{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NTBCTF25BXDRXEOC7GQU7JHVOG","short_pith_number":"pith:NTBCTF25","schema_version":"1.0","canonical_sha256":"6cc229975d0dc71b91c2f9a14fa4f571be6a1ac7e471d5054215b3d2ab360602","source":{"kind":"arxiv","id":"2312.07061","version":2},"attestation_state":"computed","paper":{"title":"MaxQ: Multi-Axis Query for N:M Sparsity Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyang Xiang, Junhao Chen, Linpeng Peng, Siqi Li, Tianxin Huang, Yong Liu, Zhuangzhi Chen","submitted_at":"2023-12-12T08:28:29Z","abstract_excerpt":"N:M sparsity has received increasing attention due to its remarkable performance and latency trade-off compared with structured and unstructured sparsity. However, existing N:M sparsity methods do not differentiate the relative importance of weights among blocks and leave important weights underappreciated. Besides, they directly apply N:M sparsity to the whole network, which will cause severe information loss. Thus, they are still sub-optimal. In this paper, we propose an efficient and effective Multi-Axis Query methodology, dubbed as MaxQ, to rectify these problems. During the training, MaxQ"},"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":"2312.07061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T08:28:29Z","cross_cats_sorted":[],"title_canon_sha256":"df3202d4a2812e5ea6f92f6dd32e9dbce88c4a417ed9b1de2777ceb09cb84691","abstract_canon_sha256":"5e5b637f0ea89161e2d88de0eeda921646f9d88c6f5d757ce138ee3843f50071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:57.623487Z","signature_b64":"WDTsHKjlNCoNhMO0fCUkG39XKeVC7UcXGySRJqTx4f+skOq/utlyVBMFEkjG6o7lpXQWvHpAB9QIfCYgxFdbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc229975d0dc71b91c2f9a14fa4f571be6a1ac7e471d5054215b3d2ab360602","last_reissued_at":"2026-07-05T07:56:57.622913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:57.622913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaxQ: Multi-Axis Query for N:M Sparsity Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyang Xiang, Junhao Chen, Linpeng Peng, Siqi Li, Tianxin Huang, Yong Liu, Zhuangzhi Chen","submitted_at":"2023-12-12T08:28:29Z","abstract_excerpt":"N:M sparsity has received increasing attention due to its remarkable performance and latency trade-off compared with structured and unstructured sparsity. However, existing N:M sparsity methods do not differentiate the relative importance of weights among blocks and leave important weights underappreciated. Besides, they directly apply N:M sparsity to the whole network, which will cause severe information loss. Thus, they are still sub-optimal. In this paper, we propose an efficient and effective Multi-Axis Query methodology, dubbed as MaxQ, to rectify these problems. During the training, MaxQ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07061","kind":"arxiv","version":2},"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/2312.07061/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":"2312.07061","created_at":"2026-07-05T07:56:57.622972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07061v2","created_at":"2026-07-05T07:56:57.622972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07061","created_at":"2026-07-05T07:56:57.622972+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTBCTF25BXDR","created_at":"2026-07-05T07:56:57.622972+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTBCTF25BXDRXEOC","created_at":"2026-07-05T07:56:57.622972+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTBCTF25","created_at":"2026-07-05T07:56:57.622972+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/NTBCTF25BXDRXEOC7GQU7JHVOG","json":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG.json","graph_json":"https://pith.science/api/pith-number/NTBCTF25BXDRXEOC7GQU7JHVOG/graph.json","events_json":"https://pith.science/api/pith-number/NTBCTF25BXDRXEOC7GQU7JHVOG/events.json","paper":"https://pith.science/paper/NTBCTF25"},"agent_actions":{"view_html":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG","download_json":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG.json","view_paper":"https://pith.science/paper/NTBCTF25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07061&json=true","fetch_graph":"https://pith.science/api/pith-number/NTBCTF25BXDRXEOC7GQU7JHVOG/graph.json","fetch_events":"https://pith.science/api/pith-number/NTBCTF25BXDRXEOC7GQU7JHVOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG/action/storage_attestation","attest_author":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG/action/author_attestation","sign_citation":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG/action/citation_signature","submit_replication":"https://pith.science/pith/NTBCTF25BXDRXEOC7GQU7JHVOG/action/replication_record"}},"created_at":"2026-07-05T07:56:57.622972+00:00","updated_at":"2026-07-05T07:56:57.622972+00:00"}