{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGN6N5NX7SFBAXZICM7QNIKQIA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"452a95c262ecd8902f677b40b8214795daf94a4dc1a3c5d2f60c4f29b19702ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T12:46:33Z","title_canon_sha256":"9088af33d3a7e6d1144a1c30c75d41c6ca67881d3ab044a41446612edba338a6"},"schema_version":"1.0","source":{"id":"2412.10105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10105","created_at":"2026-07-05T11:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10105v2","created_at":"2026-07-05T11:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10105","created_at":"2026-07-05T11:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZGN6N5NX7SFB","created_at":"2026-07-05T11:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZGN6N5NX7SFBAXZI","created_at":"2026-07-05T11:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZGN6N5NX","created_at":"2026-07-05T11:09:05Z"}],"graph_snapshots":[{"event_id":"sha256:377b325320ab6f535c9086e9b592d53c584ae68bc8334d6d12a6f5496a79a3ae","target":"graph","created_at":"2026-07-05T11:09:05Z","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/2412.10105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chiranthan Sridhar, George Arthur Baker, Katharina von der Wense, Lawrence E Hunter, Sagi Shaier","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T12:46:33Z","title":"MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10105","kind":"arxiv","version":2},"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":"sha256:85d3b901ee109edff6bd1aaff98238bcd519beb87907b1c6eaf713a1b4a9d1f2","target":"record","created_at":"2026-07-05T11:09:05Z","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":"452a95c262ecd8902f677b40b8214795daf94a4dc1a3c5d2f60c4f29b19702ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T12:46:33Z","title_canon_sha256":"9088af33d3a7e6d1144a1c30c75d41c6ca67881d3ab044a41446612edba338a6"},"schema_version":"1.0","source":{"id":"2412.10105","kind":"arxiv","version":2}},"canonical_sha256":"c99be6f5b7fc8a105f28133f06a150403cc44116e56b626fba835550b4de74b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c99be6f5b7fc8a105f28133f06a150403cc44116e56b626fba835550b4de74b1","first_computed_at":"2026-07-05T11:09:05.235909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:05.235909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OsvqOOqJMEs5vwhMaYW1I8Q+0OJsqH7rOFmETNNyjHb+XJyeJ9RFeecWM+zK+zv+BE3WfjMwMUWY+auXOOVaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:05.236401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85d3b901ee109edff6bd1aaff98238bcd519beb87907b1c6eaf713a1b4a9d1f2","sha256:377b325320ab6f535c9086e9b592d53c584ae68bc8334d6d12a6f5496a79a3ae"],"state_sha256":"55f5590e9da2c1a3869c7c6d0fde0c7fa5001320aa6e3ee5627bd287f701acbb"}