{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZX4LCNNBPMM7KTJX5KEVLRLLBD","short_pith_number":"pith:ZX4LCNNB","schema_version":"1.0","canonical_sha256":"cdf8b135a17b19f54d37ea8955c56b08e2cc6c52fc25fac564ce38fdb88ba9e2","source":{"kind":"arxiv","id":"2604.26145","version":2},"attestation_state":"computed","paper":{"title":"Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"AI explanations in language learning tools often look helpful but contain flaws that can reinforce errors and erode trust.","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Ben Knight, Danielle Carvalho, Isaac Pattis, James Edgell, Wm. Matthew Kennedy","submitted_at":"2026-04-28T22:05:57Z","abstract_excerpt":"AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over extended use. We present a portion of L2-Bench, a benchmark for evaluating AI systems in language education that includes (but is not limited to) six critical dimensions of effective feedback: diagnostic accuracy, awareness of appropriacy, causes of error, prioritisation, guidance for improvement, an"},"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":"2604.26145","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2026-04-28T22:05:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ba3ad451811049a1eb4384fe644ca2e1dd7df86f1ff4d9cb90bb9ba23c0cf75","abstract_canon_sha256":"7a82e490e5ec65047113eefab395c41d5d81de227ccad0c8c964e067d90dfe72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:15.860996Z","signature_b64":"Ju+g4HnJYCmIDBU3wjauE76EvRQ1tqShFTBhLiDbC9ZKdmXnyEUIQ0Q1cbd6uLSDYwQxvGyRQt5f080X0zAeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf8b135a17b19f54d37ea8955c56b08e2cc6c52fc25fac564ce38fdb88ba9e2","last_reissued_at":"2026-05-25T02:02:15.860230Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:15.860230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"AI explanations in language learning tools often look helpful but contain flaws that can reinforce errors and erode trust.","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Ben Knight, Danielle Carvalho, Isaac Pattis, James Edgell, Wm. Matthew Kennedy","submitted_at":"2026-04-28T22:05:57Z","abstract_excerpt":"AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over extended use. We present a portion of L2-Bench, a benchmark for evaluating AI systems in language education that includes (but is not limited to) six critical dimensions of effective feedback: diagnostic accuracy, awareness of appropriacy, causes of error, prioritisation, guidance for improvement, an"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AI-generated explanations that appear helpful on the surface but are fundamentally flawed, increasing the risk of attainment, human-AI interaction, and socioaffective harms.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the six listed dimensions capture the critical failure modes and that the resulting pitfalls actually produce the claimed harms in real learner interactions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AI explanations in language learning often fail across six dimensions like diagnostic accuracy and self-regulation support, creating hidden risks that demand better evaluation frameworks such as L2-Bench.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AI explanations in language learning tools often look helpful but contain flaws that can reinforce errors and erode trust.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"df0a42c108a59b7b047251f0a6874af7356749724b1f00fcc9b7dd34af37dab4"},"source":{"id":"2604.26145","kind":"arxiv","version":2},"verdict":{"id":"38193017-0bed-43c4-bf79-af4c2e3a4a00","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T15:05:15.251367Z","strongest_claim":"AI-generated explanations that appear helpful on the surface but are fundamentally flawed, increasing the risk of attainment, human-AI interaction, and socioaffective harms.","one_line_summary":"AI explanations in language learning often fail across six dimensions like diagnostic accuracy and self-regulation support, creating hidden risks that demand better evaluation frameworks such as L2-Bench.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the six listed dimensions capture the critical failure modes and that the resulting pitfalls actually produce the claimed harms in real learner interactions.","pith_extraction_headline":"AI explanations in language learning tools often look helpful but contain flaws that can reinforce errors and erode trust."},"integrity":{"clean":false,"summary":{"advisory":0,"critical":1,"by_detector":{"doi_compliance":{"total":1,"advisory":0,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2604.26145/integrity.json","findings":[{"note":"Identifier '10.1007/s00146-023-01753-4' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","detector":"doi_compliance","severity":"critical","ref_index":31,"audited_at":"2026-05-19T20:26:45.548676Z","detected_doi":"10.1007/s00146-023-01753-4","finding_type":"unresolvable_identifier","verdict_class":"cross_source","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T03:34:18.519966Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:26:45.548676Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"8580a2a05a20619e57efcf17217b415a22daa23f944bcca0e61cc20d777e3b65"},"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":"2604.26145","created_at":"2026-05-25T02:02:15.860339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.26145v2","created_at":"2026-05-25T02:02:15.860339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26145","created_at":"2026-05-25T02:02:15.860339+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX4LCNNBPMM7","created_at":"2026-05-25T02:02:15.860339+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX4LCNNBPMM7KTJX","created_at":"2026-05-25T02:02:15.860339+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX4LCNNB","created_at":"2026-05-25T02:02:15.860339+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/ZX4LCNNBPMM7KTJX5KEVLRLLBD","json":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD.json","graph_json":"https://pith.science/api/pith-number/ZX4LCNNBPMM7KTJX5KEVLRLLBD/graph.json","events_json":"https://pith.science/api/pith-number/ZX4LCNNBPMM7KTJX5KEVLRLLBD/events.json","paper":"https://pith.science/paper/ZX4LCNNB"},"agent_actions":{"view_html":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD","download_json":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD.json","view_paper":"https://pith.science/paper/ZX4LCNNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.26145&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX4LCNNBPMM7KTJX5KEVLRLLBD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX4LCNNBPMM7KTJX5KEVLRLLBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD/action/storage_attestation","attest_author":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD/action/author_attestation","sign_citation":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD/action/citation_signature","submit_replication":"https://pith.science/pith/ZX4LCNNBPMM7KTJX5KEVLRLLBD/action/replication_record"}},"created_at":"2026-05-25T02:02:15.860339+00:00","updated_at":"2026-05-25T02:02:15.860339+00:00"}