{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V7FPJR64QT7CPBYRITRJZ5EFVZ","short_pith_number":"pith:V7FPJR64","schema_version":"1.0","canonical_sha256":"afcaf4c7dc84fe27871144e29cf485ae6b52e2f75ad230cdfe80784750582560","source":{"kind":"arxiv","id":"1905.12300","version":1},"attestation_state":"computed","paper":{"title":"Attention Based Pruning for Shift Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Carlos Lassance, Ghouthi Boukli Hacene (IMT Atlantique - ELEC), Matthieu Courbariaux, Vincent Gripon (IMT Atlantique - ELEC), Yoshua Bengio (DIRO)","submitted_at":"2019-05-29T09:59:23Z","abstract_excerpt":"In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in order to reach state-of-the-art accuracy, thus resulting in complex and demanding systems that are poorly fitted to resource-limited devices. Recently, methods have been proposed to replace the generic convolution operator by the combination of a shift operation and a simpler 1x1 convolution. The resulting block, called Shift Layer (SL), is an efficient alter"},"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":"1905.12300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-05-29T09:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"bc05e0a73ffc5bbf154cfab176cca75236993c2c5554afb6f58a036c98d4859f","abstract_canon_sha256":"345e70ac58b4608e4df4ef069b3c3acc463fa760c5d4f110b0359c40686e1f0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:44.712959Z","signature_b64":"v1iuVHGHVByP5JjIQs8Rnb371xUrsG9U6q00E/C9zR4zm2hH30bvwVxKsab4JPlmSImaggX4+HuDgfBxUBKRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afcaf4c7dc84fe27871144e29cf485ae6b52e2f75ad230cdfe80784750582560","last_reissued_at":"2026-05-17T23:44:44.712450Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:44.712450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Based Pruning for Shift Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Carlos Lassance, Ghouthi Boukli Hacene (IMT Atlantique - ELEC), Matthieu Courbariaux, Vincent Gripon (IMT Atlantique - ELEC), Yoshua Bengio (DIRO)","submitted_at":"2019-05-29T09:59:23Z","abstract_excerpt":"In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in order to reach state-of-the-art accuracy, thus resulting in complex and demanding systems that are poorly fitted to resource-limited devices. Recently, methods have been proposed to replace the generic convolution operator by the combination of a shift operation and a simpler 1x1 convolution. The resulting block, called Shift Layer (SL), is an efficient alter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12300","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":""},"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":"1905.12300","created_at":"2026-05-17T23:44:44.712539+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12300v1","created_at":"2026-05-17T23:44:44.712539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12300","created_at":"2026-05-17T23:44:44.712539+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7FPJR64QT7C","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7FPJR64QT7CPBYR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7FPJR64","created_at":"2026-05-18T12:33:30.264802+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/V7FPJR64QT7CPBYRITRJZ5EFVZ","json":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ.json","graph_json":"https://pith.science/api/pith-number/V7FPJR64QT7CPBYRITRJZ5EFVZ/graph.json","events_json":"https://pith.science/api/pith-number/V7FPJR64QT7CPBYRITRJZ5EFVZ/events.json","paper":"https://pith.science/paper/V7FPJR64"},"agent_actions":{"view_html":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ","download_json":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ.json","view_paper":"https://pith.science/paper/V7FPJR64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12300&json=true","fetch_graph":"https://pith.science/api/pith-number/V7FPJR64QT7CPBYRITRJZ5EFVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V7FPJR64QT7CPBYRITRJZ5EFVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ/action/storage_attestation","attest_author":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ/action/author_attestation","sign_citation":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ/action/citation_signature","submit_replication":"https://pith.science/pith/V7FPJR64QT7CPBYRITRJZ5EFVZ/action/replication_record"}},"created_at":"2026-05-17T23:44:44.712539+00:00","updated_at":"2026-05-17T23:44:44.712539+00:00"}