{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FIJBFCC7XDAYDDEV6XYC4EUWFM","short_pith_number":"pith:FIJBFCC7","schema_version":"1.0","canonical_sha256":"2a1212885fb8c1818c95f5f02e12962b3fc6ca01a71a1fc7258e970be0d14728","source":{"kind":"arxiv","id":"2006.10226","version":1},"attestation_state":"computed","paper":{"title":"Efficient Execution of Quantized Deep Learning Models: A Compiler Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.DC","authors_text":"Animesh Jain, Masahiro Masuda, Shoubhik Bhattacharya, Vin Sharma, Yida Wang","submitted_at":"2020-06-18T01:38:10Z","abstract_excerpt":"A growing number of applications implement predictive functions using deep learning models, which require heavy use of compute and memory. One popular technique for increasing resource efficiency is 8-bit integer quantization, in which 32-bit floating point numbers (fp32) are represented using shorter 8-bit integer numbers. Although deep learning frameworks such as TensorFlow, TFLite, MXNet, and PyTorch enable developers to quantize models with only a small drop in accuracy, they are not well suited to execute quantized models on a variety of hardware platforms. For example, TFLite is optimize"},"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":"2006.10226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-06-18T01:38:10Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"5391b5b5d2b90b0536108fb10133994a67e4158d8cdcc74d241d77ad68228ffb","abstract_canon_sha256":"b111f2b75b2d42825a7f1f68f4ecb89e9dccbb3b49ceb45dc515e5a247042c66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:16.112925Z","signature_b64":"lLEQxJ82coSpPgU2neDlW9Wd1MzZ3CSCtGCQ4J7w1M9RBhgVRvBVSdt2tyJ24Kz9Fdi6ML1e4WKI5LMV0lufAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a1212885fb8c1818c95f5f02e12962b3fc6ca01a71a1fc7258e970be0d14728","last_reissued_at":"2026-07-05T01:11:16.112422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:16.112422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Execution of Quantized Deep Learning Models: A Compiler Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.DC","authors_text":"Animesh Jain, Masahiro Masuda, Shoubhik Bhattacharya, Vin Sharma, Yida Wang","submitted_at":"2020-06-18T01:38:10Z","abstract_excerpt":"A growing number of applications implement predictive functions using deep learning models, which require heavy use of compute and memory. One popular technique for increasing resource efficiency is 8-bit integer quantization, in which 32-bit floating point numbers (fp32) are represented using shorter 8-bit integer numbers. Although deep learning frameworks such as TensorFlow, TFLite, MXNet, and PyTorch enable developers to quantize models with only a small drop in accuracy, they are not well suited to execute quantized models on a variety of hardware platforms. For example, TFLite is optimize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10226","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10226/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":"2006.10226","created_at":"2026-07-05T01:11:16.112485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10226v1","created_at":"2026-07-05T01:11:16.112485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10226","created_at":"2026-07-05T01:11:16.112485+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIJBFCC7XDAY","created_at":"2026-07-05T01:11:16.112485+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIJBFCC7XDAYDDEV","created_at":"2026-07-05T01:11:16.112485+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIJBFCC7","created_at":"2026-07-05T01:11:16.112485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14789","citing_title":"A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM","json":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM.json","graph_json":"https://pith.science/api/pith-number/FIJBFCC7XDAYDDEV6XYC4EUWFM/graph.json","events_json":"https://pith.science/api/pith-number/FIJBFCC7XDAYDDEV6XYC4EUWFM/events.json","paper":"https://pith.science/paper/FIJBFCC7"},"agent_actions":{"view_html":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM","download_json":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM.json","view_paper":"https://pith.science/paper/FIJBFCC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10226&json=true","fetch_graph":"https://pith.science/api/pith-number/FIJBFCC7XDAYDDEV6XYC4EUWFM/graph.json","fetch_events":"https://pith.science/api/pith-number/FIJBFCC7XDAYDDEV6XYC4EUWFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM/action/storage_attestation","attest_author":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM/action/author_attestation","sign_citation":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM/action/citation_signature","submit_replication":"https://pith.science/pith/FIJBFCC7XDAYDDEV6XYC4EUWFM/action/replication_record"}},"created_at":"2026-07-05T01:11:16.112485+00:00","updated_at":"2026-07-05T01:11:16.112485+00:00"}