{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F3LOXMFHUPWI3S55V2UW4ADI23","short_pith_number":"pith:F3LOXMFH","schema_version":"1.0","canonical_sha256":"2ed6ebb0a7a3ec8dcbbdaea96e0068d6c9f0a22643618f04bb493469ba028cd2","source":{"kind":"arxiv","id":"2501.04517","version":2},"attestation_state":"computed","paper":{"title":"Histogram-Equalized Quantization for logic-gated Residual Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Gilles Sicard, Van Thien Nguyen, William Guicquero","submitted_at":"2025-01-08T14:06:07Z","abstract_excerpt":"Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CIFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accur"},"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":"2501.04517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T14:06:07Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"0522d35ef8742835a83600ee1294e063d5905a3c891711d8ea26d7bd0aaf9c13","abstract_canon_sha256":"74219a56569de6a520b004a3fb0b38a6426ee82a9360797c59db49dacbb04a2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:02.679361Z","signature_b64":"MxSNBQIsWJme+Tozzqa2gvmF/4514I69G65CTb9KlDXL8jdcwLcCMM/wxpbsOHRmm6wcBrNuEnGVbmMumPGmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed6ebb0a7a3ec8dcbbdaea96e0068d6c9f0a22643618f04bb493469ba028cd2","last_reissued_at":"2026-07-05T09:59:02.678929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:02.678929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Histogram-Equalized Quantization for logic-gated Residual Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Gilles Sicard, Van Thien Nguyen, William Guicquero","submitted_at":"2025-01-08T14:06:07Z","abstract_excerpt":"Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CIFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04517","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/2501.04517/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":"2501.04517","created_at":"2026-07-05T09:59:02.678981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04517v2","created_at":"2026-07-05T09:59:02.678981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04517","created_at":"2026-07-05T09:59:02.678981+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3LOXMFHUPWI","created_at":"2026-07-05T09:59:02.678981+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3LOXMFHUPWI3S55","created_at":"2026-07-05T09:59:02.678981+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3LOXMFH","created_at":"2026-07-05T09:59:02.678981+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/F3LOXMFHUPWI3S55V2UW4ADI23","json":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23.json","graph_json":"https://pith.science/api/pith-number/F3LOXMFHUPWI3S55V2UW4ADI23/graph.json","events_json":"https://pith.science/api/pith-number/F3LOXMFHUPWI3S55V2UW4ADI23/events.json","paper":"https://pith.science/paper/F3LOXMFH"},"agent_actions":{"view_html":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23","download_json":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23.json","view_paper":"https://pith.science/paper/F3LOXMFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04517&json=true","fetch_graph":"https://pith.science/api/pith-number/F3LOXMFHUPWI3S55V2UW4ADI23/graph.json","fetch_events":"https://pith.science/api/pith-number/F3LOXMFHUPWI3S55V2UW4ADI23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23/action/storage_attestation","attest_author":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23/action/author_attestation","sign_citation":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23/action/citation_signature","submit_replication":"https://pith.science/pith/F3LOXMFHUPWI3S55V2UW4ADI23/action/replication_record"}},"created_at":"2026-07-05T09:59:02.678981+00:00","updated_at":"2026-07-05T09:59:02.678981+00:00"}