{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:THBEHIH6SKX6GAQLDSWWGIYIE6","short_pith_number":"pith:THBEHIH6","schema_version":"1.0","canonical_sha256":"99c243a0fe92afe3020b1cad63230827bb1e1c71d250cd57f60840589727f664","source":{"kind":"arxiv","id":"2109.04236","version":2},"attestation_state":"computed","paper":{"title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Becking, Karsten M\\\"uller, Maximilian Dreyer, Sebastian Lapuschkin, Wojciech Samek","submitted_at":"2021-09-09T12:57:06Z","abstract_excerpt":"The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce these overheads, while preserving model performance as much as possible, and include parameter reduction techniques, parameter quantization, and lossless compression techniques.\n  In this chapter, we develop and describe a novel quantization paradigm fo"},"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":"2109.04236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-09T12:57:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9160fddd2948f0a1408c771906176ac62f62c6c1495ce2b9335414f1088ce652","abstract_canon_sha256":"9a833440ed6f162fcea3c66f8bf34455f91b5f3b57bc4719b4318eaef65655de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:59.091950Z","signature_b64":"vOHNi5jrqW7QqqY3Vgiq2ZeM9LM+CmeSDsHMyco5EkjSrsmVtMLD3KiLNkbt95P9crrkv/K69nFEcnYrvExLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c243a0fe92afe3020b1cad63230827bb1e1c71d250cd57f60840589727f664","last_reissued_at":"2026-07-05T08:27:59.091525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:59.091525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Becking, Karsten M\\\"uller, Maximilian Dreyer, Sebastian Lapuschkin, Wojciech Samek","submitted_at":"2021-09-09T12:57:06Z","abstract_excerpt":"The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce these overheads, while preserving model performance as much as possible, and include parameter reduction techniques, parameter quantization, and lossless compression techniques.\n  In this chapter, we develop and describe a novel quantization paradigm fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04236","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/2109.04236/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":"2109.04236","created_at":"2026-07-05T08:27:59.091575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04236v2","created_at":"2026-07-05T08:27:59.091575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04236","created_at":"2026-07-05T08:27:59.091575+00:00"},{"alias_kind":"pith_short_12","alias_value":"THBEHIH6SKX6","created_at":"2026-07-05T08:27:59.091575+00:00"},{"alias_kind":"pith_short_16","alias_value":"THBEHIH6SKX6GAQL","created_at":"2026-07-05T08:27:59.091575+00:00"},{"alias_kind":"pith_short_8","alias_value":"THBEHIH6","created_at":"2026-07-05T08:27:59.091575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16760","citing_title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6","json":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6.json","graph_json":"https://pith.science/api/pith-number/THBEHIH6SKX6GAQLDSWWGIYIE6/graph.json","events_json":"https://pith.science/api/pith-number/THBEHIH6SKX6GAQLDSWWGIYIE6/events.json","paper":"https://pith.science/paper/THBEHIH6"},"agent_actions":{"view_html":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6","download_json":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6.json","view_paper":"https://pith.science/paper/THBEHIH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04236&json=true","fetch_graph":"https://pith.science/api/pith-number/THBEHIH6SKX6GAQLDSWWGIYIE6/graph.json","fetch_events":"https://pith.science/api/pith-number/THBEHIH6SKX6GAQLDSWWGIYIE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6/action/storage_attestation","attest_author":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6/action/author_attestation","sign_citation":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6/action/citation_signature","submit_replication":"https://pith.science/pith/THBEHIH6SKX6GAQLDSWWGIYIE6/action/replication_record"}},"created_at":"2026-07-05T08:27:59.091575+00:00","updated_at":"2026-07-05T08:27:59.091575+00:00"}