{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EKTO7GMX27IMONQLJGCTYM2R3H","short_pith_number":"pith:EKTO7GMX","schema_version":"1.0","canonical_sha256":"22a6ef9997d7d0c7360b49853c3351d9c7b0fa546ab61458a6f8c24eebd66b54","source":{"kind":"arxiv","id":"2107.04191","version":2},"attestation_state":"computed","paper":{"title":"Structured Model Pruning of Convolutional Networks on Tensor Processing Units","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Ken Franko, Kongtao Chen, Ruoxin Sang","submitted_at":"2021-07-09T03:41:31Z","abstract_excerpt":"The deployment of convolutional neural networks is often hindered by high computational and storage requirements. Structured model pruning is a promising approach to alleviate these requirements. Using the VGG-16 model as an example, we measure the accuracy-efficiency trade-off for various structured model pruning methods and datasets (CIFAR-10 and ImageNet) on Tensor Processing Units (TPUs). To measure the actual performance of models, we develop a structured model pruning library for TensorFlow2 to modify models in place (instead of adding mask layers). We show that structured model pruning "},"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":"2107.04191","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T03:41:31Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"4ae5aa132f078099a67e6afe82b0b6499e36f5fd6be299988d88698c00a57b1e","abstract_canon_sha256":"d04e40464b0176055742a8b318a7ae51fbd90e222d3c6c4e31fa6561905b110a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:48.198848Z","signature_b64":"WtdNnILnfjwOT4HXGWS2vOknTfe6ZO1huok4qSAySPqjKd/wnV4BWAJzkXmY67hm4OUhyWa09JJnqP+tRvGlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a6ef9997d7d0c7360b49853c3351d9c7b0fa546ab61458a6f8c24eebd66b54","last_reissued_at":"2026-07-05T02:59:48.197952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:48.197952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Model Pruning of Convolutional Networks on Tensor Processing Units","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Ken Franko, Kongtao Chen, Ruoxin Sang","submitted_at":"2021-07-09T03:41:31Z","abstract_excerpt":"The deployment of convolutional neural networks is often hindered by high computational and storage requirements. Structured model pruning is a promising approach to alleviate these requirements. Using the VGG-16 model as an example, we measure the accuracy-efficiency trade-off for various structured model pruning methods and datasets (CIFAR-10 and ImageNet) on Tensor Processing Units (TPUs). To measure the actual performance of models, we develop a structured model pruning library for TensorFlow2 to modify models in place (instead of adding mask layers). We show that structured model pruning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04191","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/2107.04191/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":"2107.04191","created_at":"2026-07-05T02:59:48.198019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04191v2","created_at":"2026-07-05T02:59:48.198019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04191","created_at":"2026-07-05T02:59:48.198019+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKTO7GMX27IM","created_at":"2026-07-05T02:59:48.198019+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKTO7GMX27IMONQL","created_at":"2026-07-05T02:59:48.198019+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKTO7GMX","created_at":"2026-07-05T02:59:48.198019+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/EKTO7GMX27IMONQLJGCTYM2R3H","json":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H.json","graph_json":"https://pith.science/api/pith-number/EKTO7GMX27IMONQLJGCTYM2R3H/graph.json","events_json":"https://pith.science/api/pith-number/EKTO7GMX27IMONQLJGCTYM2R3H/events.json","paper":"https://pith.science/paper/EKTO7GMX"},"agent_actions":{"view_html":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H","download_json":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H.json","view_paper":"https://pith.science/paper/EKTO7GMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04191&json=true","fetch_graph":"https://pith.science/api/pith-number/EKTO7GMX27IMONQLJGCTYM2R3H/graph.json","fetch_events":"https://pith.science/api/pith-number/EKTO7GMX27IMONQLJGCTYM2R3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H/action/storage_attestation","attest_author":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H/action/author_attestation","sign_citation":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H/action/citation_signature","submit_replication":"https://pith.science/pith/EKTO7GMX27IMONQLJGCTYM2R3H/action/replication_record"}},"created_at":"2026-07-05T02:59:48.198019+00:00","updated_at":"2026-07-05T02:59:48.198019+00:00"}