{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BBXXMWQOM5BJRVRQXEXCPJGXF7","short_pith_number":"pith:BBXXMWQO","schema_version":"1.0","canonical_sha256":"086f765a0e674298d630b92e27a4d72fd23112585b193b87245ab1c60cd37d9c","source":{"kind":"arxiv","id":"2104.08682","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongkuan Xu, Ian E.H. Yen, Jinxi Zhao, Zhibin Xiao","submitted_at":"2021-04-18T02:20:37Z","abstract_excerpt":"Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large for resource-limited deployment scenarios. A thread of research has thus been working on applying network pruning techniques under the pretrain-then-finetune paradigm widely adopted in NLP. However, the existing pruning results on benchmark transformers, such as BERT, are not as remarkable as the pruning results in the literature of convolutional neural networ"},"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":"2104.08682","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T02:20:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f53b0ee731c3f9ec0c155fbba579ccb0d032d5d5109159478ad82d61d172d926","abstract_canon_sha256":"b47bf4c15a26795091477a0d335d0c20ca6580aff7bd927f1947362d272dd107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:40.792588Z","signature_b64":"yKrwTdRqXa9szTX3FGfiwzOPka+KZrCOJkK40LKtG2Y8dy3yxvU3H7k0Jiz+4bfP/brztiCc71Y4p5+BpYELCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"086f765a0e674298d630b92e27a4d72fd23112585b193b87245ab1c60cd37d9c","last_reissued_at":"2026-07-05T03:48:40.792136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:40.792136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongkuan Xu, Ian E.H. Yen, Jinxi Zhao, Zhibin Xiao","submitted_at":"2021-04-18T02:20:37Z","abstract_excerpt":"Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large for resource-limited deployment scenarios. A thread of research has thus been working on applying network pruning techniques under the pretrain-then-finetune paradigm widely adopted in NLP. However, the existing pruning results on benchmark transformers, such as BERT, are not as remarkable as the pruning results in the literature of convolutional neural networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08682","kind":"arxiv","version":2},"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/2104.08682/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":"2104.08682","created_at":"2026-07-05T03:48:40.792194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08682v2","created_at":"2026-07-05T03:48:40.792194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08682","created_at":"2026-07-05T03:48:40.792194+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBXXMWQOM5BJ","created_at":"2026-07-05T03:48:40.792194+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBXXMWQOM5BJRVRQ","created_at":"2026-07-05T03:48:40.792194+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBXXMWQO","created_at":"2026-07-05T03:48:40.792194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7","json":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7.json","graph_json":"https://pith.science/api/pith-number/BBXXMWQOM5BJRVRQXEXCPJGXF7/graph.json","events_json":"https://pith.science/api/pith-number/BBXXMWQOM5BJRVRQXEXCPJGXF7/events.json","paper":"https://pith.science/paper/BBXXMWQO"},"agent_actions":{"view_html":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7","download_json":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7.json","view_paper":"https://pith.science/paper/BBXXMWQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08682&json=true","fetch_graph":"https://pith.science/api/pith-number/BBXXMWQOM5BJRVRQXEXCPJGXF7/graph.json","fetch_events":"https://pith.science/api/pith-number/BBXXMWQOM5BJRVRQXEXCPJGXF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7/action/storage_attestation","attest_author":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7/action/author_attestation","sign_citation":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7/action/citation_signature","submit_replication":"https://pith.science/pith/BBXXMWQOM5BJRVRQXEXCPJGXF7/action/replication_record"}},"created_at":"2026-07-05T03:48:40.792194+00:00","updated_at":"2026-07-05T03:48:40.792194+00:00"}