{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PFOMXDIWNTIBC5QUCWCDIZY7Z2","short_pith_number":"pith:PFOMXDIW","schema_version":"1.0","canonical_sha256":"795ccb8d166cd0117614158434671fceb57ab7ba813fbf6b61442bd3f2cca052","source":{"kind":"arxiv","id":"2012.02792","version":1},"attestation_state":"computed","paper":{"title":"Weight Update Skipping: Reducing Training Time for Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ismail Akturk, Pooneh Safayenikoo","submitted_at":"2020-12-05T15:12:10Z","abstract_excerpt":"Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. These networks mostly use deep layers of convolution or fully connected layers with many filters in each layer, demanding a large amount of data and tunable hyperparameters to achieve competitive accuracy. As a result, storage, communication, and computational costs of training (in particular training time) become limiting factors to scale them up. In this paper, we propos"},"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":"2012.02792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-05T15:12:10Z","cross_cats_sorted":[],"title_canon_sha256":"b44c87844c379e14827392dde12096d8b4dc068637bca7bc75585e343a84b864","abstract_canon_sha256":"1801d545633a1995c69e79e151a7a819071ede59f3de11b10b8feb28091c3c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:22.610220Z","signature_b64":"9jTQucwRNmlpzjZdUvYauqdtS/mouGaUuvN+C1RBe5ppZ1CIBckdTJnafeJzqimk0QmS/s6zTNIGpdTGNRIDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"795ccb8d166cd0117614158434671fceb57ab7ba813fbf6b61442bd3f2cca052","last_reissued_at":"2026-07-05T01:57:22.609727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:22.609727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weight Update Skipping: Reducing Training Time for Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ismail Akturk, Pooneh Safayenikoo","submitted_at":"2020-12-05T15:12:10Z","abstract_excerpt":"Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. These networks mostly use deep layers of convolution or fully connected layers with many filters in each layer, demanding a large amount of data and tunable hyperparameters to achieve competitive accuracy. As a result, storage, communication, and computational costs of training (in particular training time) become limiting factors to scale them up. In this paper, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02792","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/2012.02792/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":"2012.02792","created_at":"2026-07-05T01:57:22.609786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02792v1","created_at":"2026-07-05T01:57:22.609786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02792","created_at":"2026-07-05T01:57:22.609786+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFOMXDIWNTIB","created_at":"2026-07-05T01:57:22.609786+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFOMXDIWNTIBC5QU","created_at":"2026-07-05T01:57:22.609786+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFOMXDIW","created_at":"2026-07-05T01:57:22.609786+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/PFOMXDIWNTIBC5QUCWCDIZY7Z2","json":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2.json","graph_json":"https://pith.science/api/pith-number/PFOMXDIWNTIBC5QUCWCDIZY7Z2/graph.json","events_json":"https://pith.science/api/pith-number/PFOMXDIWNTIBC5QUCWCDIZY7Z2/events.json","paper":"https://pith.science/paper/PFOMXDIW"},"agent_actions":{"view_html":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2","download_json":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2.json","view_paper":"https://pith.science/paper/PFOMXDIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02792&json=true","fetch_graph":"https://pith.science/api/pith-number/PFOMXDIWNTIBC5QUCWCDIZY7Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/PFOMXDIWNTIBC5QUCWCDIZY7Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2/action/storage_attestation","attest_author":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2/action/author_attestation","sign_citation":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2/action/citation_signature","submit_replication":"https://pith.science/pith/PFOMXDIWNTIBC5QUCWCDIZY7Z2/action/replication_record"}},"created_at":"2026-07-05T01:57:22.609786+00:00","updated_at":"2026-07-05T01:57:22.609786+00:00"}