{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ICT2GFE7N457MCG4AOGVPSC4KT","short_pith_number":"pith:ICT2GFE7","schema_version":"1.0","canonical_sha256":"40a7a3149f6f3bf608dc038d57c85c54ffcb2f609928ee2681a8a7188b5b3f6c","source":{"kind":"arxiv","id":"2303.16212","version":2},"attestation_state":"computed","paper":{"title":"A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Licheng Jiao, Ronghua Shang, Songhua Xu, Songling Zhu, Weitong Zhang, Yinan Wu","submitted_at":"2023-03-28T12:05:15Z","abstract_excerpt":"Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly,"},"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":"2303.16212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T12:05:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ccc09eb46758d5a2f8d54a63cd659a6da5f06ac8ff43f5b289d16aae166af18","abstract_canon_sha256":"8137b87de6bee8b0be414b119b02f868e039a73190f9b273b378c0a2e46360a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:57.059457Z","signature_b64":"9wbO+Boi6SCI2zWCkaNY3EN11aUJHJV28gHDwEDO8xZvaBb6W/xtUiFFbUCzEesPuFHHmv5mJKLb9InV7UvFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a7a3149f6f3bf608dc038d57c85c54ffcb2f609928ee2681a8a7188b5b3f6c","last_reissued_at":"2026-07-05T07:28:57.058970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:57.058970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Licheng Jiao, Ronghua Shang, Songhua Xu, Songling Zhu, Weitong Zhang, Yinan Wu","submitted_at":"2023-03-28T12:05:15Z","abstract_excerpt":"Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16212","kind":"arxiv","version":2},"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/2303.16212/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":"2303.16212","created_at":"2026-07-05T07:28:57.059029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16212v2","created_at":"2026-07-05T07:28:57.059029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16212","created_at":"2026-07-05T07:28:57.059029+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICT2GFE7N457","created_at":"2026-07-05T07:28:57.059029+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICT2GFE7N457MCG4","created_at":"2026-07-05T07:28:57.059029+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICT2GFE7","created_at":"2026-07-05T07:28:57.059029+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/ICT2GFE7N457MCG4AOGVPSC4KT","json":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT.json","graph_json":"https://pith.science/api/pith-number/ICT2GFE7N457MCG4AOGVPSC4KT/graph.json","events_json":"https://pith.science/api/pith-number/ICT2GFE7N457MCG4AOGVPSC4KT/events.json","paper":"https://pith.science/paper/ICT2GFE7"},"agent_actions":{"view_html":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT","download_json":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT.json","view_paper":"https://pith.science/paper/ICT2GFE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16212&json=true","fetch_graph":"https://pith.science/api/pith-number/ICT2GFE7N457MCG4AOGVPSC4KT/graph.json","fetch_events":"https://pith.science/api/pith-number/ICT2GFE7N457MCG4AOGVPSC4KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT/action/storage_attestation","attest_author":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT/action/author_attestation","sign_citation":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT/action/citation_signature","submit_replication":"https://pith.science/pith/ICT2GFE7N457MCG4AOGVPSC4KT/action/replication_record"}},"created_at":"2026-07-05T07:28:57.059029+00:00","updated_at":"2026-07-05T07:28:57.059029+00:00"}