{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XY5Z5H3QQWMV3FSLYEJAXCCHHD","short_pith_number":"pith:XY5Z5H3Q","schema_version":"1.0","canonical_sha256":"be3b9e9f7085995d964bc1120b884738c1b5ab4b10b96eaa774a58db9b30438e","source":{"kind":"arxiv","id":"2001.08839","version":1},"attestation_state":"computed","paper":{"title":"SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Geng Yuan, Mengshu Sun, Sijia Liu, Xiaolong Ma, Yanzhi Wang, Yifan Gong, Zhengang Li, Zhenglun Kong, Zheng Zhan","submitted_at":"2020-01-23T22:45:02Z","abstract_excerpt":"Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations. Previous works in this area leave great space for improvement since sparse structures with combinations of different structured pruning schemes are not exploited fully and efficiently. To mitigate the limitations, we propose SS-Auto, a single-shot, automatic structured pruning framework that can achieve row pruning and column pruning simultaneously. We adopt soft constraint-based formulation to alleviate the strong non-convexity of l0-norm constraints used in s"},"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":"2001.08839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T22:45:02Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"e63d28c63b7b6fb037d76acde4b1c881a4fe33c74c3445aeec809ab5210139b2","abstract_canon_sha256":"78d8e387629138ada8d991b772e2e771d4a6c76d4673e3436ce0a525ce874d7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:16.652324Z","signature_b64":"WGasmq+4IECeX0YVuAJwk1BoYRmI4xAzSASLkaQWY1pC31cr2lquBzREYfxZEP7/dt7qLqx/qkbMlYLuc7gmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be3b9e9f7085995d964bc1120b884738c1b5ab4b10b96eaa774a58db9b30438e","last_reissued_at":"2026-07-05T00:39:16.651894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:16.651894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Geng Yuan, Mengshu Sun, Sijia Liu, Xiaolong Ma, Yanzhi Wang, Yifan Gong, Zhengang Li, Zhenglun Kong, Zheng Zhan","submitted_at":"2020-01-23T22:45:02Z","abstract_excerpt":"Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations. Previous works in this area leave great space for improvement since sparse structures with combinations of different structured pruning schemes are not exploited fully and efficiently. To mitigate the limitations, we propose SS-Auto, a single-shot, automatic structured pruning framework that can achieve row pruning and column pruning simultaneously. We adopt soft constraint-based formulation to alleviate the strong non-convexity of l0-norm constraints used in s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08839","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/2001.08839/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":"2001.08839","created_at":"2026-07-05T00:39:16.651964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08839v1","created_at":"2026-07-05T00:39:16.651964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08839","created_at":"2026-07-05T00:39:16.651964+00:00"},{"alias_kind":"pith_short_12","alias_value":"XY5Z5H3QQWMV","created_at":"2026-07-05T00:39:16.651964+00:00"},{"alias_kind":"pith_short_16","alias_value":"XY5Z5H3QQWMV3FSL","created_at":"2026-07-05T00:39:16.651964+00:00"},{"alias_kind":"pith_short_8","alias_value":"XY5Z5H3Q","created_at":"2026-07-05T00:39:16.651964+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/XY5Z5H3QQWMV3FSLYEJAXCCHHD","json":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD.json","graph_json":"https://pith.science/api/pith-number/XY5Z5H3QQWMV3FSLYEJAXCCHHD/graph.json","events_json":"https://pith.science/api/pith-number/XY5Z5H3QQWMV3FSLYEJAXCCHHD/events.json","paper":"https://pith.science/paper/XY5Z5H3Q"},"agent_actions":{"view_html":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD","download_json":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD.json","view_paper":"https://pith.science/paper/XY5Z5H3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08839&json=true","fetch_graph":"https://pith.science/api/pith-number/XY5Z5H3QQWMV3FSLYEJAXCCHHD/graph.json","fetch_events":"https://pith.science/api/pith-number/XY5Z5H3QQWMV3FSLYEJAXCCHHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD/action/storage_attestation","attest_author":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD/action/author_attestation","sign_citation":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD/action/citation_signature","submit_replication":"https://pith.science/pith/XY5Z5H3QQWMV3FSLYEJAXCCHHD/action/replication_record"}},"created_at":"2026-07-05T00:39:16.651964+00:00","updated_at":"2026-07-05T00:39:16.651964+00:00"}