{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7JRX5GUWFMNDVNNFN47UPKNHP3","short_pith_number":"pith:7JRX5GUW","schema_version":"1.0","canonical_sha256":"fa637e9a962b1a3ab5a56f3f47a9a77eeaa1dd8f90e3dcfb0ad9197c89745b26","source":{"kind":"arxiv","id":"1905.13298","version":5},"attestation_state":"computed","paper":{"title":"DeepShift: Towards Multiplication-Less Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Farhan Shafiq, Joey Yiwei Li, Mostafa Elhoushi, Ye Henry Tian, Zihao Chen","submitted_at":"2019-05-30T20:50:21Z","abstract_excerpt":"The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CNNs is time and energy-intensive even on high-grade servers. Convolution layers and fully connected layers, because of their intense use of multiplications, are the dominant contributor to this computation budget.\n  We propose to alleviate this problem by introducing two new operations: convolutional shifts and fully-connected shifts which replace multiplications with bitwise sh"},"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":"1905.13298","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T20:50:21Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c0ae1f461e9b25c1b99342c81b64312d16a24aad01c7100fc76ddbaf033e04dd","abstract_canon_sha256":"3669b0467aa7e6fe11a712ba9ad877e3d782d0338c1b872921db286ae01fd8db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:03.436297Z","signature_b64":"eYgmr4DjTwCZTUzjsfP1aGOg332kfKhLFR7KtbGJDETwoIDrZ60C08W18tveOlgJfA23c8TsDTEI2Zi/D7xDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa637e9a962b1a3ab5a56f3f47a9a77eeaa1dd8f90e3dcfb0ad9197c89745b26","last_reissued_at":"2026-07-05T02:56:03.435654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:03.435654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepShift: Towards Multiplication-Less Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Farhan Shafiq, Joey Yiwei Li, Mostafa Elhoushi, Ye Henry Tian, Zihao Chen","submitted_at":"2019-05-30T20:50:21Z","abstract_excerpt":"The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CNNs is time and energy-intensive even on high-grade servers. Convolution layers and fully connected layers, because of their intense use of multiplications, are the dominant contributor to this computation budget.\n  We propose to alleviate this problem by introducing two new operations: convolutional shifts and fully-connected shifts which replace multiplications with bitwise sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13298","kind":"arxiv","version":5},"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/1905.13298/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":"1905.13298","created_at":"2026-07-05T02:56:03.435737+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13298v5","created_at":"2026-07-05T02:56:03.435737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13298","created_at":"2026-07-05T02:56:03.435737+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JRX5GUWFMND","created_at":"2026-07-05T02:56:03.435737+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JRX5GUWFMNDVNNF","created_at":"2026-07-05T02:56:03.435737+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JRX5GUW","created_at":"2026-07-05T02:56:03.435737+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/7JRX5GUWFMNDVNNFN47UPKNHP3","json":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3.json","graph_json":"https://pith.science/api/pith-number/7JRX5GUWFMNDVNNFN47UPKNHP3/graph.json","events_json":"https://pith.science/api/pith-number/7JRX5GUWFMNDVNNFN47UPKNHP3/events.json","paper":"https://pith.science/paper/7JRX5GUW"},"agent_actions":{"view_html":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3","download_json":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3.json","view_paper":"https://pith.science/paper/7JRX5GUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13298&json=true","fetch_graph":"https://pith.science/api/pith-number/7JRX5GUWFMNDVNNFN47UPKNHP3/graph.json","fetch_events":"https://pith.science/api/pith-number/7JRX5GUWFMNDVNNFN47UPKNHP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3/action/storage_attestation","attest_author":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3/action/author_attestation","sign_citation":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3/action/citation_signature","submit_replication":"https://pith.science/pith/7JRX5GUWFMNDVNNFN47UPKNHP3/action/replication_record"}},"created_at":"2026-07-05T02:56:03.435737+00:00","updated_at":"2026-07-05T02:56:03.435737+00:00"}