{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QDQUDJ7JHBVY2SKSAWDJJHV7AI","short_pith_number":"pith:QDQUDJ7J","canonical_record":{"source":{"id":"2211.08842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T11:43:09Z","cross_cats_sorted":[],"title_canon_sha256":"d12cd2ce64d76f9e95fd63a8c95c710104c48cf93a28da2af371ad0109d0143c","abstract_canon_sha256":"45011d062a84ca70afff41e964b2ba9971ba195cd6ce02fd6a741aaeb0410a04"},"schema_version":"1.0"},"canonical_sha256":"80e141a7e9386b8d49520586949ebf020b18521f0b890ca795c8fc0a23540506","source":{"kind":"arxiv","id":"2211.08842","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08842","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08842v2","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08842","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"QDQUDJ7JHBVY","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"QDQUDJ7JHBVY2SKS","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"QDQUDJ7J","created_at":"2026-07-05T05:22:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QDQUDJ7JHBVY2SKSAWDJJHV7AI","target":"record","payload":{"canonical_record":{"source":{"id":"2211.08842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T11:43:09Z","cross_cats_sorted":[],"title_canon_sha256":"d12cd2ce64d76f9e95fd63a8c95c710104c48cf93a28da2af371ad0109d0143c","abstract_canon_sha256":"45011d062a84ca70afff41e964b2ba9971ba195cd6ce02fd6a741aaeb0410a04"},"schema_version":"1.0"},"canonical_sha256":"80e141a7e9386b8d49520586949ebf020b18521f0b890ca795c8fc0a23540506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:31.014914Z","signature_b64":"fWiMwaWDRXKF4CClZZpX+2VYZAxSbc5g+iqzqTvr/W57N1xAwvKJZvjzVOpPdw/ghkLhTJ8QdE9AJuBYnxxXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e141a7e9386b8d49520586949ebf020b18521f0b890ca795c8fc0a23540506","last_reissued_at":"2026-07-05T05:22:31.014511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:31.014511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.08842","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9dkhvI0IrPwB2odJzzkrKK7Q+PJ+KkyWudFDk7gzX4C+rpNOUra4/4sj1977yte4pCGpXXkoCteXuLkR0xNAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:25.816280Z"},"content_sha256":"007f3e072e24845bac62d12c7e7148970c9f1663528cc8d9b03363b9d3113d6a","schema_version":"1.0","event_id":"sha256:007f3e072e24845bac62d12c7e7148970c9f1663528cc8d9b03363b9d3113d6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QDQUDJ7JHBVY2SKSAWDJJHV7AI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenchen Zhou, Jun Lin, Keli Xie, Siyuan Lu, Zhongfeng Wang","submitted_at":"2022-11-16T11:43:09Z","abstract_excerpt":"With the development of deep learning and Transformer-based pre-trained models like BERT, the accuracy of many NLP tasks has been dramatically improved. However, the large number of parameters and computations also pose challenges for their deployment. For instance, using BERT can improve the predictions in the financial sentiment analysis (FSA) task but slow it down, where speed and accuracy are equally important in terms of profits. To address these issues, we first propose an efficient and lightweight BERT (ELBERT) along with a novel confidence-window-based (CWB) early exit mechanism. Based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08842","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/2211.08842/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mAyDTmR+s3GWOppafKNBJcQIIeOZjNTcR01gx4+ItL2mK2weOxKGl9RLV/C/BMyvRBQbilLzbRZrniJCXsNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:25.816668Z"},"content_sha256":"124833848ef046fbe96d4b0fe9efe77e7fdc8da9321cf041490f50078e995d15","schema_version":"1.0","event_id":"sha256:124833848ef046fbe96d4b0fe9efe77e7fdc8da9321cf041490f50078e995d15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/bundle.json","state_url":"https://pith.science/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T14:06:25Z","links":{"resolver":"https://pith.science/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI","bundle":"https://pith.science/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/bundle.json","state":"https://pith.science/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDQUDJ7JHBVY2SKSAWDJJHV7AI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QDQUDJ7JHBVY2SKSAWDJJHV7AI","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":"45011d062a84ca70afff41e964b2ba9971ba195cd6ce02fd6a741aaeb0410a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T11:43:09Z","title_canon_sha256":"d12cd2ce64d76f9e95fd63a8c95c710104c48cf93a28da2af371ad0109d0143c"},"schema_version":"1.0","source":{"id":"2211.08842","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08842","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08842v2","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08842","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"QDQUDJ7JHBVY","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"QDQUDJ7JHBVY2SKS","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"QDQUDJ7J","created_at":"2026-07-05T05:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:124833848ef046fbe96d4b0fe9efe77e7fdc8da9321cf041490f50078e995d15","target":"graph","created_at":"2026-07-05T05:22:31Z","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/2211.08842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of deep learning and Transformer-based pre-trained models like BERT, the accuracy of many NLP tasks has been dramatically improved. However, the large number of parameters and computations also pose challenges for their deployment. For instance, using BERT can improve the predictions in the financial sentiment analysis (FSA) task but slow it down, where speed and accuracy are equally important in terms of profits. To address these issues, we first propose an efficient and lightweight BERT (ELBERT) along with a novel confidence-window-based (CWB) early exit mechanism. Based","authors_text":"Chenchen Zhou, Jun Lin, Keli Xie, Siyuan Lu, Zhongfeng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T11:43:09Z","title":"Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08842","kind":"arxiv","version":2},"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":"sha256:007f3e072e24845bac62d12c7e7148970c9f1663528cc8d9b03363b9d3113d6a","target":"record","created_at":"2026-07-05T05:22:31Z","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":"45011d062a84ca70afff41e964b2ba9971ba195cd6ce02fd6a741aaeb0410a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T11:43:09Z","title_canon_sha256":"d12cd2ce64d76f9e95fd63a8c95c710104c48cf93a28da2af371ad0109d0143c"},"schema_version":"1.0","source":{"id":"2211.08842","kind":"arxiv","version":2}},"canonical_sha256":"80e141a7e9386b8d49520586949ebf020b18521f0b890ca795c8fc0a23540506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e141a7e9386b8d49520586949ebf020b18521f0b890ca795c8fc0a23540506","first_computed_at":"2026-07-05T05:22:31.014511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:31.014511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fWiMwaWDRXKF4CClZZpX+2VYZAxSbc5g+iqzqTvr/W57N1xAwvKJZvjzVOpPdw/ghkLhTJ8QdE9AJuBYnxxXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:31.014914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08842","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:007f3e072e24845bac62d12c7e7148970c9f1663528cc8d9b03363b9d3113d6a","sha256:124833848ef046fbe96d4b0fe9efe77e7fdc8da9321cf041490f50078e995d15"],"state_sha256":"4c2c2e9a0a02bbaaac21e6da1708a504e9ae260ee0ffa6019340e99025c35dc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcbrMdRsHOSz6YTVexPJlLUMDcEvQ/lKrkKs/4zcFbV4MbLKOZ7CriPac8HRC8NuSy0raqQ/AvGTBYnOZ/eDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:06:25.818669Z","bundle_sha256":"8b9a04eb1afb2fdfa81d9127f06be5e81503be3a81cc8357a824f3cda3930f1c"}}