{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AGT45RXUDWWYD5N4N6BRASXUUV","short_pith_number":"pith:AGT45RXU","schema_version":"1.0","canonical_sha256":"01a7cec6f41dad81f5bc6f83104af4a5448574c19259762f976383bf110b0866","source":{"kind":"arxiv","id":"2408.10473","version":1},"attestation_state":"computed","paper":{"title":"Enhancing One-shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashish Sirasao, Dong Li, Emad Barsoum, Guanchen Li, Jie He, Lian Liu, Lu Tian, Xiandong Zhao, Zeping Li","submitted_at":"2024-08-20T01:05:45Z","abstract_excerpt":"Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational and storage costs. Modern pruning strategies employ one-shot techniques to compress PLMs without the need for retraining on task-specific or otherwise general data; however, these approaches often lead to an indispensable reduction in performance. In this paper, we propose SDS, a Sparse-Dense-Sparse pruning framework to enhance the performance of the pruned P"},"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":"2408.10473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T01:05:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0cf1f1d6d7a78fbb38913e7682a57f7a5b61c0ccd52c97abc4ed05f0cdc214c6","abstract_canon_sha256":"818ffe2991c805ac9dace4fa6ea2fdcf3b03c20ec78c1139dda7dbb7dd9b2563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:12.510050Z","signature_b64":"NJOhM/RMzG37Ddx/AmZhTTVruMK1CrPBLUXWYGbkM/EM1RbE6R4piWq/Aq8EvYv/NXNOxgjXlZFTh21K3ZBJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01a7cec6f41dad81f5bc6f83104af4a5448574c19259762f976383bf110b0866","last_reissued_at":"2026-07-05T08:57:12.509662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:12.509662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing One-shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashish Sirasao, Dong Li, Emad Barsoum, Guanchen Li, Jie He, Lian Liu, Lu Tian, Xiandong Zhao, Zeping Li","submitted_at":"2024-08-20T01:05:45Z","abstract_excerpt":"Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational and storage costs. Modern pruning strategies employ one-shot techniques to compress PLMs without the need for retraining on task-specific or otherwise general data; however, these approaches often lead to an indispensable reduction in performance. In this paper, we propose SDS, a Sparse-Dense-Sparse pruning framework to enhance the performance of the pruned P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10473","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/2408.10473/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":"2408.10473","created_at":"2026-07-05T08:57:12.509714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10473v1","created_at":"2026-07-05T08:57:12.509714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10473","created_at":"2026-07-05T08:57:12.509714+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGT45RXUDWWY","created_at":"2026-07-05T08:57:12.509714+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGT45RXUDWWYD5N4","created_at":"2026-07-05T08:57:12.509714+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGT45RXU","created_at":"2026-07-05T08:57:12.509714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19090","citing_title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV","json":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV.json","graph_json":"https://pith.science/api/pith-number/AGT45RXUDWWYD5N4N6BRASXUUV/graph.json","events_json":"https://pith.science/api/pith-number/AGT45RXUDWWYD5N4N6BRASXUUV/events.json","paper":"https://pith.science/paper/AGT45RXU"},"agent_actions":{"view_html":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV","download_json":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV.json","view_paper":"https://pith.science/paper/AGT45RXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10473&json=true","fetch_graph":"https://pith.science/api/pith-number/AGT45RXUDWWYD5N4N6BRASXUUV/graph.json","fetch_events":"https://pith.science/api/pith-number/AGT45RXUDWWYD5N4N6BRASXUUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV/action/storage_attestation","attest_author":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV/action/author_attestation","sign_citation":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV/action/citation_signature","submit_replication":"https://pith.science/pith/AGT45RXUDWWYD5N4N6BRASXUUV/action/replication_record"}},"created_at":"2026-07-05T08:57:12.509714+00:00","updated_at":"2026-07-05T08:57:12.509714+00:00"}