{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EGPBOVMK7L6KTT2XZS3PDUBP4D","short_pith_number":"pith:EGPBOVMK","schema_version":"1.0","canonical_sha256":"219e17558afafca9cf57ccb6f1d02fe0c43e2b3dddf6f5d5db49df14e96133d8","source":{"kind":"arxiv","id":"2411.00969","version":1},"attestation_state":"computed","paper":{"title":"Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Faming Liang, Mingxuan Zhang, Yan Sun","submitted_at":"2024-11-01T18:39:38Z","abstract_excerpt":"Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world deployment. To address this, researchers often reduce model size by pruning parameters based on their magnitude or sensitivity. Previous research has demonstrated the limitations of magnitude pruning, especially in the context of transfer learning for modern NLP tasks. In this paper, we introduce a new magnitude-based pruning algorithm called mixture Gaussian prior "},"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":"2411.00969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-11-01T18:39:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"895d4c30f355a6d5d9f0b3549bc04c62a1747b0afa45dceba67b02bb7c3bbcaf","abstract_canon_sha256":"a994312fdb3ea740b30a64e02725dd2fbc6c0d1a417496e31bb65e7ebd262897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:53.151811Z","signature_b64":"2EMFe9hIyy6/OW2PahnnB4bh4JjfLCV0v9werm10a86UoR35id17+sJWhgGO/mGOCwEmxGomXximQf+Mq29uBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"219e17558afafca9cf57ccb6f1d02fe0c43e2b3dddf6f5d5db49df14e96133d8","last_reissued_at":"2026-07-05T09:29:53.151363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:53.151363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Faming Liang, Mingxuan Zhang, Yan Sun","submitted_at":"2024-11-01T18:39:38Z","abstract_excerpt":"Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world deployment. To address this, researchers often reduce model size by pruning parameters based on their magnitude or sensitivity. Previous research has demonstrated the limitations of magnitude pruning, especially in the context of transfer learning for modern NLP tasks. In this paper, we introduce a new magnitude-based pruning algorithm called mixture Gaussian prior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00969","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/2411.00969/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":"2411.00969","created_at":"2026-07-05T09:29:53.151421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00969v1","created_at":"2026-07-05T09:29:53.151421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00969","created_at":"2026-07-05T09:29:53.151421+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGPBOVMK7L6K","created_at":"2026-07-05T09:29:53.151421+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGPBOVMK7L6KTT2X","created_at":"2026-07-05T09:29:53.151421+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGPBOVMK","created_at":"2026-07-05T09:29:53.151421+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/EGPBOVMK7L6KTT2XZS3PDUBP4D","json":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D.json","graph_json":"https://pith.science/api/pith-number/EGPBOVMK7L6KTT2XZS3PDUBP4D/graph.json","events_json":"https://pith.science/api/pith-number/EGPBOVMK7L6KTT2XZS3PDUBP4D/events.json","paper":"https://pith.science/paper/EGPBOVMK"},"agent_actions":{"view_html":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D","download_json":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D.json","view_paper":"https://pith.science/paper/EGPBOVMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00969&json=true","fetch_graph":"https://pith.science/api/pith-number/EGPBOVMK7L6KTT2XZS3PDUBP4D/graph.json","fetch_events":"https://pith.science/api/pith-number/EGPBOVMK7L6KTT2XZS3PDUBP4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D/action/storage_attestation","attest_author":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D/action/author_attestation","sign_citation":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D/action/citation_signature","submit_replication":"https://pith.science/pith/EGPBOVMK7L6KTT2XZS3PDUBP4D/action/replication_record"}},"created_at":"2026-07-05T09:29:53.151421+00:00","updated_at":"2026-07-05T09:29:53.151421+00:00"}