{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QBKK4ERH24YBDKBJ4KVDOT5ZDK","short_pith_number":"pith:QBKK4ERH","schema_version":"1.0","canonical_sha256":"8054ae1227d73011a829e2aa374fb91ab4785354242057600904d87a51d25aae","source":{"kind":"arxiv","id":"1710.09282","version":9},"attestation_state":"computed","paper":{"title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Duo Wang, Pan Zhou, Tao Zhang, Yu Cheng","submitted_at":"2017-10-23T20:16:55Z","abstract_excerpt":"Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past five years, tremendous progress has been made in this area. In this paper, we review the recent techniques for compactin"},"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":"1710.09282","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-23T20:16:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9ad591c50a28ef2823fc06026583dbd352e1b86eee40159378fc3b63f14502d3","abstract_canon_sha256":"9cfbf8de2039596cd083bbc4226523094c6fd6b4caa410cf28e021d285928029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:10.156448Z","signature_b64":"66N8PFm8HfyGeaPleCwvW17EdHSM6wZW2HKo9oOLBGkOrPU72IGWR5i/gMBJD1K3VbqSXsd6LBEiNwpBbJpkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8054ae1227d73011a829e2aa374fb91ab4785354242057600904d87a51d25aae","last_reissued_at":"2026-07-05T01:10:10.155853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:10.155853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Duo Wang, Pan Zhou, Tao Zhang, Yu Cheng","submitted_at":"2017-10-23T20:16:55Z","abstract_excerpt":"Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past five years, tremendous progress has been made in this area. In this paper, we review the recent techniques for compactin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09282","kind":"arxiv","version":9},"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/1710.09282/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":"1710.09282","created_at":"2026-07-05T01:10:10.155922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.09282v9","created_at":"2026-07-05T01:10:10.155922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09282","created_at":"2026-07-05T01:10:10.155922+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBKK4ERH24YB","created_at":"2026-07-05T01:10:10.155922+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBKK4ERH24YBDKBJ","created_at":"2026-07-05T01:10:10.155922+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBKK4ERH","created_at":"2026-07-05T01:10:10.155922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09357","citing_title":"Rethinking Depth: A study of the Recursive-Transformer for Speech Recognition","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01412","citing_title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02345","citing_title":"Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2508.17431","citing_title":"FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16423","citing_title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2312.05821","citing_title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2508.17431","citing_title":"FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2309.10668","citing_title":"Language Modeling Is Compression","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26587","citing_title":"Sparse-on-Dense: Area and Energy-Efficient Computing of Sparse Neural Networks on Dense Matrix Multiplication Accelerators","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK","json":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK.json","graph_json":"https://pith.science/api/pith-number/QBKK4ERH24YBDKBJ4KVDOT5ZDK/graph.json","events_json":"https://pith.science/api/pith-number/QBKK4ERH24YBDKBJ4KVDOT5ZDK/events.json","paper":"https://pith.science/paper/QBKK4ERH"},"agent_actions":{"view_html":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK","download_json":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK.json","view_paper":"https://pith.science/paper/QBKK4ERH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.09282&json=true","fetch_graph":"https://pith.science/api/pith-number/QBKK4ERH24YBDKBJ4KVDOT5ZDK/graph.json","fetch_events":"https://pith.science/api/pith-number/QBKK4ERH24YBDKBJ4KVDOT5ZDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK/action/storage_attestation","attest_author":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK/action/author_attestation","sign_citation":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK/action/citation_signature","submit_replication":"https://pith.science/pith/QBKK4ERH24YBDKBJ4KVDOT5ZDK/action/replication_record"}},"created_at":"2026-07-05T01:10:10.155922+00:00","updated_at":"2026-07-05T01:10:10.155922+00:00"}