{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CSPINKIBGRD2FK2KGISNGSYEN7","short_pith_number":"pith:CSPINKIB","schema_version":"1.0","canonical_sha256":"149e86a9013447a2ab4a3224d34b046fef14458ecea9176587a1714e614f2761","source":{"kind":"arxiv","id":"2305.14403","version":1},"attestation_state":"computed","paper":{"title":"Layer-adaptive Structured Pruning Guided by Latency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Liang Hou, Linna Zhang, Siyuan Pan, Xiaobing Tu, Xiaoshuang Li","submitted_at":"2023-05-23T11:18:37Z","abstract_excerpt":"Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative loss function to guide network pruning together. Existing pruning methods that optimize latency have demonstrated leading performance, however, they often overlook the hardware features and connection in the network. To address this problem, we propose a global importance score SP-LAMP(Structured Pruning Layer-Adaptive Magnitude-based Pruning) by deriving a"},"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":"2305.14403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T11:18:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"637b30cadcb0e835a8c168d265a046269980c8c544ce5491c60ca8be618c0071","abstract_canon_sha256":"f702ed7bed76f205439112ed612b6cdab7a01623f346f85d628517f0f74f5a82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:23.010064Z","signature_b64":"gUI3n4saXAHVuGEJ6WSahhR2963eDRkaZAaE0bieWAyP3V4UtIN660pzx99GBiYj4jIM5t3wIOYIaMO34a8vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"149e86a9013447a2ab4a3224d34b046fef14458ecea9176587a1714e614f2761","last_reissued_at":"2026-07-05T06:13:23.009539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:23.009539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-adaptive Structured Pruning Guided by Latency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Liang Hou, Linna Zhang, Siyuan Pan, Xiaobing Tu, Xiaoshuang Li","submitted_at":"2023-05-23T11:18:37Z","abstract_excerpt":"Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative loss function to guide network pruning together. Existing pruning methods that optimize latency have demonstrated leading performance, however, they often overlook the hardware features and connection in the network. To address this problem, we propose a global importance score SP-LAMP(Structured Pruning Layer-Adaptive Magnitude-based Pruning) by deriving a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14403","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/2305.14403/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":"2305.14403","created_at":"2026-07-05T06:13:23.009596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14403v1","created_at":"2026-07-05T06:13:23.009596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14403","created_at":"2026-07-05T06:13:23.009596+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSPINKIBGRD2","created_at":"2026-07-05T06:13:23.009596+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSPINKIBGRD2FK2K","created_at":"2026-07-05T06:13:23.009596+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSPINKIB","created_at":"2026-07-05T06:13:23.009596+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/CSPINKIBGRD2FK2KGISNGSYEN7","json":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7.json","graph_json":"https://pith.science/api/pith-number/CSPINKIBGRD2FK2KGISNGSYEN7/graph.json","events_json":"https://pith.science/api/pith-number/CSPINKIBGRD2FK2KGISNGSYEN7/events.json","paper":"https://pith.science/paper/CSPINKIB"},"agent_actions":{"view_html":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7","download_json":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7.json","view_paper":"https://pith.science/paper/CSPINKIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14403&json=true","fetch_graph":"https://pith.science/api/pith-number/CSPINKIBGRD2FK2KGISNGSYEN7/graph.json","fetch_events":"https://pith.science/api/pith-number/CSPINKIBGRD2FK2KGISNGSYEN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7/action/storage_attestation","attest_author":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7/action/author_attestation","sign_citation":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7/action/citation_signature","submit_replication":"https://pith.science/pith/CSPINKIBGRD2FK2KGISNGSYEN7/action/replication_record"}},"created_at":"2026-07-05T06:13:23.009596+00:00","updated_at":"2026-07-05T06:13:23.009596+00:00"}