{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EMLUEY3DLZTZQHADRAVDBD2FQX","short_pith_number":"pith:EMLUEY3D","schema_version":"1.0","canonical_sha256":"23174263635e67981c03882a308f4585ffb36c2105cedf470010ee6995432ae9","source":{"kind":"arxiv","id":"2001.07710","version":3},"attestation_state":"computed","paper":{"title":"An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Hongjia Li, Jian Tang, Kaisheng Ma, Sheng Lin, Sijia Liu, Tianyun Zhang, Wei Niu, Xiang Chen, Xiaolong Ma, Yanzhi Wang","submitted_at":"2020-01-20T16:17:36Z","abstract_excerpt":"Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are essentially trade-offs between model accuracy and regularity which lead to impaired inference accuracy and limited on-device acceleration performance. To solve the problem, we introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. With carefull"},"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":"2001.07710","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-20T16:17:36Z","cross_cats_sorted":["cs.LG","cs.NE","eess.IV"],"title_canon_sha256":"4405e6e79288d091d5592c25e8a13a9db1c6a0cc7928eb36ce85ee60ffddd2c2","abstract_canon_sha256":"a9336bbdcd7802d9bcdecae9b890409be073e1ddf72cdd0ddc099e0596c80948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:12.279189Z","signature_b64":"10FROPVgp65OcCb+LsRKJm81Hl9BXm3mRvJivoivzgRSF393uUogY7YAQkpygGRNRdCv96sILOQIjB/wyhLyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23174263635e67981c03882a308f4585ffb36c2105cedf470010ee6995432ae9","last_reissued_at":"2026-07-05T01:16:12.278696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:12.278696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Hongjia Li, Jian Tang, Kaisheng Ma, Sheng Lin, Sijia Liu, Tianyun Zhang, Wei Niu, Xiang Chen, Xiaolong Ma, Yanzhi Wang","submitted_at":"2020-01-20T16:17:36Z","abstract_excerpt":"Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are essentially trade-offs between model accuracy and regularity which lead to impaired inference accuracy and limited on-device acceleration performance. To solve the problem, we introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. With carefull"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07710","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/2001.07710/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":"2001.07710","created_at":"2026-07-05T01:16:12.278752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07710v3","created_at":"2026-07-05T01:16:12.278752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07710","created_at":"2026-07-05T01:16:12.278752+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMLUEY3DLZTZ","created_at":"2026-07-05T01:16:12.278752+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMLUEY3DLZTZQHAD","created_at":"2026-07-05T01:16:12.278752+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMLUEY3D","created_at":"2026-07-05T01:16:12.278752+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/EMLUEY3DLZTZQHADRAVDBD2FQX","json":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX.json","graph_json":"https://pith.science/api/pith-number/EMLUEY3DLZTZQHADRAVDBD2FQX/graph.json","events_json":"https://pith.science/api/pith-number/EMLUEY3DLZTZQHADRAVDBD2FQX/events.json","paper":"https://pith.science/paper/EMLUEY3D"},"agent_actions":{"view_html":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX","download_json":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX.json","view_paper":"https://pith.science/paper/EMLUEY3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07710&json=true","fetch_graph":"https://pith.science/api/pith-number/EMLUEY3DLZTZQHADRAVDBD2FQX/graph.json","fetch_events":"https://pith.science/api/pith-number/EMLUEY3DLZTZQHADRAVDBD2FQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX/action/storage_attestation","attest_author":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX/action/author_attestation","sign_citation":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX/action/citation_signature","submit_replication":"https://pith.science/pith/EMLUEY3DLZTZQHADRAVDBD2FQX/action/replication_record"}},"created_at":"2026-07-05T01:16:12.278752+00:00","updated_at":"2026-07-05T01:16:12.278752+00:00"}