{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZGN6N5NX7SFBAXZICM7QNIKQIA","short_pith_number":"pith:ZGN6N5NX","schema_version":"1.0","canonical_sha256":"c99be6f5b7fc8a105f28133f06a150403cc44116e56b626fba835550b4de74b1","source":{"kind":"arxiv","id":"2412.10105","version":2},"attestation_state":"computed","paper":{"title":"MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiranthan Sridhar, George Arthur Baker, Katharina von der Wense, Lawrence E Hunter, Sagi Shaier","submitted_at":"2024-12-13T12:46:33Z","abstract_excerpt":"Language models (LMs) have excelled in various broad domains. However, to ensure their safe and effective integration into real-world educational settings, they must demonstrate proficiency in specific, granular areas of knowledge. Existing cloze-style benchmarks, commonly used to evaluate LMs' knowledge, have three major limitations. They: 1) do not cover the educational domain; 2) typically focus on low-complexity, generic knowledge or broad domains, which do not adequately assess the models' knowledge in specific subjects; and 3) often rely on templates that can bias model predictions. Here"},"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":"2412.10105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T12:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"9088af33d3a7e6d1144a1c30c75d41c6ca67881d3ab044a41446612edba338a6","abstract_canon_sha256":"452a95c262ecd8902f677b40b8214795daf94a4dc1a3c5d2f60c4f29b19702ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:05.236401Z","signature_b64":"OsvqOOqJMEs5vwhMaYW1I8Q+0OJsqH7rOFmETNNyjHb+XJyeJ9RFeecWM+zK+zv+BE3WfjMwMUWY+auXOOVaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99be6f5b7fc8a105f28133f06a150403cc44116e56b626fba835550b4de74b1","last_reissued_at":"2026-07-05T11:09:05.235909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:05.235909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiranthan Sridhar, George Arthur Baker, Katharina von der Wense, Lawrence E Hunter, Sagi Shaier","submitted_at":"2024-12-13T12:46:33Z","abstract_excerpt":"Language models (LMs) have excelled in various broad domains. However, to ensure their safe and effective integration into real-world educational settings, they must demonstrate proficiency in specific, granular areas of knowledge. Existing cloze-style benchmarks, commonly used to evaluate LMs' knowledge, have three major limitations. They: 1) do not cover the educational domain; 2) typically focus on low-complexity, generic knowledge or broad domains, which do not adequately assess the models' knowledge in specific subjects; and 3) often rely on templates that can bias model predictions. Here"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10105","kind":"arxiv","version":2},"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/2412.10105/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":"2412.10105","created_at":"2026-07-05T11:09:05.235967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10105v2","created_at":"2026-07-05T11:09:05.235967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10105","created_at":"2026-07-05T11:09:05.235967+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGN6N5NX7SFB","created_at":"2026-07-05T11:09:05.235967+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGN6N5NX7SFBAXZI","created_at":"2026-07-05T11:09:05.235967+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGN6N5NX","created_at":"2026-07-05T11:09:05.235967+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/ZGN6N5NX7SFBAXZICM7QNIKQIA","json":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA.json","graph_json":"https://pith.science/api/pith-number/ZGN6N5NX7SFBAXZICM7QNIKQIA/graph.json","events_json":"https://pith.science/api/pith-number/ZGN6N5NX7SFBAXZICM7QNIKQIA/events.json","paper":"https://pith.science/paper/ZGN6N5NX"},"agent_actions":{"view_html":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA","download_json":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA.json","view_paper":"https://pith.science/paper/ZGN6N5NX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10105&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGN6N5NX7SFBAXZICM7QNIKQIA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGN6N5NX7SFBAXZICM7QNIKQIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA/action/storage_attestation","attest_author":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA/action/author_attestation","sign_citation":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA/action/citation_signature","submit_replication":"https://pith.science/pith/ZGN6N5NX7SFBAXZICM7QNIKQIA/action/replication_record"}},"created_at":"2026-07-05T11:09:05.235967+00:00","updated_at":"2026-07-05T11:09:05.235967+00:00"}