{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GGZP545WBQOGY7N2GVCUL7WJNT","short_pith_number":"pith:GGZP545W","schema_version":"1.0","canonical_sha256":"31b2fef3b60c1c6c7dba354545fec96cd24cf33bb3105f2307a6ce6864faef12","source":{"kind":"arxiv","id":"2412.09687","version":1},"attestation_state":"computed","paper":{"title":"DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Cano, Paul Henderson, Wenhao Hu","submitted_at":"2024-12-12T19:03:53Z","abstract_excerpt":"Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy, existing methods for quantizing activations rely on complex mathematical computations or perform extensive searches for the best hyper-parameters. However, these expensive operations are impractical on devices with limited computation capabilities, memory capacities, and energy budgets. Furthermore, many existing methods do not focus on sub-6-bit (or deep) qua"},"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":"2412.09687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T19:03:53Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1f08687b65583854d3bf947334b6992389de0dea33e79b1e4cf6a3fe6595d1f9","abstract_canon_sha256":"4fa0c715198cf13f9cd5085ca4486c2c2345c6ab4e1507807735226cf0c10b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:40.121351Z","signature_b64":"DQZyRmKxtqVeY/ASFic3s2LnpR9B26HiTgxrodblQI+0sAvB0Eu8U/PWA7ojDQi6TueIPo/eJyFzwjrEzL4nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31b2fef3b60c1c6c7dba354545fec96cd24cf33bb3105f2307a6ce6864faef12","last_reissued_at":"2026-07-05T09:48:40.120898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:40.120898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Cano, Paul Henderson, Wenhao Hu","submitted_at":"2024-12-12T19:03:53Z","abstract_excerpt":"Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy, existing methods for quantizing activations rely on complex mathematical computations or perform extensive searches for the best hyper-parameters. However, these expensive operations are impractical on devices with limited computation capabilities, memory capacities, and energy budgets. Furthermore, many existing methods do not focus on sub-6-bit (or deep) qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09687","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/2412.09687/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":"2412.09687","created_at":"2026-07-05T09:48:40.120947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09687v1","created_at":"2026-07-05T09:48:40.120947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09687","created_at":"2026-07-05T09:48:40.120947+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGZP545WBQOG","created_at":"2026-07-05T09:48:40.120947+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGZP545WBQOGY7N2","created_at":"2026-07-05T09:48:40.120947+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGZP545W","created_at":"2026-07-05T09:48:40.120947+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/GGZP545WBQOGY7N2GVCUL7WJNT","json":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT.json","graph_json":"https://pith.science/api/pith-number/GGZP545WBQOGY7N2GVCUL7WJNT/graph.json","events_json":"https://pith.science/api/pith-number/GGZP545WBQOGY7N2GVCUL7WJNT/events.json","paper":"https://pith.science/paper/GGZP545W"},"agent_actions":{"view_html":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT","download_json":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT.json","view_paper":"https://pith.science/paper/GGZP545W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09687&json=true","fetch_graph":"https://pith.science/api/pith-number/GGZP545WBQOGY7N2GVCUL7WJNT/graph.json","fetch_events":"https://pith.science/api/pith-number/GGZP545WBQOGY7N2GVCUL7WJNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT/action/storage_attestation","attest_author":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT/action/author_attestation","sign_citation":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT/action/citation_signature","submit_replication":"https://pith.science/pith/GGZP545WBQOGY7N2GVCUL7WJNT/action/replication_record"}},"created_at":"2026-07-05T09:48:40.120947+00:00","updated_at":"2026-07-05T09:48:40.120947+00:00"}