{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6NXIDW4BEW2K6YQQXCJFSNKZ2H","short_pith_number":"pith:6NXIDW4B","schema_version":"1.0","canonical_sha256":"f36e81db8125b4af6210b892593559d1c5323fc87f6fbea6177e0cfb36845844","source":{"kind":"arxiv","id":"2112.07198","version":1},"attestation_state":"computed","paper":{"title":"From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Chengyu Wang, Fei Huang, Fuli Luo, Jun Huang, Runxin Xu, Songfang Huang","submitted_at":"2021-12-14T07:14:09Z","abstract_excerpt":"Pre-trained Language Models (PLMs) have achieved great success in various Natural Language Processing (NLP) tasks under the pre-training and fine-tuning paradigm. With large quantities of parameters, PLMs are computation-intensive and resource-hungry. Hence, model pruning has been introduced to compress large-scale PLMs. However, most prior approaches only consider task-specific knowledge towards downstream tasks, but ignore the essential task-agnostic knowledge during pruning, which may cause catastrophic forgetting problem and lead to poor generalization ability. To maintain both task-agnost"},"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":"2112.07198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T07:14:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"91c9237163c7a17a7aa01acba11327a57fa3898682df1eee1ade3e0e7911e2fd","abstract_canon_sha256":"88dde7cea443ab00e309dd4298a762e2d258940b8766daa2503cb24c019f3557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:55.715007Z","signature_b64":"vJfgUp+54A1+AOrNeSb67WbaOhNRozcUE2/EsAkH44EbsvhO3Y9UVodrLXSyZpvrAkDjlSjHNyKo097EkU1DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f36e81db8125b4af6210b892593559d1c5323fc87f6fbea6177e0cfb36845844","last_reissued_at":"2026-07-05T03:40:55.714609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:55.714609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Chengyu Wang, Fei Huang, Fuli Luo, Jun Huang, Runxin Xu, Songfang Huang","submitted_at":"2021-12-14T07:14:09Z","abstract_excerpt":"Pre-trained Language Models (PLMs) have achieved great success in various Natural Language Processing (NLP) tasks under the pre-training and fine-tuning paradigm. With large quantities of parameters, PLMs are computation-intensive and resource-hungry. Hence, model pruning has been introduced to compress large-scale PLMs. However, most prior approaches only consider task-specific knowledge towards downstream tasks, but ignore the essential task-agnostic knowledge during pruning, which may cause catastrophic forgetting problem and lead to poor generalization ability. To maintain both task-agnost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07198","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/2112.07198/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":"2112.07198","created_at":"2026-07-05T03:40:55.714666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07198v1","created_at":"2026-07-05T03:40:55.714666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07198","created_at":"2026-07-05T03:40:55.714666+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NXIDW4BEW2K","created_at":"2026-07-05T03:40:55.714666+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NXIDW4BEW2K6YQQ","created_at":"2026-07-05T03:40:55.714666+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NXIDW4B","created_at":"2026-07-05T03:40:55.714666+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/6NXIDW4BEW2K6YQQXCJFSNKZ2H","json":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H.json","graph_json":"https://pith.science/api/pith-number/6NXIDW4BEW2K6YQQXCJFSNKZ2H/graph.json","events_json":"https://pith.science/api/pith-number/6NXIDW4BEW2K6YQQXCJFSNKZ2H/events.json","paper":"https://pith.science/paper/6NXIDW4B"},"agent_actions":{"view_html":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H","download_json":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H.json","view_paper":"https://pith.science/paper/6NXIDW4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07198&json=true","fetch_graph":"https://pith.science/api/pith-number/6NXIDW4BEW2K6YQQXCJFSNKZ2H/graph.json","fetch_events":"https://pith.science/api/pith-number/6NXIDW4BEW2K6YQQXCJFSNKZ2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H/action/storage_attestation","attest_author":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H/action/author_attestation","sign_citation":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H/action/citation_signature","submit_replication":"https://pith.science/pith/6NXIDW4BEW2K6YQQXCJFSNKZ2H/action/replication_record"}},"created_at":"2026-07-05T03:40:55.714666+00:00","updated_at":"2026-07-05T03:40:55.714666+00:00"}