{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LMU7A47N5DXW25NMRVM4WOTPRI","short_pith_number":"pith:LMU7A47N","schema_version":"1.0","canonical_sha256":"5b29f073ede8ef6d75ac8d59cb3a6f8a2a45121691849d9b39fdb639f1867e88","source":{"kind":"arxiv","id":"2206.10461","version":1},"attestation_state":"computed","paper":{"title":"An Automatic and Efficient BERT Pruning for Edge AI Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiwen Ding, Dongkuan Xu, Hongjia Li, Hongwu Peng, Mimi Xie, Ning Liu, Shaoyi Huang, Yueying Liang","submitted_at":"2022-06-21T15:10:29Z","abstract_excerpt":"With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy. Existing BERT pruning methods require domain experts to heuristically handcraft hyperparameters to strike a balance among model size, latency, and accuracy. In this work, we propose AE-BERT, an automatic and efficient BERT pruning framework with efficient evaluation to select a \"good\" sub-network candidate (with high accuracy) given the overall pruning ratio constraints. Our p"},"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":"2206.10461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T15:10:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5773503b47a0f2c84b19ed053134e5e6c0ebbd047a545f7651ff733672f32f0","abstract_canon_sha256":"2aa7939bb7211b5829c46a2c4ad8d9d2880972d976357a7c37e2464c3afe2eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:47.937073Z","signature_b64":"KsuPMLMeb0eSItWi7xDw9m1uc4KgbO9T/HgExHq4sK/sYKr72ZebUREcHptTieNQ8xqDuHmUjjI6ahOhh5adDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b29f073ede8ef6d75ac8d59cb3a6f8a2a45121691849d9b39fdb639f1867e88","last_reissued_at":"2026-07-05T04:33:47.936648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:47.936648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Automatic and Efficient BERT Pruning for Edge AI Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiwen Ding, Dongkuan Xu, Hongjia Li, Hongwu Peng, Mimi Xie, Ning Liu, Shaoyi Huang, Yueying Liang","submitted_at":"2022-06-21T15:10:29Z","abstract_excerpt":"With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy. Existing BERT pruning methods require domain experts to heuristically handcraft hyperparameters to strike a balance among model size, latency, and accuracy. In this work, we propose AE-BERT, an automatic and efficient BERT pruning framework with efficient evaluation to select a \"good\" sub-network candidate (with high accuracy) given the overall pruning ratio constraints. Our p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10461","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/2206.10461/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":"2206.10461","created_at":"2026-07-05T04:33:47.936710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10461v1","created_at":"2026-07-05T04:33:47.936710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10461","created_at":"2026-07-05T04:33:47.936710+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMU7A47N5DXW","created_at":"2026-07-05T04:33:47.936710+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMU7A47N5DXW25NM","created_at":"2026-07-05T04:33:47.936710+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMU7A47N","created_at":"2026-07-05T04:33:47.936710+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/LMU7A47N5DXW25NMRVM4WOTPRI","json":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI.json","graph_json":"https://pith.science/api/pith-number/LMU7A47N5DXW25NMRVM4WOTPRI/graph.json","events_json":"https://pith.science/api/pith-number/LMU7A47N5DXW25NMRVM4WOTPRI/events.json","paper":"https://pith.science/paper/LMU7A47N"},"agent_actions":{"view_html":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI","download_json":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI.json","view_paper":"https://pith.science/paper/LMU7A47N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10461&json=true","fetch_graph":"https://pith.science/api/pith-number/LMU7A47N5DXW25NMRVM4WOTPRI/graph.json","fetch_events":"https://pith.science/api/pith-number/LMU7A47N5DXW25NMRVM4WOTPRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI/action/storage_attestation","attest_author":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI/action/author_attestation","sign_citation":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI/action/citation_signature","submit_replication":"https://pith.science/pith/LMU7A47N5DXW25NMRVM4WOTPRI/action/replication_record"}},"created_at":"2026-07-05T04:33:47.936710+00:00","updated_at":"2026-07-05T04:33:47.936710+00:00"}