{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BCB7TNVOWTZTOP3AFXBFTTOXYD","short_pith_number":"pith:BCB7TNVO","schema_version":"1.0","canonical_sha256":"0883f9b6aeb4f3373f602dc259cdd7c0f2a6317ab7405d8c9e942779b97fc996","source":{"kind":"arxiv","id":"2204.02601","version":1},"attestation_state":"computed","paper":{"title":"Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Huang, Fuli Luo, Liwei Wang, Runxin Xu, Songfang Huang, Yanyang Li","submitted_at":"2022-04-06T06:29:52Z","abstract_excerpt":"Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena: for settings, individually pruning for each language does not induce a better result; for algorithms, the simplest method performs the best; for efficiency, a fast model does not imply that it is also small. To facilita"},"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":"2204.02601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T06:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"68e3c97188c8b9c0ddd141fd83ebeedb0ab35347eae5664ec0cf26d7381c9e88","abstract_canon_sha256":"4c3ba91e36ae047bcfa40f5c8a0f0c5293167640d350796312134bbb522cb82c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:10.594118Z","signature_b64":"d6+hRPPPO1Bg+KZLX5bjN2gbx0aHTtPAjVnk2yYuxeqfFma4o5c4GSGtfPsqAHov1Vv6WPhOXU/05X3qQ4FLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0883f9b6aeb4f3373f602dc259cdd7c0f2a6317ab7405d8c9e942779b97fc996","last_reissued_at":"2026-07-05T04:12:10.593678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:10.593678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Huang, Fuli Luo, Liwei Wang, Runxin Xu, Songfang Huang, Yanyang Li","submitted_at":"2022-04-06T06:29:52Z","abstract_excerpt":"Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena: for settings, individually pruning for each language does not induce a better result; for algorithms, the simplest method performs the best; for efficiency, a fast model does not imply that it is also small. To facilita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02601","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/2204.02601/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":"2204.02601","created_at":"2026-07-05T04:12:10.593734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02601v1","created_at":"2026-07-05T04:12:10.593734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02601","created_at":"2026-07-05T04:12:10.593734+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCB7TNVOWTZT","created_at":"2026-07-05T04:12:10.593734+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCB7TNVOWTZTOP3A","created_at":"2026-07-05T04:12:10.593734+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCB7TNVO","created_at":"2026-07-05T04:12:10.593734+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/BCB7TNVOWTZTOP3AFXBFTTOXYD","json":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD.json","graph_json":"https://pith.science/api/pith-number/BCB7TNVOWTZTOP3AFXBFTTOXYD/graph.json","events_json":"https://pith.science/api/pith-number/BCB7TNVOWTZTOP3AFXBFTTOXYD/events.json","paper":"https://pith.science/paper/BCB7TNVO"},"agent_actions":{"view_html":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD","download_json":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD.json","view_paper":"https://pith.science/paper/BCB7TNVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02601&json=true","fetch_graph":"https://pith.science/api/pith-number/BCB7TNVOWTZTOP3AFXBFTTOXYD/graph.json","fetch_events":"https://pith.science/api/pith-number/BCB7TNVOWTZTOP3AFXBFTTOXYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD/action/storage_attestation","attest_author":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD/action/author_attestation","sign_citation":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD/action/citation_signature","submit_replication":"https://pith.science/pith/BCB7TNVOWTZTOP3AFXBFTTOXYD/action/replication_record"}},"created_at":"2026-07-05T04:12:10.593734+00:00","updated_at":"2026-07-05T04:12:10.593734+00:00"}