{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TQLDOHFTGODLOEXLIX46EMZLYE","short_pith_number":"pith:TQLDOHFT","schema_version":"1.0","canonical_sha256":"9c16371cb33386b712eb45f9e2332bc1052c481d0af5bc2543cb003c4df9c9af","source":{"kind":"arxiv","id":"2304.07007","version":1},"attestation_state":"computed","paper":{"title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Schlangen","submitted_at":"2023-04-14T09:11:36Z","abstract_excerpt":"How does one measure \"ability to understand language\"? If it is a person's ability that is being measured, this is a question that almost never poses itself in an unqualified manner: Whatever formal test is applied, it takes place on the background of the person's language use in daily social practice, and what is measured is a specialised variety of language understanding (e.g., of a second language; or of written, technical language). Computer programs do not have this background. What does that mean for the applicability of formal tests of language understanding? I argue that such tests nee"},"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":"2304.07007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T09:11:36Z","cross_cats_sorted":[],"title_canon_sha256":"471dbad99dd2caa63de80b14810c077ffd2d89833ac989dfda44098d94f79b2e","abstract_canon_sha256":"bda487fb34bdaf6ca1d2949fd1b45ffae7ae7a20727c3de50c5ca7bd9b6746bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:04.165260Z","signature_b64":"uyUXLlrue/9yOGeaHWweU1o/TcfQ5Zu4Fujjolzn5gllFn+UFYz1JgQHLyREzly85xXyE6cIy396L63eMrjZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c16371cb33386b712eb45f9e2332bc1052c481d0af5bc2543cb003c4df9c9af","last_reissued_at":"2026-07-05T06:01:04.164886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:04.164886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Schlangen","submitted_at":"2023-04-14T09:11:36Z","abstract_excerpt":"How does one measure \"ability to understand language\"? If it is a person's ability that is being measured, this is a question that almost never poses itself in an unqualified manner: Whatever formal test is applied, it takes place on the background of the person's language use in daily social practice, and what is measured is a specialised variety of language understanding (e.g., of a second language; or of written, technical language). Computer programs do not have this background. What does that mean for the applicability of formal tests of language understanding? I argue that such tests nee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07007","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/2304.07007/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":"2304.07007","created_at":"2026-07-05T06:01:04.164940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07007v1","created_at":"2026-07-05T06:01:04.164940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07007","created_at":"2026-07-05T06:01:04.164940+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQLDOHFTGODL","created_at":"2026-07-05T06:01:04.164940+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQLDOHFTGODLOEXL","created_at":"2026-07-05T06:01:04.164940+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQLDOHFT","created_at":"2026-07-05T06:01:04.164940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":239,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE","json":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE.json","graph_json":"https://pith.science/api/pith-number/TQLDOHFTGODLOEXLIX46EMZLYE/graph.json","events_json":"https://pith.science/api/pith-number/TQLDOHFTGODLOEXLIX46EMZLYE/events.json","paper":"https://pith.science/paper/TQLDOHFT"},"agent_actions":{"view_html":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE","download_json":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE.json","view_paper":"https://pith.science/paper/TQLDOHFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07007&json=true","fetch_graph":"https://pith.science/api/pith-number/TQLDOHFTGODLOEXLIX46EMZLYE/graph.json","fetch_events":"https://pith.science/api/pith-number/TQLDOHFTGODLOEXLIX46EMZLYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE/action/storage_attestation","attest_author":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE/action/author_attestation","sign_citation":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE/action/citation_signature","submit_replication":"https://pith.science/pith/TQLDOHFTGODLOEXLIX46EMZLYE/action/replication_record"}},"created_at":"2026-07-05T06:01:04.164940+00:00","updated_at":"2026-07-05T06:01:04.164940+00:00"}