{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HA2JKUSCC6NT72KYYHQEALGICW","short_pith_number":"pith:HA2JKUSC","schema_version":"1.0","canonical_sha256":"3834955242179b3fe958c1e0402cc815a6f06a41e7024aa1d733c5ef1c75c72a","source":{"kind":"arxiv","id":"2010.06595","version":1},"attestation_state":"computed","paper":{"title":"With Little Power Comes Great Responsibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dallas Card, Dan Jurafsky, Kyle Mahowald, Peter Henderson, Robin Jia, Urvashi Khandelwal","submitted_at":"2020-10-13T18:00:02Z","abstract_excerpt":"Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored by the NLP community. Underpowered experiments make it more difficult to discern the difference between statistical noise and meaningful model improvements, and increase the chances of exaggerated findings. By meta-analyzing a set of existing NLP papers and datasets, we characterize typical power for a variety of settings and conclude that underpowered experiments are common in the NLP literature. In particular, for"},"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":"2010.06595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-13T18:00:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c67ee3123d3f2519675c600e0b7f5b6e1dd1d419eb1d7c8794264f2bd9ce9831","abstract_canon_sha256":"c1946f1d14f285609e9d7c556803d3baea62072f339481c0888a0b1c5308d2e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:57.602386Z","signature_b64":"8dt/vA/hwEBEzO4w1MOPgbRhb6PiI+Mk0yvrNxhPprp+ZFIhbGn/R5K3eOHykHHyzmd4Ust+DZ6S/Flsr47kAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3834955242179b3fe958c1e0402cc815a6f06a41e7024aa1d733c5ef1c75c72a","last_reissued_at":"2026-07-05T01:42:57.601978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:57.601978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"With Little Power Comes Great Responsibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dallas Card, Dan Jurafsky, Kyle Mahowald, Peter Henderson, Robin Jia, Urvashi Khandelwal","submitted_at":"2020-10-13T18:00:02Z","abstract_excerpt":"Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored by the NLP community. Underpowered experiments make it more difficult to discern the difference between statistical noise and meaningful model improvements, and increase the chances of exaggerated findings. By meta-analyzing a set of existing NLP papers and datasets, we characterize typical power for a variety of settings and conclude that underpowered experiments are common in the NLP literature. In particular, for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06595","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/2010.06595/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":"2010.06595","created_at":"2026-07-05T01:42:57.602040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06595v1","created_at":"2026-07-05T01:42:57.602040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06595","created_at":"2026-07-05T01:42:57.602040+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA2JKUSCC6NT","created_at":"2026-07-05T01:42:57.602040+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA2JKUSCC6NT72KY","created_at":"2026-07-05T01:42:57.602040+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA2JKUSC","created_at":"2026-07-05T01:42:57.602040+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/HA2JKUSCC6NT72KYYHQEALGICW","json":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW.json","graph_json":"https://pith.science/api/pith-number/HA2JKUSCC6NT72KYYHQEALGICW/graph.json","events_json":"https://pith.science/api/pith-number/HA2JKUSCC6NT72KYYHQEALGICW/events.json","paper":"https://pith.science/paper/HA2JKUSC"},"agent_actions":{"view_html":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW","download_json":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW.json","view_paper":"https://pith.science/paper/HA2JKUSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06595&json=true","fetch_graph":"https://pith.science/api/pith-number/HA2JKUSCC6NT72KYYHQEALGICW/graph.json","fetch_events":"https://pith.science/api/pith-number/HA2JKUSCC6NT72KYYHQEALGICW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW/action/storage_attestation","attest_author":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW/action/author_attestation","sign_citation":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW/action/citation_signature","submit_replication":"https://pith.science/pith/HA2JKUSCC6NT72KYYHQEALGICW/action/replication_record"}},"created_at":"2026-07-05T01:42:57.602040+00:00","updated_at":"2026-07-05T01:42:57.602040+00:00"}