{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFETAE4S7XIJINTQ5S3DC5T4F7","short_pith_number":"pith:MFETAE4S","schema_version":"1.0","canonical_sha256":"6149301392fdd0943670ecb631767c2fe66e0cc832624e777df6099bc82af099","source":{"kind":"arxiv","id":"2502.14911","version":2},"attestation_state":"computed","paper":{"title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjanette Cayabyab, David Demitri Africa, Jann Railey Montalan, Jimson Paulo Layacan, Michael T. Lopez II, Richell Isaiah Flores, Theresa Denise Magsajo, William Chandra Tjhi","submitted_at":"2025-02-19T07:03:15Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated remarkable capabilities on widely benchmarked high-resource languages. However, linguistic nuances of under-resourced languages remain unexplored. We introduce Batayan, a holistic Filipino benchmark that systematically evaluates LLMs across three key natural language processing (NLP) competencies: understanding, reasoning, and generation. Batayan consolidates eight tasks, three of which have not existed prior for Filipino corpora, covering both Tagalog and code-switched Taglish utterances. Our rigorous, native-speaker-driven ada"},"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":"2502.14911","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T07:03:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30964b5f9be9c0e99b5e4769ae797c41fa0093adb232d979af829e5b887034a1","abstract_canon_sha256":"c9bcb1311ad2b4b8ac5baad37351c253226bc3676a31dee3e2fbb26b49613981"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:14.742032Z","signature_b64":"Jxf5MIID9b6+mfmwNeYnOiHAAAA/GneWdrATke9BlX5KeXgE2zEWL+vvoBaxX1uSBiCHluWx+NvRmBa4LShHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6149301392fdd0943670ecb631767c2fe66e0cc832624e777df6099bc82af099","last_reissued_at":"2026-07-05T11:24:14.741354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:14.741354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjanette Cayabyab, David Demitri Africa, Jann Railey Montalan, Jimson Paulo Layacan, Michael T. Lopez II, Richell Isaiah Flores, Theresa Denise Magsajo, William Chandra Tjhi","submitted_at":"2025-02-19T07:03:15Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated remarkable capabilities on widely benchmarked high-resource languages. However, linguistic nuances of under-resourced languages remain unexplored. We introduce Batayan, a holistic Filipino benchmark that systematically evaluates LLMs across three key natural language processing (NLP) competencies: understanding, reasoning, and generation. Batayan consolidates eight tasks, three of which have not existed prior for Filipino corpora, covering both Tagalog and code-switched Taglish utterances. Our rigorous, native-speaker-driven ada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14911","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/2502.14911/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":"2502.14911","created_at":"2026-07-05T11:24:14.741432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14911v2","created_at":"2026-07-05T11:24:14.741432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14911","created_at":"2026-07-05T11:24:14.741432+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFETAE4S7XIJ","created_at":"2026-07-05T11:24:14.741432+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFETAE4S7XIJINTQ","created_at":"2026-07-05T11:24:14.741432+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFETAE4S","created_at":"2026-07-05T11:24:14.741432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06065","citing_title":"KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7","json":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7.json","graph_json":"https://pith.science/api/pith-number/MFETAE4S7XIJINTQ5S3DC5T4F7/graph.json","events_json":"https://pith.science/api/pith-number/MFETAE4S7XIJINTQ5S3DC5T4F7/events.json","paper":"https://pith.science/paper/MFETAE4S"},"agent_actions":{"view_html":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7","download_json":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7.json","view_paper":"https://pith.science/paper/MFETAE4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14911&json=true","fetch_graph":"https://pith.science/api/pith-number/MFETAE4S7XIJINTQ5S3DC5T4F7/graph.json","fetch_events":"https://pith.science/api/pith-number/MFETAE4S7XIJINTQ5S3DC5T4F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7/action/storage_attestation","attest_author":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7/action/author_attestation","sign_citation":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7/action/citation_signature","submit_replication":"https://pith.science/pith/MFETAE4S7XIJINTQ5S3DC5T4F7/action/replication_record"}},"created_at":"2026-07-05T11:24:14.741432+00:00","updated_at":"2026-07-05T11:24:14.741432+00:00"}