{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XHZADZDWWPMWYRTQ5B3THS3LNV","short_pith_number":"pith:XHZADZDW","schema_version":"1.0","canonical_sha256":"b9f201e476b3d96c4670e87733cb6b6d4cf044cca387fa684384ced31ed7e1b9","source":{"kind":"arxiv","id":"2204.07288","version":1},"attestation_state":"computed","paper":{"title":"Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Lisa Wu Wills, Phyllis Ang","submitted_at":"2022-04-15T01:52:45Z","abstract_excerpt":"With many real-world applications of Natural Language Processing (NLP) comprising of long texts, there has been a rise in NLP benchmarks that measure the accuracy of models that can handle longer input sequences. However, these benchmarks do not consider the trade-offs between accuracy, speed, and power consumption as input sizes or model sizes are varied. In this work, we perform a systematic study of this accuracy vs. efficiency trade-off on two widely used long-sequence models - Longformer-Encoder-Decoder (LED) and Big Bird - during fine-tuning and inference on four datasets from the SCROLL"},"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":"2204.07288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-15T01:52:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b34de81bfde9fd15b5a460721c72cddab0ca857bdff3f447b1eb14823e635ef","abstract_canon_sha256":"645c0fcd1e23508d9e67ef0c8103981f1bcf13a9bed74608a94eff74e94acd49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:53.520295Z","signature_b64":"V8wDFJ6VrDWTfCLytpzWpru/ZSIkG1yrxCLPEbleK6YBqVGjFmdIZaunWZcGwv78Ce1x+JSonFa4APYS03XqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f201e476b3d96c4670e87733cb6b6d4cf044cca387fa684384ced31ed7e1b9","last_reissued_at":"2026-07-05T04:14:53.519902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:53.519902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Lisa Wu Wills, Phyllis Ang","submitted_at":"2022-04-15T01:52:45Z","abstract_excerpt":"With many real-world applications of Natural Language Processing (NLP) comprising of long texts, there has been a rise in NLP benchmarks that measure the accuracy of models that can handle longer input sequences. However, these benchmarks do not consider the trade-offs between accuracy, speed, and power consumption as input sizes or model sizes are varied. In this work, we perform a systematic study of this accuracy vs. efficiency trade-off on two widely used long-sequence models - Longformer-Encoder-Decoder (LED) and Big Bird - during fine-tuning and inference on four datasets from the SCROLL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07288","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/2204.07288/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":"2204.07288","created_at":"2026-07-05T04:14:53.519958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.07288v1","created_at":"2026-07-05T04:14:53.519958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07288","created_at":"2026-07-05T04:14:53.519958+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHZADZDWWPMW","created_at":"2026-07-05T04:14:53.519958+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHZADZDWWPMWYRTQ","created_at":"2026-07-05T04:14:53.519958+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHZADZDW","created_at":"2026-07-05T04:14:53.519958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02641","citing_title":"SEMANTIC SEE-THROUGH GOGGLES: Wearing Linguistic Virtual Reality in (Artificial) Intelligence","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV","json":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV.json","graph_json":"https://pith.science/api/pith-number/XHZADZDWWPMWYRTQ5B3THS3LNV/graph.json","events_json":"https://pith.science/api/pith-number/XHZADZDWWPMWYRTQ5B3THS3LNV/events.json","paper":"https://pith.science/paper/XHZADZDW"},"agent_actions":{"view_html":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV","download_json":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV.json","view_paper":"https://pith.science/paper/XHZADZDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.07288&json=true","fetch_graph":"https://pith.science/api/pith-number/XHZADZDWWPMWYRTQ5B3THS3LNV/graph.json","fetch_events":"https://pith.science/api/pith-number/XHZADZDWWPMWYRTQ5B3THS3LNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV/action/storage_attestation","attest_author":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV/action/author_attestation","sign_citation":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV/action/citation_signature","submit_replication":"https://pith.science/pith/XHZADZDWWPMWYRTQ5B3THS3LNV/action/replication_record"}},"created_at":"2026-07-05T04:14:53.519958+00:00","updated_at":"2026-07-05T04:14:53.519958+00:00"}