{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3G3NFGA4JAJC4Y6FZB7KKYGWL","short_pith_number":"pith:Z3G3NFGA","schema_version":"1.0","canonical_sha256":"cecdb694c0e24091731e2e43f52b06b2c336ca90759b6e67b5e91e78eaa0cd44","source":{"kind":"arxiv","id":"2412.03915","version":1},"attestation_state":"computed","paper":{"title":"Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alireza Maleki, Mahsa Lavaei, Mohsen Bagheritabar, Salar Beigzad, Zahra Abadi","submitted_at":"2024-12-05T06:34:06Z","abstract_excerpt":"Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high importance which demands even more available resources. In this work, we introduce an approach that combines saliency-guided training with quantization techniques to create an interpretable and resource-efficient model without compromising accuracy. We utilize Parameterized Clipping Activation (PACT) to perform quantization-aware training, specifically targeti"},"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":"2412.03915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T06:34:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bb818d036f5791ad275d08c128286a6e0dd00728db8a7008082cf3244a2065ca","abstract_canon_sha256":"57cc02d4004712a9f079aec277ed1502408244766ed2e1758f2e2072fdf22cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:56.307200Z","signature_b64":"xsa74a5XO9tx37k3PlKaGJy23qTgzz4By8ScxjCjzOtMDvswO1PHx8TWwezEWgMWFGDIz+A+QZh+puRcCnI/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cecdb694c0e24091731e2e43f52b06b2c336ca90759b6e67b5e91e78eaa0cd44","last_reissued_at":"2026-07-05T09:44:56.306718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:56.306718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alireza Maleki, Mahsa Lavaei, Mohsen Bagheritabar, Salar Beigzad, Zahra Abadi","submitted_at":"2024-12-05T06:34:06Z","abstract_excerpt":"Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high importance which demands even more available resources. In this work, we introduce an approach that combines saliency-guided training with quantization techniques to create an interpretable and resource-efficient model without compromising accuracy. We utilize Parameterized Clipping Activation (PACT) to perform quantization-aware training, specifically targeti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03915","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/2412.03915/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":"2412.03915","created_at":"2026-07-05T09:44:56.306776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03915v1","created_at":"2026-07-05T09:44:56.306776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03915","created_at":"2026-07-05T09:44:56.306776+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3G3NFGA4JAJ","created_at":"2026-07-05T09:44:56.306776+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3G3NFGA4JAJC4Y6","created_at":"2026-07-05T09:44:56.306776+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3G3NFGA","created_at":"2026-07-05T09:44:56.306776+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/Z3G3NFGA4JAJC4Y6FZB7KKYGWL","json":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL.json","graph_json":"https://pith.science/api/pith-number/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/graph.json","events_json":"https://pith.science/api/pith-number/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/events.json","paper":"https://pith.science/paper/Z3G3NFGA"},"agent_actions":{"view_html":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL","download_json":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL.json","view_paper":"https://pith.science/paper/Z3G3NFGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03915&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/action/storage_attestation","attest_author":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/action/author_attestation","sign_citation":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/action/citation_signature","submit_replication":"https://pith.science/pith/Z3G3NFGA4JAJC4Y6FZB7KKYGWL/action/replication_record"}},"created_at":"2026-07-05T09:44:56.306776+00:00","updated_at":"2026-07-05T09:44:56.306776+00:00"}