{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LESIB6L7IBRHMMDOYK53KFU3UO","short_pith_number":"pith:LESIB6L7","schema_version":"1.0","canonical_sha256":"592480f97f406276306ec2bbb5169ba399a3e08246dad50a49fdcbbed8113339","source":{"kind":"arxiv","id":"2212.11670","version":1},"attestation_state":"computed","paper":{"title":"Evaluation for Change","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Rishi Bommasani","submitted_at":"2022-12-20T17:49:27Z","abstract_excerpt":"Evaluation is the central means for assessing, understanding, and communicating about NLP models. In this position paper, we argue evaluation should be more than that: it is a force for driving change, carrying a sociological and political character beyond its technical dimensions. As a force, evaluation's power arises from its adoption: under our view, evaluation succeeds when it achieves the desired change in the field. Further, by framing evaluation as a force, we consider how it competes with other forces. Under our analysis, we conjecture that the current trajectory of NLP suggests evalua"},"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":"2212.11670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T17:49:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b63d9553e9f0c70e2d7a1d8c33c9e0d7ebe71211731a135dd6f526de1499a86","abstract_canon_sha256":"5d31c384e45cac4548795827503bee338d48287b877016b6959122b3b1aac637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:41.383843Z","signature_b64":"xF/iVCJ8Pkw4SQcMrNPjD56+FR7MjfIiMMJw/qhkBbKlZIoGJyl8K51eQpUS1GTqgQ60MmMJc9CSTbbOjejVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"592480f97f406276306ec2bbb5169ba399a3e08246dad50a49fdcbbed8113339","last_reissued_at":"2026-07-05T05:27:41.383414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:41.383414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation for Change","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Rishi Bommasani","submitted_at":"2022-12-20T17:49:27Z","abstract_excerpt":"Evaluation is the central means for assessing, understanding, and communicating about NLP models. In this position paper, we argue evaluation should be more than that: it is a force for driving change, carrying a sociological and political character beyond its technical dimensions. As a force, evaluation's power arises from its adoption: under our view, evaluation succeeds when it achieves the desired change in the field. Further, by framing evaluation as a force, we consider how it competes with other forces. Under our analysis, we conjecture that the current trajectory of NLP suggests evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11670","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/2212.11670/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":"2212.11670","created_at":"2026-07-05T05:27:41.383468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11670v1","created_at":"2026-07-05T05:27:41.383468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11670","created_at":"2026-07-05T05:27:41.383468+00:00"},{"alias_kind":"pith_short_12","alias_value":"LESIB6L7IBRH","created_at":"2026-07-05T05:27:41.383468+00:00"},{"alias_kind":"pith_short_16","alias_value":"LESIB6L7IBRHMMDO","created_at":"2026-07-05T05:27:41.383468+00:00"},{"alias_kind":"pith_short_8","alias_value":"LESIB6L7","created_at":"2026-07-05T05:27:41.383468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03038","citing_title":"The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO","json":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO.json","graph_json":"https://pith.science/api/pith-number/LESIB6L7IBRHMMDOYK53KFU3UO/graph.json","events_json":"https://pith.science/api/pith-number/LESIB6L7IBRHMMDOYK53KFU3UO/events.json","paper":"https://pith.science/paper/LESIB6L7"},"agent_actions":{"view_html":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO","download_json":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO.json","view_paper":"https://pith.science/paper/LESIB6L7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11670&json=true","fetch_graph":"https://pith.science/api/pith-number/LESIB6L7IBRHMMDOYK53KFU3UO/graph.json","fetch_events":"https://pith.science/api/pith-number/LESIB6L7IBRHMMDOYK53KFU3UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO/action/storage_attestation","attest_author":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO/action/author_attestation","sign_citation":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO/action/citation_signature","submit_replication":"https://pith.science/pith/LESIB6L7IBRHMMDOYK53KFU3UO/action/replication_record"}},"created_at":"2026-07-05T05:27:41.383468+00:00","updated_at":"2026-07-05T05:27:41.383468+00:00"}