{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHFGNIP2M7BYRZK6WRIX2WNIKK","short_pith_number":"pith:UHFGNIP2","schema_version":"1.0","canonical_sha256":"a1ca66a1fa67c388e55eb4517d59a8528181bfc0e6a8258e0c2a7f9547b72a05","source":{"kind":"arxiv","id":"2403.07094","version":1},"attestation_state":"computed","paper":{"title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rahul Mazumder, Riade Benbaki, Wenyu Chen, Xiang Meng","submitted_at":"2024-03-11T18:40:47Z","abstract_excerpt":"The increasing computational demands of modern neural networks present deployment challenges on resource-constrained devices. Network pruning offers a solution to reduce model size and computational cost while maintaining performance. However, most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters, often neglecting other deployment costs such as inference time, which are closely related to the number of floating-point operations (FLOPs). In this paper, we propose FALCON, a novel combinatorial-optimization-based framework for network prun"},"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":"2403.07094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T18:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"884e9c8613efc8206d0322bdea26aa6a4d64a22cbab02dca14bcd659d7837ac5","abstract_canon_sha256":"0b719d70e65fb138dc2497931268141c4dc7f3efc5b4c9f6496644520926d45b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:59.007410Z","signature_b64":"tfsn5gjhwTi9zAeibpjBG9I9WzJskxAw6WC78EFG6ROzI68sxbJLWSIMgEtcUWPDhrage77K0IzXEysVEV4nBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1ca66a1fa67c388e55eb4517d59a8528181bfc0e6a8258e0c2a7f9547b72a05","last_reissued_at":"2026-07-05T07:54:59.006872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:59.006872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rahul Mazumder, Riade Benbaki, Wenyu Chen, Xiang Meng","submitted_at":"2024-03-11T18:40:47Z","abstract_excerpt":"The increasing computational demands of modern neural networks present deployment challenges on resource-constrained devices. Network pruning offers a solution to reduce model size and computational cost while maintaining performance. However, most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters, often neglecting other deployment costs such as inference time, which are closely related to the number of floating-point operations (FLOPs). In this paper, we propose FALCON, a novel combinatorial-optimization-based framework for network prun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07094","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/2403.07094/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":"2403.07094","created_at":"2026-07-05T07:54:59.006943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07094v1","created_at":"2026-07-05T07:54:59.006943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07094","created_at":"2026-07-05T07:54:59.006943+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHFGNIP2M7BY","created_at":"2026-07-05T07:54:59.006943+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHFGNIP2M7BYRZK6","created_at":"2026-07-05T07:54:59.006943+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHFGNIP2","created_at":"2026-07-05T07:54:59.006943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18376","citing_title":"Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK","json":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK.json","graph_json":"https://pith.science/api/pith-number/UHFGNIP2M7BYRZK6WRIX2WNIKK/graph.json","events_json":"https://pith.science/api/pith-number/UHFGNIP2M7BYRZK6WRIX2WNIKK/events.json","paper":"https://pith.science/paper/UHFGNIP2"},"agent_actions":{"view_html":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK","download_json":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK.json","view_paper":"https://pith.science/paper/UHFGNIP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07094&json=true","fetch_graph":"https://pith.science/api/pith-number/UHFGNIP2M7BYRZK6WRIX2WNIKK/graph.json","fetch_events":"https://pith.science/api/pith-number/UHFGNIP2M7BYRZK6WRIX2WNIKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK/action/storage_attestation","attest_author":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK/action/author_attestation","sign_citation":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK/action/citation_signature","submit_replication":"https://pith.science/pith/UHFGNIP2M7BYRZK6WRIX2WNIKK/action/replication_record"}},"created_at":"2026-07-05T07:54:59.006943+00:00","updated_at":"2026-07-05T07:54:59.006943+00:00"}