{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ULJ6GFRHCDH375AS4RD2534NZA","short_pith_number":"pith:ULJ6GFRH","schema_version":"1.0","canonical_sha256":"a2d3e3162710cfbff412e447aeef8dc80824f2165424712a1b97e0d5d41b4d94","source":{"kind":"arxiv","id":"2409.03777","version":3},"attestation_state":"computed","paper":{"title":"A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anurag Reddy Parvathgari, Kiran Purohit, Sourangshu Bhattacharya","submitted_at":"2024-08-22T03:59:57Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes require heavy computational resources, making pruning redundant filters from existing pre-trained CNNs an essential task in developing efficient models for resource-constrained devices. Whole-network filter pruning algorithms prune varying fractions of filters from each layer, hence providing greater flexibility. Current whole-network pruning methods are either computationally expensive due to the need to calculate the loss for each pruned filter using "},"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":"2409.03777","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T03:59:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"296814c6fd5b1d46769e8a8b754167a800a3aa10c41872a8e7fff6ad4e3403c1","abstract_canon_sha256":"84984d912dc12cc2231dcaf1b6cfd5c30fe4677517cafdb1bb2017abe7c751fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:08.952005Z","signature_b64":"xcd371MAAL4+8yoCSdbgzBDeJ0iK/ASQ+YHWPOWFibp30MI0mr6xJt12WQ6lMIYcTc+ytoF4LJTO+ODYj7KCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d3e3162710cfbff412e447aeef8dc80824f2165424712a1b97e0d5d41b4d94","last_reissued_at":"2026-05-26T01:03:08.951035Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:08.951035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anurag Reddy Parvathgari, Kiran Purohit, Sourangshu Bhattacharya","submitted_at":"2024-08-22T03:59:57Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes require heavy computational resources, making pruning redundant filters from existing pre-trained CNNs an essential task in developing efficient models for resource-constrained devices. Whole-network filter pruning algorithms prune varying fractions of filters from each layer, hence providing greater flexibility. Current whole-network pruning methods are either computationally expensive due to the need to calculate the loss for each pruned filter using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03777","kind":"arxiv","version":3},"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/2409.03777/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":"2409.03777","created_at":"2026-05-26T01:03:08.951153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03777v3","created_at":"2026-05-26T01:03:08.951153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03777","created_at":"2026-05-26T01:03:08.951153+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULJ6GFRHCDH3","created_at":"2026-05-26T01:03:08.951153+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULJ6GFRHCDH375AS","created_at":"2026-05-26T01:03:08.951153+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULJ6GFRH","created_at":"2026-05-26T01:03:08.951153+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/ULJ6GFRHCDH375AS4RD2534NZA","json":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA.json","graph_json":"https://pith.science/api/pith-number/ULJ6GFRHCDH375AS4RD2534NZA/graph.json","events_json":"https://pith.science/api/pith-number/ULJ6GFRHCDH375AS4RD2534NZA/events.json","paper":"https://pith.science/paper/ULJ6GFRH"},"agent_actions":{"view_html":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA","download_json":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA.json","view_paper":"https://pith.science/paper/ULJ6GFRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03777&json=true","fetch_graph":"https://pith.science/api/pith-number/ULJ6GFRHCDH375AS4RD2534NZA/graph.json","fetch_events":"https://pith.science/api/pith-number/ULJ6GFRHCDH375AS4RD2534NZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA/action/storage_attestation","attest_author":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA/action/author_attestation","sign_citation":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA/action/citation_signature","submit_replication":"https://pith.science/pith/ULJ6GFRHCDH375AS4RD2534NZA/action/replication_record"}},"created_at":"2026-05-26T01:03:08.951153+00:00","updated_at":"2026-05-26T01:03:08.951153+00:00"}