{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5HXQQI4SEMKHODOGWPP5RASDLL","short_pith_number":"pith:5HXQQI4S","schema_version":"1.0","canonical_sha256":"e9ef0823922314770dc6b3dfd882435ad226cdb26ed3087eae3e216a03c1c847","source":{"kind":"arxiv","id":"2005.13213","version":1},"attestation_state":"computed","paper":{"title":"Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jey Han Lau, Kobi Leins, Timothy Baldwin","submitted_at":"2020-05-27T07:31:57Z","abstract_excerpt":"As part of growing NLP capabilities, coupled with an awareness of the ethical dimensions of research, questions have been raised about whether particular datasets and tasks should be deemed off-limits for NLP research. We examine this question with respect to a paper on automatic legal sentencing from EMNLP 2019 which was a source of some debate, in asking whether the paper should have been allowed to be published, who should have been charged with making such a decision, and on what basis. We focus in particular on the role of data statements in ethically assessing research, but also discuss "},"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":"2005.13213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-27T07:31:57Z","cross_cats_sorted":[],"title_canon_sha256":"c1c3db19e2acf861f80dbca28217fdaa55685408fa427391891ffd86f0b91647","abstract_canon_sha256":"c391755d45e89ccb66a6bc32769ee08f76d8777a3fa3dc4c29f769745c8b69be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:14.014041Z","signature_b64":"23TVayg6ZblV/dC/F6NLKBCeg2LKwyi24zpT2Wh/bJZpD9BBXFcN+05MORmb31ps9Lwa25QNCwBxll5KkKvhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ef0823922314770dc6b3dfd882435ad226cdb26ed3087eae3e216a03c1c847","last_reissued_at":"2026-07-05T01:06:14.013598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:14.013598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jey Han Lau, Kobi Leins, Timothy Baldwin","submitted_at":"2020-05-27T07:31:57Z","abstract_excerpt":"As part of growing NLP capabilities, coupled with an awareness of the ethical dimensions of research, questions have been raised about whether particular datasets and tasks should be deemed off-limits for NLP research. We examine this question with respect to a paper on automatic legal sentencing from EMNLP 2019 which was a source of some debate, in asking whether the paper should have been allowed to be published, who should have been charged with making such a decision, and on what basis. We focus in particular on the role of data statements in ethically assessing research, but also discuss "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13213","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/2005.13213/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":"2005.13213","created_at":"2026-07-05T01:06:14.013656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.13213v1","created_at":"2026-07-05T01:06:14.013656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13213","created_at":"2026-07-05T01:06:14.013656+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HXQQI4SEMKH","created_at":"2026-07-05T01:06:14.013656+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HXQQI4SEMKHODOG","created_at":"2026-07-05T01:06:14.013656+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HXQQI4S","created_at":"2026-07-05T01:06:14.013656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07936","citing_title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","ref_index":126,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL","json":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL.json","graph_json":"https://pith.science/api/pith-number/5HXQQI4SEMKHODOGWPP5RASDLL/graph.json","events_json":"https://pith.science/api/pith-number/5HXQQI4SEMKHODOGWPP5RASDLL/events.json","paper":"https://pith.science/paper/5HXQQI4S"},"agent_actions":{"view_html":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL","download_json":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL.json","view_paper":"https://pith.science/paper/5HXQQI4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.13213&json=true","fetch_graph":"https://pith.science/api/pith-number/5HXQQI4SEMKHODOGWPP5RASDLL/graph.json","fetch_events":"https://pith.science/api/pith-number/5HXQQI4SEMKHODOGWPP5RASDLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL/action/storage_attestation","attest_author":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL/action/author_attestation","sign_citation":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL/action/citation_signature","submit_replication":"https://pith.science/pith/5HXQQI4SEMKHODOGWPP5RASDLL/action/replication_record"}},"created_at":"2026-07-05T01:06:14.013656+00:00","updated_at":"2026-07-05T01:06:14.013656+00:00"}