{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TRKB3S4ECBCQ23CIFA2QNMQVSZ","short_pith_number":"pith:TRKB3S4E","schema_version":"1.0","canonical_sha256":"9c541dcb8410450d6c48283506b215965b35bd9eaa483c90f339acb9cbc6d470","source":{"kind":"arxiv","id":"2301.13330","version":2},"attestation_state":"computed","paper":{"title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Deepika Bablani, Dharmendra S. Modha, Jeffrey L. McKinstry, Rathinakumar Appuswamy, Steven K. Esser","submitted_at":"2023-01-30T23:26:33Z","abstract_excerpt":"For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for simplifying networks. As each layer of a network may have different sensitivity to quantization, mixed precision quantization methods selectively tune the precision of individual layers to achieve a minimum drop in task performance (e.g., accuracy). To estimate the impact of layer precision choice on task performance, two methods are introduced: i) Entropy Ap"},"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":"2301.13330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T23:26:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5e8bc756d813f02f95bb4fec4ac0268cd05d9ef76d68b2e6a9a3f6957b61b047","abstract_canon_sha256":"aa0756fdfa1aa747eeacd8e3ba143d70d2321a0ad2cef4faf0b13cf334d14497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:16.785449Z","signature_b64":"f8lea56cm2Q5I39rIIm1OKJeLOu3+H5qbUfc6ZQzNjoaRShNRQYPYPS6UDIUiy7ocaYiCRS7IZctX46qGOseBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c541dcb8410450d6c48283506b215965b35bd9eaa483c90f339acb9cbc6d470","last_reissued_at":"2026-07-05T07:32:16.785003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:16.785003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Deepika Bablani, Dharmendra S. Modha, Jeffrey L. McKinstry, Rathinakumar Appuswamy, Steven K. Esser","submitted_at":"2023-01-30T23:26:33Z","abstract_excerpt":"For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for simplifying networks. As each layer of a network may have different sensitivity to quantization, mixed precision quantization methods selectively tune the precision of individual layers to achieve a minimum drop in task performance (e.g., accuracy). To estimate the impact of layer precision choice on task performance, two methods are introduced: i) Entropy Ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13330","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/2301.13330/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":"2301.13330","created_at":"2026-07-05T07:32:16.785059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13330v2","created_at":"2026-07-05T07:32:16.785059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13330","created_at":"2026-07-05T07:32:16.785059+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRKB3S4ECBCQ","created_at":"2026-07-05T07:32:16.785059+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRKB3S4ECBCQ23CI","created_at":"2026-07-05T07:32:16.785059+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRKB3S4E","created_at":"2026-07-05T07:32:16.785059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27884","citing_title":"SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ","json":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ.json","graph_json":"https://pith.science/api/pith-number/TRKB3S4ECBCQ23CIFA2QNMQVSZ/graph.json","events_json":"https://pith.science/api/pith-number/TRKB3S4ECBCQ23CIFA2QNMQVSZ/events.json","paper":"https://pith.science/paper/TRKB3S4E"},"agent_actions":{"view_html":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ","download_json":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ.json","view_paper":"https://pith.science/paper/TRKB3S4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13330&json=true","fetch_graph":"https://pith.science/api/pith-number/TRKB3S4ECBCQ23CIFA2QNMQVSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TRKB3S4ECBCQ23CIFA2QNMQVSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ/action/storage_attestation","attest_author":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ/action/author_attestation","sign_citation":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ/action/citation_signature","submit_replication":"https://pith.science/pith/TRKB3S4ECBCQ23CIFA2QNMQVSZ/action/replication_record"}},"created_at":"2026-07-05T07:32:16.785059+00:00","updated_at":"2026-07-05T07:32:16.785059+00:00"}