{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JZ4RA4GHWUQJXYK2YQX6UARBDC","short_pith_number":"pith:JZ4RA4GH","schema_version":"1.0","canonical_sha256":"4e791070c7b5209be15ac42fea0221188d9481719e91c93a60c11eb75fff3302","source":{"kind":"arxiv","id":"2209.15560","version":1},"attestation_state":"computed","paper":{"title":"Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Hari Prabhat Gupta, Rahul Mishra","submitted_at":"2022-09-30T16:18:24Z","abstract_excerpt":"Automated feature extraction capability and significant performance of Deep Neural Networks (DNN) make them suitable for Internet of Things (IoT) applications. However, deploying DNN on edge devices becomes prohibitive due to the colossal computation, energy, and storage requirements. This paper presents a novel approach for designing and training lightweight DNN using large-size DNN. The approach considers the available storage, processing speed, and maximum allowable processing time to execute the task on edge devices. We present a knowledge distillation based training procedure to train the"},"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":"2209.15560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T16:18:24Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a18240fff9b99d6870834c9b35a54b00c6ec4e2e8739d6d09f1de219f2e7ac5e","abstract_canon_sha256":"8d1072c1b537e3a49663ad9e15e2a31e635ec2f4111842693364b698980b3e2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:21.013809Z","signature_b64":"I+sNLNcxoRiWFBkM+7MHKmUtQDBhrmh+UgizE931yqOH3rvsR8PlW8+bl3jn13lHd+qTRBJ9S0j3hgN62+XpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e791070c7b5209be15ac42fea0221188d9481719e91c93a60c11eb75fff3302","last_reissued_at":"2026-07-05T05:02:21.013406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:21.013406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Hari Prabhat Gupta, Rahul Mishra","submitted_at":"2022-09-30T16:18:24Z","abstract_excerpt":"Automated feature extraction capability and significant performance of Deep Neural Networks (DNN) make them suitable for Internet of Things (IoT) applications. However, deploying DNN on edge devices becomes prohibitive due to the colossal computation, energy, and storage requirements. This paper presents a novel approach for designing and training lightweight DNN using large-size DNN. The approach considers the available storage, processing speed, and maximum allowable processing time to execute the task on edge devices. We present a knowledge distillation based training procedure to train the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15560","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/2209.15560/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":"2209.15560","created_at":"2026-07-05T05:02:21.013461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15560v1","created_at":"2026-07-05T05:02:21.013461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15560","created_at":"2026-07-05T05:02:21.013461+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZ4RA4GHWUQJ","created_at":"2026-07-05T05:02:21.013461+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZ4RA4GHWUQJXYK2","created_at":"2026-07-05T05:02:21.013461+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZ4RA4GH","created_at":"2026-07-05T05:02:21.013461+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/JZ4RA4GHWUQJXYK2YQX6UARBDC","json":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC.json","graph_json":"https://pith.science/api/pith-number/JZ4RA4GHWUQJXYK2YQX6UARBDC/graph.json","events_json":"https://pith.science/api/pith-number/JZ4RA4GHWUQJXYK2YQX6UARBDC/events.json","paper":"https://pith.science/paper/JZ4RA4GH"},"agent_actions":{"view_html":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC","download_json":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC.json","view_paper":"https://pith.science/paper/JZ4RA4GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15560&json=true","fetch_graph":"https://pith.science/api/pith-number/JZ4RA4GHWUQJXYK2YQX6UARBDC/graph.json","fetch_events":"https://pith.science/api/pith-number/JZ4RA4GHWUQJXYK2YQX6UARBDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC/action/storage_attestation","attest_author":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC/action/author_attestation","sign_citation":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC/action/citation_signature","submit_replication":"https://pith.science/pith/JZ4RA4GHWUQJXYK2YQX6UARBDC/action/replication_record"}},"created_at":"2026-07-05T05:02:21.013461+00:00","updated_at":"2026-07-05T05:02:21.013461+00:00"}