{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:26UHL2JBEMBAVGROWFUUFZKD62","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":"026227e7195097a99157ae9ecaae6926593365b5d4dcb3524d6c02fc0b56e499","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T11:17:07Z","title_canon_sha256":"11a46db1b4825b146af6dfb7ca82899c13c9e707fbee4b1695e1915f87467d78"},"schema_version":"1.0","source":{"id":"2005.02068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02068","created_at":"2026-07-05T01:00:22Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02068v1","created_at":"2026-07-05T01:00:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02068","created_at":"2026-07-05T01:00:22Z"},{"alias_kind":"pith_short_12","alias_value":"26UHL2JBEMBA","created_at":"2026-07-05T01:00:22Z"},{"alias_kind":"pith_short_16","alias_value":"26UHL2JBEMBAVGRO","created_at":"2026-07-05T01:00:22Z"},{"alias_kind":"pith_short_8","alias_value":"26UHL2JB","created_at":"2026-07-05T01:00:22Z"}],"graph_snapshots":[{"event_id":"sha256:e1492ee7cd2d8bdb3764be5103569585145ff63da4352048d807e17bc1d7144a","target":"graph","created_at":"2026-07-05T01:00:22Z","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/2005.02068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While transformer-based finetuning techniques have proven effective in tasks that involve low-resource, low-data environments, a lack of properly established baselines and benchmark datasets make it hard to compare different approaches that are aimed at tackling the low-resource setting. In this work, we provide three contributions. First, we introduce two previously unreleased datasets as benchmark datasets for text classification and low-resource multilabel text classification for the low-resource language Filipino. Second, we pretrain better BERT and DistilBERT models for use within the Fil","authors_text":"Charibeth Cheng, Jan Christian Blaise Cruz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T11:17:07Z","title":"Establishing Baselines for Text Classification in Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02068","kind":"arxiv","version":1},"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:e06b4dd805646bc9fe9417ef3c09ef2f58ac15f13dad3d20ffe88fa445cebb92","target":"record","created_at":"2026-07-05T01:00:22Z","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":"026227e7195097a99157ae9ecaae6926593365b5d4dcb3524d6c02fc0b56e499","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T11:17:07Z","title_canon_sha256":"11a46db1b4825b146af6dfb7ca82899c13c9e707fbee4b1695e1915f87467d78"},"schema_version":"1.0","source":{"id":"2005.02068","kind":"arxiv","version":1}},"canonical_sha256":"d7a875e92123020a9a2eb16942e543f6aad5bf784e062ce20beed0c05739b279","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7a875e92123020a9a2eb16942e543f6aad5bf784e062ce20beed0c05739b279","first_computed_at":"2026-07-05T01:00:22.123391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:22.123391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s9OGLVvc6w+w+2ay6f1TTAm5MAJv1LvLyF+caOq6SGgRdNE0HPSjWPrREDlFArE8OceeSJH0YlNcCBW86gOODw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:22.123769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.02068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e06b4dd805646bc9fe9417ef3c09ef2f58ac15f13dad3d20ffe88fa445cebb92","sha256:e1492ee7cd2d8bdb3764be5103569585145ff63da4352048d807e17bc1d7144a"],"state_sha256":"8795b75dc14049e7754d012963a55b8aecc41fbc2451dd568de4efde9ca53e77"}