{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PGL3VAVK2IF6V2EC6NJ27OD6XT","short_pith_number":"pith:PGL3VAVK","schema_version":"1.0","canonical_sha256":"7997ba82aad20beae882f353afb87ebcf38ce049c0e0bf0ec749781ab4bc7a87","source":{"kind":"arxiv","id":"1904.02835","version":1},"attestation_state":"computed","paper":{"title":"FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Marculescu, R. D. (shawn) Blanton, Ruizhou Ding, Ting-Wu Chin, Zeye Liu","submitted_at":"2019-04-05T00:27:16Z","abstract_excerpt":"To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\\in\\{1,2\\}$) of powers of 2. In such networks, the multiply-accumulate operation can be replaced with a single shift operation, or two shifts and an add operation. To provide even more design flexibility, the $k$ for each convolutional filter can be optimally chosen instead of being fixed for every filter. In this paper, we formulate the selection of $k$ to be differentiable, and describe model"},"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":"1904.02835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-05T00:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"b129a03af0146123277cf54994edc7bcc66d6e4c43bbb40d72d377cd91f79b26","abstract_canon_sha256":"3f4841e3a878d00596fca397837463599bd019da41b7888e2a372d24625a3e87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:19.499507Z","signature_b64":"67vd/sMoCq3Bluq7O/3LP/hVP1Q8YIo3rucn+pMZtQQZE9wKLpBa/op9VbiP5u+PkepC08oKGL63FN0JO+5/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7997ba82aad20beae882f353afb87ebcf38ce049c0e0bf0ec749781ab4bc7a87","last_reissued_at":"2026-05-17T23:49:19.498817Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:19.498817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Marculescu, R. D. (shawn) Blanton, Ruizhou Ding, Ting-Wu Chin, Zeye Liu","submitted_at":"2019-04-05T00:27:16Z","abstract_excerpt":"To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\\in\\{1,2\\}$) of powers of 2. In such networks, the multiply-accumulate operation can be replaced with a single shift operation, or two shifts and an add operation. To provide even more design flexibility, the $k$ for each convolutional filter can be optimally chosen instead of being fixed for every filter. In this paper, we formulate the selection of $k$ to be differentiable, and describe model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02835","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":"1904.02835","created_at":"2026-05-17T23:49:19.498915+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02835v1","created_at":"2026-05-17T23:49:19.498915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02835","created_at":"2026-05-17T23:49:19.498915+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGL3VAVK2IF6","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGL3VAVK2IF6V2EC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGL3VAVK","created_at":"2026-05-18T12:33:24.271573+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/PGL3VAVK2IF6V2EC6NJ27OD6XT","json":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT.json","graph_json":"https://pith.science/api/pith-number/PGL3VAVK2IF6V2EC6NJ27OD6XT/graph.json","events_json":"https://pith.science/api/pith-number/PGL3VAVK2IF6V2EC6NJ27OD6XT/events.json","paper":"https://pith.science/paper/PGL3VAVK"},"agent_actions":{"view_html":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT","download_json":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT.json","view_paper":"https://pith.science/paper/PGL3VAVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02835&json=true","fetch_graph":"https://pith.science/api/pith-number/PGL3VAVK2IF6V2EC6NJ27OD6XT/graph.json","fetch_events":"https://pith.science/api/pith-number/PGL3VAVK2IF6V2EC6NJ27OD6XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT/action/storage_attestation","attest_author":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT/action/author_attestation","sign_citation":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT/action/citation_signature","submit_replication":"https://pith.science/pith/PGL3VAVK2IF6V2EC6NJ27OD6XT/action/replication_record"}},"created_at":"2026-05-17T23:49:19.498915+00:00","updated_at":"2026-05-17T23:49:19.498915+00:00"}