{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4ITB4UJ525UJYLCRIZQQUOWWL4","short_pith_number":"pith:4ITB4UJ5","schema_version":"1.0","canonical_sha256":"e2261e513dd7689c2c5146610a3ad65f3f5cc85f74917e45c990786749c10144","source":{"kind":"arxiv","id":"2011.06923","version":3},"attestation_state":"computed","paper":{"title":"LEAN: graph-based pruning for convolutional neural networks by extracting longest chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Allard A. Hendriksen, Dani\\\"el M. Pelt, K. Joost Batenburg, Richard Schoonhoven","submitted_at":"2020-11-13T14:17:51Z","abstract_excerpt":"Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs). Common pruning methods determine which convolutional filters to remove by ranking the filters individually, i.e., without taking into account their interdependence. In this paper, we advocate the viewpoint that pruning should consider the interdependence between series of consecutive operators. We propose the LongEst-chAiN (LEAN) method that prunes CNNs by using graph-based algorithms to select relevant chains of convolutions. A CNN is interpreted as a graph, with"},"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":"2011.06923","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T14:17:51Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"6d233fb4fcd2ded1006e38fb36ad91b14fe71a34349174e0717d6f7134750252","abstract_canon_sha256":"3db4526edf2352eadba8e628f7940b2ded650f6630d91ec8c3fb7f96f3cd3eaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:11.868155Z","signature_b64":"2GwhzMEKg+EPQr0CQ8ldBxaErmPlFbhbaq1fqMKgXnaVSFJoA0EKpSBdtBkMi3v4DEs60xAqVPjTg8b6XXO0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2261e513dd7689c2c5146610a3ad65f3f5cc85f74917e45c990786749c10144","last_reissued_at":"2026-07-05T04:34:11.867749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:11.867749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAN: graph-based pruning for convolutional neural networks by extracting longest chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Allard A. Hendriksen, Dani\\\"el M. Pelt, K. Joost Batenburg, Richard Schoonhoven","submitted_at":"2020-11-13T14:17:51Z","abstract_excerpt":"Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs). Common pruning methods determine which convolutional filters to remove by ranking the filters individually, i.e., without taking into account their interdependence. In this paper, we advocate the viewpoint that pruning should consider the interdependence between series of consecutive operators. We propose the LongEst-chAiN (LEAN) method that prunes CNNs by using graph-based algorithms to select relevant chains of convolutions. A CNN is interpreted as a graph, with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06923","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/2011.06923/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":"2011.06923","created_at":"2026-07-05T04:34:11.867804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06923v3","created_at":"2026-07-05T04:34:11.867804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06923","created_at":"2026-07-05T04:34:11.867804+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ITB4UJ525UJ","created_at":"2026-07-05T04:34:11.867804+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ITB4UJ525UJYLCR","created_at":"2026-07-05T04:34:11.867804+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ITB4UJ5","created_at":"2026-07-05T04:34:11.867804+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/4ITB4UJ525UJYLCRIZQQUOWWL4","json":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4.json","graph_json":"https://pith.science/api/pith-number/4ITB4UJ525UJYLCRIZQQUOWWL4/graph.json","events_json":"https://pith.science/api/pith-number/4ITB4UJ525UJYLCRIZQQUOWWL4/events.json","paper":"https://pith.science/paper/4ITB4UJ5"},"agent_actions":{"view_html":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4","download_json":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4.json","view_paper":"https://pith.science/paper/4ITB4UJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06923&json=true","fetch_graph":"https://pith.science/api/pith-number/4ITB4UJ525UJYLCRIZQQUOWWL4/graph.json","fetch_events":"https://pith.science/api/pith-number/4ITB4UJ525UJYLCRIZQQUOWWL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4/action/storage_attestation","attest_author":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4/action/author_attestation","sign_citation":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4/action/citation_signature","submit_replication":"https://pith.science/pith/4ITB4UJ525UJYLCRIZQQUOWWL4/action/replication_record"}},"created_at":"2026-07-05T04:34:11.867804+00:00","updated_at":"2026-07-05T04:34:11.867804+00:00"}