{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIHAU6DB3V2IV4VHGP542HAZ3O","short_pith_number":"pith:PIHAU6DB","schema_version":"1.0","canonical_sha256":"7a0e0a7861dd748af2a733fbcd1c19db802b9ea9115fa3e67edea6537c24ae23","source":{"kind":"arxiv","id":"2411.15577","version":2},"attestation_state":"computed","paper":{"title":"From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Kornilov, Tatiana Shavrina","submitted_at":"2024-11-23T14:47:10Z","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"},"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":"2411.15577","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T14:47:10Z","cross_cats_sorted":[],"title_canon_sha256":"e12a12ecb922b149734126da4a010448d14fd7a5c53c91592d091795de735d05","abstract_canon_sha256":"a5fbdb4d34bc1673e34c09ed8c51c516115995ef410e0d08846db50de9f18f1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:29.823836Z","signature_b64":"smxHAhtBlYAl0mSCZHcH6ZuUPZPyfzDAteDpJ/0mEmw2nmK9yELn0E13r6u3w3XVF4vSuLFZzZBnnT8Obc7CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a0e0a7861dd748af2a733fbcd1c19db802b9ea9115fa3e67edea6537c24ae23","last_reissued_at":"2026-07-05T09:54:29.823342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:29.823342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Kornilov, Tatiana Shavrina","submitted_at":"2024-11-23T14:47:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15577","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/2411.15577/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":"2411.15577","created_at":"2026-07-05T09:54:29.823414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15577v2","created_at":"2026-07-05T09:54:29.823414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15577","created_at":"2026-07-05T09:54:29.823414+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIHAU6DB3V2I","created_at":"2026-07-05T09:54:29.823414+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIHAU6DB3V2IV4VH","created_at":"2026-07-05T09:54:29.823414+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIHAU6DB","created_at":"2026-07-05T09:54:29.823414+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/PIHAU6DB3V2IV4VHGP542HAZ3O","json":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O.json","graph_json":"https://pith.science/api/pith-number/PIHAU6DB3V2IV4VHGP542HAZ3O/graph.json","events_json":"https://pith.science/api/pith-number/PIHAU6DB3V2IV4VHGP542HAZ3O/events.json","paper":"https://pith.science/paper/PIHAU6DB"},"agent_actions":{"view_html":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O","download_json":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O.json","view_paper":"https://pith.science/paper/PIHAU6DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15577&json=true","fetch_graph":"https://pith.science/api/pith-number/PIHAU6DB3V2IV4VHGP542HAZ3O/graph.json","fetch_events":"https://pith.science/api/pith-number/PIHAU6DB3V2IV4VHGP542HAZ3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O/action/storage_attestation","attest_author":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O/action/author_attestation","sign_citation":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O/action/citation_signature","submit_replication":"https://pith.science/pith/PIHAU6DB3V2IV4VHGP542HAZ3O/action/replication_record"}},"created_at":"2026-07-05T09:54:29.823414+00:00","updated_at":"2026-07-05T09:54:29.823414+00:00"}