{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VBK5UU2RX4S5LYUGSTASEG53RN","short_pith_number":"pith:VBK5UU2R","schema_version":"1.0","canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","source":{"kind":"arxiv","id":"2111.05754","version":1},"attestation_state":"computed","paper":{"title":"Prune Once for All: Sparse Pre-Trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ariel Larey, Guy Boudoukh, Haihao Shen, Moshe Wasserblat, Ofir Zafrir","submitted_at":"2021-11-10T15:52:40Z","abstract_excerpt":"Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase the implementation efficiency of large Transformer-based models on target hardware. In this work we present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity "},"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":"2111.05754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-10T15:52:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d9353a08822984bf3a2aba9ea5885b8934e43810b8bf51544b00c619f6d2070b","abstract_canon_sha256":"4c4d419cc668f0752a0271152397979149a9f7a052645ae0473d7bb6b2a93341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:47.781433Z","signature_b64":"v44Oiu3PPqrAQLE8AtAsunTBV+0TJyzVwSgGay+KeC7eXgJyQVlww7eoYC8WU9jjCETl5njU7/FbZS6gFdn4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855da5351bf25d5e28694c1221bbb8b5cff99a96724390b258df6eddebfba6b","last_reissued_at":"2026-07-05T03:30:47.780902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:47.780902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prune Once for All: Sparse Pre-Trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ariel Larey, Guy Boudoukh, Haihao Shen, Moshe Wasserblat, Ofir Zafrir","submitted_at":"2021-11-10T15:52:40Z","abstract_excerpt":"Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase the implementation efficiency of large Transformer-based models on target hardware. In this work we present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05754","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/2111.05754/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":"2111.05754","created_at":"2026-07-05T03:30:47.780984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05754v1","created_at":"2026-07-05T03:30:47.780984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05754","created_at":"2026-07-05T03:30:47.780984+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBK5UU2RX4S5","created_at":"2026-07-05T03:30:47.780984+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBK5UU2RX4S5LYUG","created_at":"2026-07-05T03:30:47.780984+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBK5UU2R","created_at":"2026-07-05T03:30:47.780984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02277","citing_title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12744","citing_title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12744","citing_title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN","json":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN.json","graph_json":"https://pith.science/api/pith-number/VBK5UU2RX4S5LYUGSTASEG53RN/graph.json","events_json":"https://pith.science/api/pith-number/VBK5UU2RX4S5LYUGSTASEG53RN/events.json","paper":"https://pith.science/paper/VBK5UU2R"},"agent_actions":{"view_html":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN","download_json":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN.json","view_paper":"https://pith.science/paper/VBK5UU2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05754&json=true","fetch_graph":"https://pith.science/api/pith-number/VBK5UU2RX4S5LYUGSTASEG53RN/graph.json","fetch_events":"https://pith.science/api/pith-number/VBK5UU2RX4S5LYUGSTASEG53RN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/action/storage_attestation","attest_author":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/action/author_attestation","sign_citation":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/action/citation_signature","submit_replication":"https://pith.science/pith/VBK5UU2RX4S5LYUGSTASEG53RN/action/replication_record"}},"created_at":"2026-07-05T03:30:47.780984+00:00","updated_at":"2026-07-05T03:30:47.780984+00:00"}