{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QVSVYQWQJG755INCVZSEKBARID","short_pith_number":"pith:QVSVYQWQ","schema_version":"1.0","canonical_sha256":"85655c42d049bfdea1a2ae6445041140c5184ae1ba837051c359e3c9dea60ec6","source":{"kind":"arxiv","id":"2504.13296","version":2},"attestation_state":"computed","paper":{"title":"Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel G\\\"orges, Ganesh Sundaram, Jonas Ulmen","submitted_at":"2025-04-17T19:12:49Z","abstract_excerpt":"Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency analysis reduce model size with specific regard to computational performance. When applying them to Multi-Component Neural Architectures (MCNAs), they risk network integrity by removing large parameter groups. We introduce a component-aware pruning strategy, extending dependency graphs to isolate individual components and inter-component flows. This creates smaller, targeted pruni"},"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":"2504.13296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T19:12:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4b230483b0784fec0880737ac37e625524f0fc1d88d07b87f4f7fe8df7f0896","abstract_canon_sha256":"3416b80d65c9a4e55fe1d3108f52368b3335d5ed2c3c2f72340cedaaba9b47c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:53.052608Z","signature_b64":"QEfcx8O5ApvjtCG3cttI8ux6p0nzTbpNR6cnHGHp71FQSZIUr7GBJDMnAKm8BgZm899uLe8G2PDjdqsT0fFzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85655c42d049bfdea1a2ae6445041140c5184ae1ba837051c359e3c9dea60ec6","last_reissued_at":"2026-07-05T11:39:53.052034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:53.052034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel G\\\"orges, Ganesh Sundaram, Jonas Ulmen","submitted_at":"2025-04-17T19:12:49Z","abstract_excerpt":"Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency analysis reduce model size with specific regard to computational performance. When applying them to Multi-Component Neural Architectures (MCNAs), they risk network integrity by removing large parameter groups. We introduce a component-aware pruning strategy, extending dependency graphs to isolate individual components and inter-component flows. This creates smaller, targeted pruni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13296","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/2504.13296/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":"2504.13296","created_at":"2026-07-05T11:39:53.052103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13296v2","created_at":"2026-07-05T11:39:53.052103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13296","created_at":"2026-07-05T11:39:53.052103+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVSVYQWQJG75","created_at":"2026-07-05T11:39:53.052103+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVSVYQWQJG755INC","created_at":"2026-07-05T11:39:53.052103+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVSVYQWQ","created_at":"2026-07-05T11:39:53.052103+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/QVSVYQWQJG755INCVZSEKBARID","json":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID.json","graph_json":"https://pith.science/api/pith-number/QVSVYQWQJG755INCVZSEKBARID/graph.json","events_json":"https://pith.science/api/pith-number/QVSVYQWQJG755INCVZSEKBARID/events.json","paper":"https://pith.science/paper/QVSVYQWQ"},"agent_actions":{"view_html":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID","download_json":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID.json","view_paper":"https://pith.science/paper/QVSVYQWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13296&json=true","fetch_graph":"https://pith.science/api/pith-number/QVSVYQWQJG755INCVZSEKBARID/graph.json","fetch_events":"https://pith.science/api/pith-number/QVSVYQWQJG755INCVZSEKBARID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID/action/storage_attestation","attest_author":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID/action/author_attestation","sign_citation":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID/action/citation_signature","submit_replication":"https://pith.science/pith/QVSVYQWQJG755INCVZSEKBARID/action/replication_record"}},"created_at":"2026-07-05T11:39:53.052103+00:00","updated_at":"2026-07-05T11:39:53.052103+00:00"}