{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S2J42CAW76S4UIQEM3I7JQXT4C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb2019ce3798bb257239de3fc4b53c8481cdb7773eaee4ae96129a46a0d753e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T21:12:07Z","title_canon_sha256":"d9d4bfc2d6cc189132af0e3632b55965329af2c3573f848a7aced4ce1f314299"},"schema_version":"1.0","source":{"id":"2305.09022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09022","created_at":"2026-07-05T06:11:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09022v1","created_at":"2026-07-05T06:11:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09022","created_at":"2026-07-05T06:11:33Z"},{"alias_kind":"pith_short_12","alias_value":"S2J42CAW76S4","created_at":"2026-07-05T06:11:33Z"},{"alias_kind":"pith_short_16","alias_value":"S2J42CAW76S4UIQE","created_at":"2026-07-05T06:11:33Z"},{"alias_kind":"pith_short_8","alias_value":"S2J42CAW","created_at":"2026-07-05T06:11:33Z"}],"graph_snapshots":[{"event_id":"sha256:d5858f5a3f785b97c4e4ad37fb377ea3455c39a8ae1c808d243f186e8e36dbad","target":"graph","created_at":"2026-07-05T06:11:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.09022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Progress in NLP is increasingly measured through benchmarks; hence, contextualizing progress requires understanding when and why practitioners may disagree about the validity of benchmarks. We develop a taxonomy of disagreement, drawing on tools from measurement modeling, and distinguish between two types of disagreement: 1) how tasks are conceptualized and 2) how measurements of model performance are operationalized. To provide evidence for our taxonomy, we conduct a meta-analysis of relevant literature to understand how NLP tasks are conceptualized, as well as a survey of practitioners about","authors_text":"Arjun Subramonian, Hal Daum\\'e III, Su Lin Blodgett, Xingdi Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T21:12:07Z","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09022","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8007f0493ca470d99e2c6b93b643c4020f2858c6dfe0cb359fbc6510efc0be3","target":"record","created_at":"2026-07-05T06:11:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bb2019ce3798bb257239de3fc4b53c8481cdb7773eaee4ae96129a46a0d753e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T21:12:07Z","title_canon_sha256":"d9d4bfc2d6cc189132af0e3632b55965329af2c3573f848a7aced4ce1f314299"},"schema_version":"1.0","source":{"id":"2305.09022","kind":"arxiv","version":1}},"canonical_sha256":"9693cd0816ffa5ca220466d1f4c2f3e0b5dc3f7f301341f46a53f7da44996d83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9693cd0816ffa5ca220466d1f4c2f3e0b5dc3f7f301341f46a53f7da44996d83","first_computed_at":"2026-07-05T06:11:33.270096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:33.270096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TpOvvyECjQlgRRU9iZfaXkqsn2z/qTmHEOzGchnCexYf/X6wxm8NJAix8GyDFmS2L0BaVoHfxRDvRpEMaRsuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:33.270518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8007f0493ca470d99e2c6b93b643c4020f2858c6dfe0cb359fbc6510efc0be3","sha256:d5858f5a3f785b97c4e4ad37fb377ea3455c39a8ae1c808d243f186e8e36dbad"],"state_sha256":"26f5397c2523b139a59dcf7b32891d8303e8379a54a4f9cf6fadc9480c830623"}