{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PIHAU6DB3V2IV4VHGP542HAZ3O","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":"a5fbdb4d34bc1673e34c09ed8c51c516115995ef410e0d08846db50de9f18f1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T14:47:10Z","title_canon_sha256":"e12a12ecb922b149734126da4a010448d14fd7a5c53c91592d091795de735d05"},"schema_version":"1.0","source":{"id":"2411.15577","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15577","created_at":"2026-07-05T09:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15577v2","created_at":"2026-07-05T09:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15577","created_at":"2026-07-05T09:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"PIHAU6DB3V2I","created_at":"2026-07-05T09:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"PIHAU6DB3V2IV4VH","created_at":"2026-07-05T09:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"PIHAU6DB","created_at":"2026-07-05T09:54:29Z"}],"graph_snapshots":[{"event_id":"sha256:aebeb8a151e89e35c3b901d2d245bbf07a629119ce683f1b8c05716908713591","target":"graph","created_at":"2026-07-05T09:54:29Z","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/2411.15577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language modeling have demonstrated significant improvements in zero-shot capabilities, including in-context learning, instruction following, and machine translation for extremely under-resourced languages (Tanzer et al., 2024). However, many languages with limited written resources rely primarily on formal descriptions of grammar and vocabulary.\n  In this paper, we introduce a set of benchmarks to evaluate how well models can extract and classify information from the complex descriptions found in linguistic grammars. We present a Retrieval-Augmented Generation (RAG)-based a","authors_text":"Albert Kornilov, Tatiana Shavrina","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T14:47:10Z","title":"From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15577","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":"sha256:430c411315034e53d319ab6e00b1e57dc865fff42dbbfaf4a3b0d6b488dc7ead","target":"record","created_at":"2026-07-05T09:54:29Z","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":"a5fbdb4d34bc1673e34c09ed8c51c516115995ef410e0d08846db50de9f18f1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T14:47:10Z","title_canon_sha256":"e12a12ecb922b149734126da4a010448d14fd7a5c53c91592d091795de735d05"},"schema_version":"1.0","source":{"id":"2411.15577","kind":"arxiv","version":2}},"canonical_sha256":"7a0e0a7861dd748af2a733fbcd1c19db802b9ea9115fa3e67edea6537c24ae23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a0e0a7861dd748af2a733fbcd1c19db802b9ea9115fa3e67edea6537c24ae23","first_computed_at":"2026-07-05T09:54:29.823342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:29.823342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"smxHAhtBlYAl0mSCZHcH6ZuUPZPyfzDAteDpJ/0mEmw2nmK9yELn0E13r6u3w3XVF4vSuLFZzZBnnT8Obc7CAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:29.823836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15577","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:430c411315034e53d319ab6e00b1e57dc865fff42dbbfaf4a3b0d6b488dc7ead","sha256:aebeb8a151e89e35c3b901d2d245bbf07a629119ce683f1b8c05716908713591"],"state_sha256":"e30857440070e332350303647537b6732d2061b9378079554959fffeb2f06e2a"}