{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JBMCIOEFEVJZP72MHQEF2K2UNX","short_pith_number":"pith:JBMCIOEF","schema_version":"1.0","canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","source":{"kind":"arxiv","id":"2002.11985","version":2},"attestation_state":"computed","paper":{"title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Deming Chen, Hassan Sajjad, Marianne Winslett, Mohammad Ali Khan, Prakhar Ganesh, Preslav Nakov, Xin Lou, Yao Chen, Yin Yang","submitted_at":"2020-02-27T09:20:31Z","abstract_excerpt":"Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compressio"},"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":"2002.11985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T09:20:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"60c72e5ca38141302ac8571ff8d06860d9a91a978f6f2a17bdc345b08a1ff00b","abstract_canon_sha256":"3f8f91da4cc746c935db2b0891af9fb43720bc83be265ef4e420f05ec0904c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:44.378769Z","signature_b64":"pVXc83P2qI+dd2Lh6w8uTD4v1RtTa3GsBoaSIzFMZRNE5I/sQWlrsbkfMxEsuzXg5c+q1wmzp6xJ+YWREfWXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4858243885255397ff4c3c085d2b546dc252114a82eba0af072519a4cb08370b","last_reissued_at":"2026-07-05T03:17:44.378348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:44.378348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Deming Chen, Hassan Sajjad, Marianne Winslett, Mohammad Ali Khan, Prakhar Ganesh, Preslav Nakov, Xin Lou, Yao Chen, Yin Yang","submitted_at":"2020-02-27T09:20:31Z","abstract_excerpt":"Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compressio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11985","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/2002.11985/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":"2002.11985","created_at":"2026-07-05T03:17:44.378407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11985v2","created_at":"2026-07-05T03:17:44.378407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11985","created_at":"2026-07-05T03:17:44.378407+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBMCIOEFEVJZ","created_at":"2026-07-05T03:17:44.378407+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBMCIOEFEVJZP72M","created_at":"2026-07-05T03:17:44.378407+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBMCIOEF","created_at":"2026-07-05T03:17:44.378407+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/JBMCIOEFEVJZP72MHQEF2K2UNX","json":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX.json","graph_json":"https://pith.science/api/pith-number/JBMCIOEFEVJZP72MHQEF2K2UNX/graph.json","events_json":"https://pith.science/api/pith-number/JBMCIOEFEVJZP72MHQEF2K2UNX/events.json","paper":"https://pith.science/paper/JBMCIOEF"},"agent_actions":{"view_html":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX","download_json":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX.json","view_paper":"https://pith.science/paper/JBMCIOEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11985&json=true","fetch_graph":"https://pith.science/api/pith-number/JBMCIOEFEVJZP72MHQEF2K2UNX/graph.json","fetch_events":"https://pith.science/api/pith-number/JBMCIOEFEVJZP72MHQEF2K2UNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/action/storage_attestation","attest_author":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/action/author_attestation","sign_citation":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/action/citation_signature","submit_replication":"https://pith.science/pith/JBMCIOEFEVJZP72MHQEF2K2UNX/action/replication_record"}},"created_at":"2026-07-05T03:17:44.378407+00:00","updated_at":"2026-07-05T03:17:44.378407+00:00"}