{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FER3QRPUKPOTNYFQESMWLWRSH7","short_pith_number":"pith:FER3QRPU","schema_version":"1.0","canonical_sha256":"2923b845f453dd36e0b0249965da323fe9b9baecf9acf6f4639bf07545127d7a","source":{"kind":"arxiv","id":"2110.03036","version":1},"attestation_state":"computed","paper":{"title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julia Kreutzer, Orevaoghene Ahia, Sara Hooker","submitted_at":"2021-10-06T19:48:18Z","abstract_excerpt":"A \"bigger is better\" explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed importance as a way to bridge the gap. However, evaluation of the trade-offs incurred by popular compression techniques has been centered on high-resource datasets. In this work, we instead consider the impact of compression in a data-limited regime. We introduce the term low-resource double bind to refer to the co-occurrence of data limitations and co"},"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":"2110.03036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T19:48:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"456aa3e2a6a0d2b8ac7a90cb8dc4cedeeb932623850f5a8773f19ac99e6ccd41","abstract_canon_sha256":"77004278b4d726e132cbaa4aae147414bf0ccc41c321d5ab9d035e25607a745b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:38.989459Z","signature_b64":"JPDeIk2QVN66hIN5p+5I8W0IYhrs7uA70yMIYQ80e2ccSEtpQaNWLnVg3zsOV6oeXgfUCFLVSUQfOqlQqT+NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2923b845f453dd36e0b0249965da323fe9b9baecf9acf6f4639bf07545127d7a","last_reissued_at":"2026-07-05T03:20:38.989037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:38.989037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julia Kreutzer, Orevaoghene Ahia, Sara Hooker","submitted_at":"2021-10-06T19:48:18Z","abstract_excerpt":"A \"bigger is better\" explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed importance as a way to bridge the gap. However, evaluation of the trade-offs incurred by popular compression techniques has been centered on high-resource datasets. In this work, we instead consider the impact of compression in a data-limited regime. We introduce the term low-resource double bind to refer to the co-occurrence of data limitations and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03036","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/2110.03036/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":"2110.03036","created_at":"2026-07-05T03:20:38.989087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03036v1","created_at":"2026-07-05T03:20:38.989087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03036","created_at":"2026-07-05T03:20:38.989087+00:00"},{"alias_kind":"pith_short_12","alias_value":"FER3QRPUKPOT","created_at":"2026-07-05T03:20:38.989087+00:00"},{"alias_kind":"pith_short_16","alias_value":"FER3QRPUKPOTNYFQ","created_at":"2026-07-05T03:20:38.989087+00:00"},{"alias_kind":"pith_short_8","alias_value":"FER3QRPU","created_at":"2026-07-05T03:20:38.989087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2207.04672","citing_title":"No Language Left Behind: Scaling Human-Centered Machine Translation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7","json":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7.json","graph_json":"https://pith.science/api/pith-number/FER3QRPUKPOTNYFQESMWLWRSH7/graph.json","events_json":"https://pith.science/api/pith-number/FER3QRPUKPOTNYFQESMWLWRSH7/events.json","paper":"https://pith.science/paper/FER3QRPU"},"agent_actions":{"view_html":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7","download_json":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7.json","view_paper":"https://pith.science/paper/FER3QRPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03036&json=true","fetch_graph":"https://pith.science/api/pith-number/FER3QRPUKPOTNYFQESMWLWRSH7/graph.json","fetch_events":"https://pith.science/api/pith-number/FER3QRPUKPOTNYFQESMWLWRSH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7/action/storage_attestation","attest_author":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7/action/author_attestation","sign_citation":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7/action/citation_signature","submit_replication":"https://pith.science/pith/FER3QRPUKPOTNYFQESMWLWRSH7/action/replication_record"}},"created_at":"2026-07-05T03:20:38.989087+00:00","updated_at":"2026-07-05T03:20:38.989087+00:00"}