{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DBPQIA4IOS3CZ3ES7GHPS67BQF","short_pith_number":"pith:DBPQIA4I","schema_version":"1.0","canonical_sha256":"185f04038874b62cec92f98ef97be1814b2f25635dfa2886d54d802446f65714","source":{"kind":"arxiv","id":"2607.08842","version":1},"attestation_state":"computed","paper":{"title":"L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Ben Knight, Danielle Carvalho, James Edgell, Martin Ku, Wm. Matthew Kennedy","submitted_at":"2026-07-09T18:02:55Z","abstract_excerpt":"Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning ou"},"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":"2607.08842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-09T18:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"95f1a3f4c1baf429005413034c34dacdd9c10d51123041917ad4b0d3468678d8","abstract_canon_sha256":"24b39911c8b6c6e9b3a5f4fd298f7d5464cc6bfeafb882604d0a7e7f0ab9ca02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:21.467220Z","signature_b64":"cB/vykwNOgyeRZ6EjKSWzg3u16pFAD596nj74SBw7yRKn/FVba5mKC4UzX+SCLn/um4nJDFlUpolC88FT1vrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"185f04038874b62cec92f98ef97be1814b2f25635dfa2886d54d802446f65714","last_reissued_at":"2026-07-13T00:17:21.466137Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:21.466137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Ben Knight, Danielle Carvalho, James Edgell, Martin Ku, Wm. Matthew Kennedy","submitted_at":"2026-07-09T18:02:55Z","abstract_excerpt":"Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08842","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/2607.08842/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":"2607.08842","created_at":"2026-07-13T00:17:21.466698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08842v1","created_at":"2026-07-13T00:17:21.466698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08842","created_at":"2026-07-13T00:17:21.466698+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBPQIA4IOS3C","created_at":"2026-07-13T00:17:21.466698+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBPQIA4IOS3CZ3ES","created_at":"2026-07-13T00:17:21.466698+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBPQIA4I","created_at":"2026-07-13T00:17:21.466698+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/DBPQIA4IOS3CZ3ES7GHPS67BQF","json":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF.json","graph_json":"https://pith.science/api/pith-number/DBPQIA4IOS3CZ3ES7GHPS67BQF/graph.json","events_json":"https://pith.science/api/pith-number/DBPQIA4IOS3CZ3ES7GHPS67BQF/events.json","paper":"https://pith.science/paper/DBPQIA4I"},"agent_actions":{"view_html":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF","download_json":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF.json","view_paper":"https://pith.science/paper/DBPQIA4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08842&json=true","fetch_graph":"https://pith.science/api/pith-number/DBPQIA4IOS3CZ3ES7GHPS67BQF/graph.json","fetch_events":"https://pith.science/api/pith-number/DBPQIA4IOS3CZ3ES7GHPS67BQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF/action/storage_attestation","attest_author":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF/action/author_attestation","sign_citation":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF/action/citation_signature","submit_replication":"https://pith.science/pith/DBPQIA4IOS3CZ3ES7GHPS67BQF/action/replication_record"}},"created_at":"2026-07-13T00:17:21.466698+00:00","updated_at":"2026-07-13T00:17:21.466698+00:00"}