{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DBPQIA4IOS3CZ3ES7GHPS67BQF","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"24b39911c8b6c6e9b3a5f4fd298f7d5464cc6bfeafb882604d0a7e7f0ab9ca02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-09T18:02:55Z","title_canon_sha256":"95f1a3f4c1baf429005413034c34dacdd9c10d51123041917ad4b0d3468678d8"},"schema_version":"1.0","source":{"id":"2607.08842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08842","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08842v1","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08842","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"DBPQIA4IOS3C","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"DBPQIA4IOS3CZ3ES","created_at":"2026-07-13T00:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"DBPQIA4I","created_at":"2026-07-13T00:17:21Z"}],"graph_snapshots":[{"event_id":"sha256:42347c23a550955bc36707d30faea617b00d642f10571aefa31affe7196c73a3","target":"graph","created_at":"2026-07-13T00:17:21Z","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/2607.08842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ben Knight, Danielle Carvalho, James Edgell, Martin Ku, Wm. Matthew Kennedy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-09T18:02:55Z","title":"L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08842","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:a21579ffc310b04a82aab785d7645391ed76b423c9dd6f786a47b5d876707397","target":"record","created_at":"2026-07-13T00:17:21Z","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":"24b39911c8b6c6e9b3a5f4fd298f7d5464cc6bfeafb882604d0a7e7f0ab9ca02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-09T18:02:55Z","title_canon_sha256":"95f1a3f4c1baf429005413034c34dacdd9c10d51123041917ad4b0d3468678d8"},"schema_version":"1.0","source":{"id":"2607.08842","kind":"arxiv","version":1}},"canonical_sha256":"185f04038874b62cec92f98ef97be1814b2f25635dfa2886d54d802446f65714","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"185f04038874b62cec92f98ef97be1814b2f25635dfa2886d54d802446f65714","first_computed_at":"2026-07-13T00:17:21.466137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:21.466137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cB/vykwNOgyeRZ6EjKSWzg3u16pFAD596nj74SBw7yRKn/FVba5mKC4UzX+SCLn/um4nJDFlUpolC88FT1vrAw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:21.467220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08842","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:4d7ce05efb58a75efeb34d3a264272ee4ca6cfe439401ad610f86a12e72d2c7d","sha256:da56551d41698b066f24cb69df2f44c233ab6abf41005d9be94b9fbb3adbec3c"]}],"invalid_events":[],"applied_event_ids":["sha256:a21579ffc310b04a82aab785d7645391ed76b423c9dd6f786a47b5d876707397","sha256:42347c23a550955bc36707d30faea617b00d642f10571aefa31affe7196c73a3"],"state_sha256":"f095abcebfdda4479ff444534a6f29d0916e91098182013bd9eb8dcaa4b7c623"}