{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BITBCD4MEAFI3FK4XLLYTZXTMI","short_pith_number":"pith:BITBCD4M","schema_version":"1.0","canonical_sha256":"0a26110f8c200a8d955cbad789e6f36235fd200a852f36cd427df5088cdfc191","source":{"kind":"arxiv","id":"2605.17745","version":1},"attestation_state":"computed","paper":{"title":"StatQAT: Statistical Quantizer Optimization for Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Huang, Ke Ding, Mehmet Aktukmak","submitted_at":"2026-05-18T01:56:12Z","abstract_excerpt":"Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes, selecting optimal quantization parameters remains a key challenge, particularly for diverse data distributions encountered during training and inference. This work presents a novel statistical error analysis framework for uniform and floating-point quantization, providing theoretical insight into error behavior across quantization configurations. Building o"},"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":"2605.17745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T01:56:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4b297763089130f6c16f72607eadb02e2bf7486082a7e9a7812fdfa8316b936","abstract_canon_sha256":"d3122ba3583ff7e54f6d1806cfdc08e5e7c5ca2846c78eb49e1de9a50857e4ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:56.146240Z","signature_b64":"oitFzwPu4tcGPThOTeHAiGM02BCXGccs5oPeUod+UEPOFsBpMn3A4QSY7XQfDxOa1qVkEE9wkCZLs3WAKTf2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a26110f8c200a8d955cbad789e6f36235fd200a852f36cd427df5088cdfc191","last_reissued_at":"2026-05-20T00:04:56.145457Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:56.145457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StatQAT: Statistical Quantizer Optimization for Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Huang, Ke Ding, Mehmet Aktukmak","submitted_at":"2026-05-18T01:56:12Z","abstract_excerpt":"Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes, selecting optimal quantization parameters remains a key challenge, particularly for diverse data distributions encountered during training and inference. This work presents a novel statistical error analysis framework for uniform and floating-point quantization, providing theoretical insight into error behavior across quantization configurations. Building o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17745","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/2605.17745/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":"2605.17745","created_at":"2026-05-20T00:04:56.145588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17745v1","created_at":"2026-05-20T00:04:56.145588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17745","created_at":"2026-05-20T00:04:56.145588+00:00"},{"alias_kind":"pith_short_12","alias_value":"BITBCD4MEAFI","created_at":"2026-05-20T00:04:56.145588+00:00"},{"alias_kind":"pith_short_16","alias_value":"BITBCD4MEAFI3FK4","created_at":"2026-05-20T00:04:56.145588+00:00"},{"alias_kind":"pith_short_8","alias_value":"BITBCD4M","created_at":"2026-05-20T00:04:56.145588+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/BITBCD4MEAFI3FK4XLLYTZXTMI","json":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI.json","graph_json":"https://pith.science/api/pith-number/BITBCD4MEAFI3FK4XLLYTZXTMI/graph.json","events_json":"https://pith.science/api/pith-number/BITBCD4MEAFI3FK4XLLYTZXTMI/events.json","paper":"https://pith.science/paper/BITBCD4M"},"agent_actions":{"view_html":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI","download_json":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI.json","view_paper":"https://pith.science/paper/BITBCD4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17745&json=true","fetch_graph":"https://pith.science/api/pith-number/BITBCD4MEAFI3FK4XLLYTZXTMI/graph.json","fetch_events":"https://pith.science/api/pith-number/BITBCD4MEAFI3FK4XLLYTZXTMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI/action/storage_attestation","attest_author":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI/action/author_attestation","sign_citation":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI/action/citation_signature","submit_replication":"https://pith.science/pith/BITBCD4MEAFI3FK4XLLYTZXTMI/action/replication_record"}},"created_at":"2026-05-20T00:04:56.145588+00:00","updated_at":"2026-05-20T00:04:56.145588+00:00"}