{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WK2QW4CKUDUQNH756ARQVQ5MSF","short_pith_number":"pith:WK2QW4CK","schema_version":"1.0","canonical_sha256":"b2b50b704aa0e9069ffdf0230ac3ac91577e4be9515e65af67ddde5b8f3df061","source":{"kind":"arxiv","id":"2108.11033","version":1},"attestation_state":"computed","paper":{"title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Ren, Gang Zhou, Peiyan Dong, Wei Niu, Xiaolong Ma, Xuehai Qian, Xue Lin, Yanzhi Wang, Zhengang Li","submitted_at":"2021-08-25T03:50:46Z","abstract_excerpt":"It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as ``resource-constrained'' when executing large-scale DNNs. It necessitates the sparse model inference via weight pruning, i.e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy. This paper designs a novel mobile inference acceleration framework GRIM that is General to both convolutional n"},"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":"2108.11033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-25T03:50:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56cc7f06e2b40a77e312d6bc0a65ee39ca7c0ed6058e5fc282bfb9b01138bdfa","abstract_canon_sha256":"0c2b85f82ae81318b2a8a3f91989ac082a8f460f7e9940d58210bd870e360408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:48.603643Z","signature_b64":"OhqeekTVl/+eo1hyF3KxnwISzmFsGvVXahssbfFt//Lr27kdjKZC7+1Xm8r5nvfqca4skgHxKpAvE9I/W3HfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b50b704aa0e9069ffdf0230ac3ac91577e4be9515e65af67ddde5b8f3df061","last_reissued_at":"2026-07-05T03:08:48.603266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:48.603266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Ren, Gang Zhou, Peiyan Dong, Wei Niu, Xiaolong Ma, Xuehai Qian, Xue Lin, Yanzhi Wang, Zhengang Li","submitted_at":"2021-08-25T03:50:46Z","abstract_excerpt":"It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as ``resource-constrained'' when executing large-scale DNNs. It necessitates the sparse model inference via weight pruning, i.e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy. This paper designs a novel mobile inference acceleration framework GRIM that is General to both convolutional n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11033","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.11033/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":"2108.11033","created_at":"2026-07-05T03:08:48.603322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11033v1","created_at":"2026-07-05T03:08:48.603322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11033","created_at":"2026-07-05T03:08:48.603322+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK2QW4CKUDUQ","created_at":"2026-07-05T03:08:48.603322+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK2QW4CKUDUQNH75","created_at":"2026-07-05T03:08:48.603322+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK2QW4CK","created_at":"2026-07-05T03:08:48.603322+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/WK2QW4CKUDUQNH756ARQVQ5MSF","json":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF.json","graph_json":"https://pith.science/api/pith-number/WK2QW4CKUDUQNH756ARQVQ5MSF/graph.json","events_json":"https://pith.science/api/pith-number/WK2QW4CKUDUQNH756ARQVQ5MSF/events.json","paper":"https://pith.science/paper/WK2QW4CK"},"agent_actions":{"view_html":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF","download_json":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF.json","view_paper":"https://pith.science/paper/WK2QW4CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11033&json=true","fetch_graph":"https://pith.science/api/pith-number/WK2QW4CKUDUQNH756ARQVQ5MSF/graph.json","fetch_events":"https://pith.science/api/pith-number/WK2QW4CKUDUQNH756ARQVQ5MSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF/action/storage_attestation","attest_author":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF/action/author_attestation","sign_citation":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF/action/citation_signature","submit_replication":"https://pith.science/pith/WK2QW4CKUDUQNH756ARQVQ5MSF/action/replication_record"}},"created_at":"2026-07-05T03:08:48.603322+00:00","updated_at":"2026-07-05T03:08:48.603322+00:00"}