{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VQBKA7OFF7EW77OYE22OSDEERH","short_pith_number":"pith:VQBKA7OF","schema_version":"1.0","canonical_sha256":"ac02a07dc52fc96ffdd826b4e90c8489c1cd7b4b0b9f6b2e7f0703eac3d1cdd4","source":{"kind":"arxiv","id":"2112.10898","version":1},"attestation_state":"computed","paper":{"title":"Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fei Sun, Haoran Li, Junwen Luo, Minghai Qin, Tianyun Zhang, Xiaolong Ma, Yen-Kuang Chen, Yuan Xie, Zihao Zhao","submitted_at":"2021-12-20T22:55:45Z","abstract_excerpt":"Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model weights, has shown to be an effective method to provide good trade-offs between model accuracy and computation efficiency, and is a widely-used method to generate compressed models. However, the granularity of pruning makes important trade-offs. At the same sparsity level, a coarse-grained structured sparse pattern is more efficient on conventional hardware but "},"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":"2112.10898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T22:55:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b3ab0d402879e2b78b299323fb4239749c17656b8e5bc6e326f2ec96713b521","abstract_canon_sha256":"d16995a6e353fc3a68c0c0a58801aa9c1a10b4ffa6dc97a90f76e303b43507ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:27.439384Z","signature_b64":"g4lWu8Qxx03gX2rpOQjgN3TKr1z06DYdE4inFaXs1DMeJ69xroSwdF61OomtSc2t3A9MHKSreArfCFb8CbQ6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac02a07dc52fc96ffdd826b4e90c8489c1cd7b4b0b9f6b2e7f0703eac3d1cdd4","last_reissued_at":"2026-07-05T03:42:27.438927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:27.438927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fei Sun, Haoran Li, Junwen Luo, Minghai Qin, Tianyun Zhang, Xiaolong Ma, Yen-Kuang Chen, Yuan Xie, Zihao Zhao","submitted_at":"2021-12-20T22:55:45Z","abstract_excerpt":"Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model weights, has shown to be an effective method to provide good trade-offs between model accuracy and computation efficiency, and is a widely-used method to generate compressed models. However, the granularity of pruning makes important trade-offs. At the same sparsity level, a coarse-grained structured sparse pattern is more efficient on conventional hardware but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10898","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/2112.10898/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":"2112.10898","created_at":"2026-07-05T03:42:27.438986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10898v1","created_at":"2026-07-05T03:42:27.438986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10898","created_at":"2026-07-05T03:42:27.438986+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQBKA7OFF7EW","created_at":"2026-07-05T03:42:27.438986+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQBKA7OFF7EW77OY","created_at":"2026-07-05T03:42:27.438986+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQBKA7OF","created_at":"2026-07-05T03:42:27.438986+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/VQBKA7OFF7EW77OYE22OSDEERH","json":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH.json","graph_json":"https://pith.science/api/pith-number/VQBKA7OFF7EW77OYE22OSDEERH/graph.json","events_json":"https://pith.science/api/pith-number/VQBKA7OFF7EW77OYE22OSDEERH/events.json","paper":"https://pith.science/paper/VQBKA7OF"},"agent_actions":{"view_html":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH","download_json":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH.json","view_paper":"https://pith.science/paper/VQBKA7OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10898&json=true","fetch_graph":"https://pith.science/api/pith-number/VQBKA7OFF7EW77OYE22OSDEERH/graph.json","fetch_events":"https://pith.science/api/pith-number/VQBKA7OFF7EW77OYE22OSDEERH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH/action/storage_attestation","attest_author":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH/action/author_attestation","sign_citation":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH/action/citation_signature","submit_replication":"https://pith.science/pith/VQBKA7OFF7EW77OYE22OSDEERH/action/replication_record"}},"created_at":"2026-07-05T03:42:27.438986+00:00","updated_at":"2026-07-05T03:42:27.438986+00:00"}