{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PJ5M5EKZ3R55B4DG4ABQJTPZT7","short_pith_number":"pith:PJ5M5EKZ","schema_version":"1.0","canonical_sha256":"7a7ace9159dc7bd0f066e00304cdf99fe0f2ee8ebecef6e5cdc6930ce944da1b","source":{"kind":"arxiv","id":"1806.09228","version":1},"attestation_state":"computed","paper":{"title":"Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Veeraraghavan, Junru Wu, Yingyan Lin, Yue Wang, Zhangyang Wang, Zhenyu Wu","submitted_at":"2018-06-24T22:49:24Z","abstract_excerpt":"The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e.g., GoogLeNet, ResNet and Wide ResNet). Further, the high energy consumption of convolutions limits its deployment on mobile devices. To this end, we proposed a simple yet effective scheme for compressing convolutions though applying k-means clustering on the weights, compression is achieved through weight-sharing, by only recording $K$ cluster centers and weight assignment indexes. We then intro"},"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":"1806.09228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-24T22:49:24Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"c769745f591df603ee926ecf07c018aab33c823b502e0fc83d638d4e33cd3142","abstract_canon_sha256":"aa167cda5b49772d304eabeed3d192ea3ed053d1ddc751fdea6c41440f0cf25b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:29.937373Z","signature_b64":"6/u4Ub4H70rIS9tX/Kov0iIgW6VX/O9UybEz25gYMwc2useRjYC1DgnQGfWuSlqT6uLSWdKbnixR6CytW2jhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7ace9159dc7bd0f066e00304cdf99fe0f2ee8ebecef6e5cdc6930ce944da1b","last_reissued_at":"2026-05-18T00:12:29.936878Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:29.936878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Veeraraghavan, Junru Wu, Yingyan Lin, Yue Wang, Zhangyang Wang, Zhenyu Wu","submitted_at":"2018-06-24T22:49:24Z","abstract_excerpt":"The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e.g., GoogLeNet, ResNet and Wide ResNet). Further, the high energy consumption of convolutions limits its deployment on mobile devices. To this end, we proposed a simple yet effective scheme for compressing convolutions though applying k-means clustering on the weights, compression is achieved through weight-sharing, by only recording $K$ cluster centers and weight assignment indexes. We then intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09228","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":""},"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":"1806.09228","created_at":"2026-05-18T00:12:29.936959+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09228v1","created_at":"2026-05-18T00:12:29.936959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09228","created_at":"2026-05-18T00:12:29.936959+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ5M5EKZ3R55","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ5M5EKZ3R55B4DG","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ5M5EKZ","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15551","citing_title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7","json":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7.json","graph_json":"https://pith.science/api/pith-number/PJ5M5EKZ3R55B4DG4ABQJTPZT7/graph.json","events_json":"https://pith.science/api/pith-number/PJ5M5EKZ3R55B4DG4ABQJTPZT7/events.json","paper":"https://pith.science/paper/PJ5M5EKZ"},"agent_actions":{"view_html":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7","download_json":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7.json","view_paper":"https://pith.science/paper/PJ5M5EKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09228&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ5M5EKZ3R55B4DG4ABQJTPZT7/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ5M5EKZ3R55B4DG4ABQJTPZT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7/action/storage_attestation","attest_author":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7/action/author_attestation","sign_citation":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7/action/citation_signature","submit_replication":"https://pith.science/pith/PJ5M5EKZ3R55B4DG4ABQJTPZT7/action/replication_record"}},"created_at":"2026-05-18T00:12:29.936959+00:00","updated_at":"2026-05-18T00:12:29.936959+00:00"}