{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UKSKEV4IBQTSWNEAK57EPR626G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"62e96d8c85ce2a23e9b68bf61aded266bee0aae6b1b8384b065129fe9a52c861","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T18:12:30Z","title_canon_sha256":"f709f3f1f7045d3994dd2dd9d03e94f281fcb1b4ef3c091fa6caaa1a6d915c69"},"schema_version":"1.0","source":{"id":"1910.06360","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06360","created_at":"2026-07-05T02:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06360v3","created_at":"2026-07-05T02:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06360","created_at":"2026-07-05T02:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"UKSKEV4IBQTS","created_at":"2026-07-05T02:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"UKSKEV4IBQTSWNEA","created_at":"2026-07-05T02:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"UKSKEV4I","created_at":"2026-07-05T02:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:6d7babff94cf2686c6e216ea043f30a1f7ba88627dad49a1e83a0e4c8227bca6","target":"graph","created_at":"2026-07-05T02:30:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.06360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent trend in industry-setting Natural Language Processing (NLP) research has been to operate large %scale pretrained language models like BERT under strict computational limits. While most model compression work has focused on \"distilling\" a general-purpose language representation using expensive pretraining distillation, less attention has been paid to creating smaller task-specific language representations which, arguably, are more useful in an industry setting. In this paper, we investigate compressing BERT- and RoBERTa-based question answering systems by structured pruning of parame","authors_text":"Avirup Sil, J.S. McCarley, Rishav Chakravarti","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T18:12:30Z","title":"Structured Pruning of a BERT-based Question Answering Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06360","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:85eb40be5d90faaff5f7378c5761d1275bfb62afef5c1af93322e844a7eee78c","target":"record","created_at":"2026-07-05T02:30:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"62e96d8c85ce2a23e9b68bf61aded266bee0aae6b1b8384b065129fe9a52c861","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T18:12:30Z","title_canon_sha256":"f709f3f1f7045d3994dd2dd9d03e94f281fcb1b4ef3c091fa6caaa1a6d915c69"},"schema_version":"1.0","source":{"id":"1910.06360","kind":"arxiv","version":3}},"canonical_sha256":"a2a4a257880c272b3480577e47c7daf183900bd06d1d46a812ee2504e0e6be8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2a4a257880c272b3480577e47c7daf183900bd06d1d46a812ee2504e0e6be8f","first_computed_at":"2026-07-05T02:30:55.632015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:55.632015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4eLB9kgHLPnz+LEjNmv6d2bp2OAw6OEIU1i+VqprDduS+ONCeXpNtPTeJuimNhO3DktCNwpckPKSZqwnehWDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:55.632567Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.06360","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85eb40be5d90faaff5f7378c5761d1275bfb62afef5c1af93322e844a7eee78c","sha256:6d7babff94cf2686c6e216ea043f30a1f7ba88627dad49a1e83a0e4c8227bca6"],"state_sha256":"06e1356abd3aece6952e40c1ed46f46dafee1be2db25d0032eceac28a2fa1cdb"}