{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3F76BY3YPDDNWTTMG46CSPSURP","short_pith_number":"pith:3F76BY3Y","schema_version":"1.0","canonical_sha256":"d97fe0e37878c6db4e6c373c293e548bcd4f009f452f8e88c1efcaf49d794354","source":{"kind":"arxiv","id":"2507.21573","version":1},"attestation_state":"computed","paper":{"title":"LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Deli\\`ege, Anthony Cioppa, Marc Van Droogenbroeck, Maxim Henry","submitted_at":"2025-07-29T08:17:10Z","abstract_excerpt":"Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on resource-constrained platforms. Hence, network pruning has emerged as an effective way of reducing the size and computational requirements of neural networks by removing redundant or unimportant parameters. However, a fundamental challenge with pruning consists in optimally removing redundancies without degrading performance. Most existing pruning techniques overlook structural dependencies across feature maps withi"},"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":"2507.21573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T08:17:10Z","cross_cats_sorted":[],"title_canon_sha256":"cdc9cb0f91792b450a393652cba20bd4cf87e5ce4f4a40340b8ff41bba73065b","abstract_canon_sha256":"6feefe9156ec82a54b236bfbc766f3b58bed41ece001773448f2d49c61918905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:02.442508Z","signature_b64":"17Ju8jkXDoy4b3c4Qg7O2d1AnlmFjm/hBV1MpmzJmC3Ozu4ECbMQKXu3E2oRchtVs/kcEGFkzsPYL0u6vTuaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d97fe0e37878c6db4e6c373c293e548bcd4f009f452f8e88c1efcaf49d794354","last_reissued_at":"2026-07-05T11:45:02.442032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:02.442032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Deli\\`ege, Anthony Cioppa, Marc Van Droogenbroeck, Maxim Henry","submitted_at":"2025-07-29T08:17:10Z","abstract_excerpt":"Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on resource-constrained platforms. Hence, network pruning has emerged as an effective way of reducing the size and computational requirements of neural networks by removing redundant or unimportant parameters. However, a fundamental challenge with pruning consists in optimally removing redundancies without degrading performance. Most existing pruning techniques overlook structural dependencies across feature maps withi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21573","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/2507.21573/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":"2507.21573","created_at":"2026-07-05T11:45:02.442090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21573v1","created_at":"2026-07-05T11:45:02.442090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21573","created_at":"2026-07-05T11:45:02.442090+00:00"},{"alias_kind":"pith_short_12","alias_value":"3F76BY3YPDDN","created_at":"2026-07-05T11:45:02.442090+00:00"},{"alias_kind":"pith_short_16","alias_value":"3F76BY3YPDDNWTTM","created_at":"2026-07-05T11:45:02.442090+00:00"},{"alias_kind":"pith_short_8","alias_value":"3F76BY3Y","created_at":"2026-07-05T11:45:02.442090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23656","citing_title":"Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP","json":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP.json","graph_json":"https://pith.science/api/pith-number/3F76BY3YPDDNWTTMG46CSPSURP/graph.json","events_json":"https://pith.science/api/pith-number/3F76BY3YPDDNWTTMG46CSPSURP/events.json","paper":"https://pith.science/paper/3F76BY3Y"},"agent_actions":{"view_html":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP","download_json":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP.json","view_paper":"https://pith.science/paper/3F76BY3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21573&json=true","fetch_graph":"https://pith.science/api/pith-number/3F76BY3YPDDNWTTMG46CSPSURP/graph.json","fetch_events":"https://pith.science/api/pith-number/3F76BY3YPDDNWTTMG46CSPSURP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP/action/storage_attestation","attest_author":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP/action/author_attestation","sign_citation":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP/action/citation_signature","submit_replication":"https://pith.science/pith/3F76BY3YPDDNWTTMG46CSPSURP/action/replication_record"}},"created_at":"2026-07-05T11:45:02.442090+00:00","updated_at":"2026-07-05T11:45:02.442090+00:00"}