{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRJPOCPPOZJXH4TVGCF2E2IEJJ","short_pith_number":"pith:WRJPOCPP","schema_version":"1.0","canonical_sha256":"b452f709ef765373f275308ba269044a6f9c1928faa6d215018c73d473c9b1ed","source":{"kind":"arxiv","id":"2404.02947","version":1},"attestation_state":"computed","paper":{"title":"DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Kamjoo, Behnam Ghavami, Lesley Shannon, Steve Wilton","submitted_at":"2024-04-03T15:06:09Z","abstract_excerpt":"The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces a technique that effectively reduces the memory footprint of DNNs, accommodating the limitations of resource-constrained edge devices while preserving model accuracy. Our proposed technique, named Post-Training Intra-Layer Multi-Precision Quantization (PTILMPQ), employs a post-training quantization approach, eliminating the need for extensive training data. "},"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":"2404.02947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-03T15:06:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23b8793c37d114f000d0087fed0426778f36f1d778326b8c6364d1104fb7d495","abstract_canon_sha256":"a9157c0743a1f00069c301a675a4264ec31f1113c0cd837e789e851cede638b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:03.806539Z","signature_b64":"5YxMrYxr9bhilwtTZp5GWQd2wxYjvEjT/H3PHIgWTszRYtwKGVMYBzOpwKUNz3Kt1vuesIGnsrLPPatYDRCyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b452f709ef765373f275308ba269044a6f9c1928faa6d215018c73d473c9b1ed","last_reissued_at":"2026-07-05T08:04:03.806114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:03.806114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Kamjoo, Behnam Ghavami, Lesley Shannon, Steve Wilton","submitted_at":"2024-04-03T15:06:09Z","abstract_excerpt":"The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces a technique that effectively reduces the memory footprint of DNNs, accommodating the limitations of resource-constrained edge devices while preserving model accuracy. Our proposed technique, named Post-Training Intra-Layer Multi-Precision Quantization (PTILMPQ), employs a post-training quantization approach, eliminating the need for extensive training data. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02947","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/2404.02947/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":"2404.02947","created_at":"2026-07-05T08:04:03.806174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02947v1","created_at":"2026-07-05T08:04:03.806174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02947","created_at":"2026-07-05T08:04:03.806174+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRJPOCPPOZJX","created_at":"2026-07-05T08:04:03.806174+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRJPOCPPOZJXH4TV","created_at":"2026-07-05T08:04:03.806174+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRJPOCPP","created_at":"2026-07-05T08:04:03.806174+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/WRJPOCPPOZJXH4TVGCF2E2IEJJ","json":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ.json","graph_json":"https://pith.science/api/pith-number/WRJPOCPPOZJXH4TVGCF2E2IEJJ/graph.json","events_json":"https://pith.science/api/pith-number/WRJPOCPPOZJXH4TVGCF2E2IEJJ/events.json","paper":"https://pith.science/paper/WRJPOCPP"},"agent_actions":{"view_html":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ","download_json":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ.json","view_paper":"https://pith.science/paper/WRJPOCPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02947&json=true","fetch_graph":"https://pith.science/api/pith-number/WRJPOCPPOZJXH4TVGCF2E2IEJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WRJPOCPPOZJXH4TVGCF2E2IEJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ/action/storage_attestation","attest_author":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ/action/author_attestation","sign_citation":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ/action/citation_signature","submit_replication":"https://pith.science/pith/WRJPOCPPOZJXH4TVGCF2E2IEJJ/action/replication_record"}},"created_at":"2026-07-05T08:04:03.806174+00:00","updated_at":"2026-07-05T08:04:03.806174+00:00"}