{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A3TAKRQU7QBOVPSFFVI75JQVBN","short_pith_number":"pith:A3TAKRQU","schema_version":"1.0","canonical_sha256":"06e6054614fc02eabe452d51fea6150b7d1f05abda99b5c29fb18544877f5241","source":{"kind":"arxiv","id":"1912.13200","version":6},"attestation_state":"computed","paper":{"title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Chang Xu, Chao Xu, Chunjing Xu, Hanting Chen, Qi Tian, Yunhe Wang","submitted_at":"2019-12-31T06:56:47Z","abstract_excerpt":"Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\\ell_1$-norm distance betwe"},"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":"1912.13200","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-31T06:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"504838f32423ff30e1e0479cfd9e0527b94093626e427c1166ed16d1ed33c3c0","abstract_canon_sha256":"04fa70fb80ee6880f4cd7cad4bff1e19229ebe523febe7bbbe3e8455849ff1b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:52.706407Z","signature_b64":"w1/8Jy/JFuLgtNvpIGqhTMNjOPPRsmMnIDCJq0+LjJofoPbBo4GmBRs0vPVXfnw5cTNqZGY3+jxqJW1XoYc7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e6054614fc02eabe452d51fea6150b7d1f05abda99b5c29fb18544877f5241","last_reissued_at":"2026-07-05T02:56:52.705837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:52.705837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Chang Xu, Chao Xu, Chunjing Xu, Hanting Chen, Qi Tian, Yunhe Wang","submitted_at":"2019-12-31T06:56:47Z","abstract_excerpt":"Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\\ell_1$-norm distance betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13200","kind":"arxiv","version":6},"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/1912.13200/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":"1912.13200","created_at":"2026-07-05T02:56:52.705899+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.13200v6","created_at":"2026-07-05T02:56:52.705899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13200","created_at":"2026-07-05T02:56:52.705899+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3TAKRQU7QBO","created_at":"2026-07-05T02:56:52.705899+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3TAKRQU7QBOVPSF","created_at":"2026-07-05T02:56:52.705899+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3TAKRQU","created_at":"2026-07-05T02:56:52.705899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13902","citing_title":"Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN","json":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN.json","graph_json":"https://pith.science/api/pith-number/A3TAKRQU7QBOVPSFFVI75JQVBN/graph.json","events_json":"https://pith.science/api/pith-number/A3TAKRQU7QBOVPSFFVI75JQVBN/events.json","paper":"https://pith.science/paper/A3TAKRQU"},"agent_actions":{"view_html":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN","download_json":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN.json","view_paper":"https://pith.science/paper/A3TAKRQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.13200&json=true","fetch_graph":"https://pith.science/api/pith-number/A3TAKRQU7QBOVPSFFVI75JQVBN/graph.json","fetch_events":"https://pith.science/api/pith-number/A3TAKRQU7QBOVPSFFVI75JQVBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN/action/storage_attestation","attest_author":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN/action/author_attestation","sign_citation":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN/action/citation_signature","submit_replication":"https://pith.science/pith/A3TAKRQU7QBOVPSFFVI75JQVBN/action/replication_record"}},"created_at":"2026-07-05T02:56:52.705899+00:00","updated_at":"2026-07-05T02:56:52.705899+00:00"}