limited precision. In this paper we propose a novel quantization algorithm for energy-efficient deployment of the hardware accelerators. For weights and biases, the optimal bit length of the fractional part is determined so that the quantization error is minimized over their distribution. For feature-map data, meanwhile, their sample distribution is well approximated with the gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13329","kind":"arxiv","version":1},"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":"1810.13329","created_at":"2026-05-18T00:01:49.669548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.13329v1","created_at":"2026-05-18T00:01:49.669548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13329","created_at":"2026-05-18T00:01:49.669548+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPNEFYOGFHM3","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPNEFYOGFHM3A5QZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPNEFYOG","created_at":"2026-05-18T12:32:43.782077+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/OPNEFYOGFHM3A5QZG4L2MZMDTX","json":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX.json","graph_json":"https://pith.science/api/pith-number/OPNEFYOGFHM3A5QZG4L2MZMDTX/graph.json","events_json":"https://pith.science/api/pith-number/OPNEFYOGFHM3A5QZG4L2MZMDTX/events.json","paper":"https://pith.science/paper/OPNEFYOG"},"agent_actions":{"view_html":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX","download_json":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX.json","view_paper":"https://pith.science/paper/OPNEFYOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.13329&json=true","fetch_graph":"https://pith.science/api/pith-number/OPNEFYOGFHM3A5QZG4L2MZMDTX/graph.json","fetch_events":"https://pith.science/api/pith-number/OPNEFYOGFHM3A5QZG4L2MZMDTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX/action/storage_attestation","attest_author":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX/action/author_attestation","sign_citation":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX/action/citation_signature","submit_replication":"https://pith.science/pith/OPNEFYOGFHM3A5QZG4L2MZMDTX/action/replication_record"}},"created_at":"2026-05-18T00:01:49.669548+00:00","updated_at":"2026-05-18T00:01:49.669548+00:00"}