{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q7LMMOYNOF463N5UIRLPVR5X3D","short_pith_number":"pith:Q7LMMOYN","schema_version":"1.0","canonical_sha256":"87d6c63b0d7179edb7b44456fac7b7d8d280b20900851847212e59f4ee7bd3be","source":{"kind":"arxiv","id":"2004.10694","version":1},"attestation_state":"computed","paper":{"title":"DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qiang Wang, Yikang Zhang, Zhao Zhong","submitted_at":"2020-04-22T16:58:05Z","abstract_excerpt":"Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although some efficient network structures have been proposed, such as MobileNet or ShuffleNet, we find that there still exists redundant information between convolution kernels. To address this issue, we propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. To demonstrate the effectiveness, we apply dynamic c"},"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":"2004.10694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-22T16:58:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6900b05ce4acc512f974e24bcc89780e93d3d03ca74240ff785f13834ef49291","abstract_canon_sha256":"44446205f88d5aabcbf548d79fd9f5d908c3ea43ab12695981a42ab2ea2e34b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:31.327252Z","signature_b64":"HyhPDqYBLdMkOxdznYcXNMgpGe7kvBl9nDzAb1pUayvgDgxD11nuw6qJetGv0WF2CWnyVkaoaNGMxKlHqORPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d6c63b0d7179edb7b44456fac7b7d8d280b20900851847212e59f4ee7bd3be","last_reissued_at":"2026-07-05T00:57:31.326910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:31.326910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qiang Wang, Yikang Zhang, Zhao Zhong","submitted_at":"2020-04-22T16:58:05Z","abstract_excerpt":"Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although some efficient network structures have been proposed, such as MobileNet or ShuffleNet, we find that there still exists redundant information between convolution kernels. To address this issue, we propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. To demonstrate the effectiveness, we apply dynamic c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10694","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/2004.10694/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":"2004.10694","created_at":"2026-07-05T00:57:31.326972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.10694v1","created_at":"2026-07-05T00:57:31.326972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10694","created_at":"2026-07-05T00:57:31.326972+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7LMMOYNOF46","created_at":"2026-07-05T00:57:31.326972+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7LMMOYNOF463N5U","created_at":"2026-07-05T00:57:31.326972+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7LMMOYN","created_at":"2026-07-05T00:57:31.326972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07705","citing_title":"Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D","json":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D.json","graph_json":"https://pith.science/api/pith-number/Q7LMMOYNOF463N5UIRLPVR5X3D/graph.json","events_json":"https://pith.science/api/pith-number/Q7LMMOYNOF463N5UIRLPVR5X3D/events.json","paper":"https://pith.science/paper/Q7LMMOYN"},"agent_actions":{"view_html":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D","download_json":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D.json","view_paper":"https://pith.science/paper/Q7LMMOYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.10694&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7LMMOYNOF463N5UIRLPVR5X3D/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7LMMOYNOF463N5UIRLPVR5X3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D/action/storage_attestation","attest_author":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D/action/author_attestation","sign_citation":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D/action/citation_signature","submit_replication":"https://pith.science/pith/Q7LMMOYNOF463N5UIRLPVR5X3D/action/replication_record"}},"created_at":"2026-07-05T00:57:31.326972+00:00","updated_at":"2026-07-05T00:57:31.326972+00:00"}