{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LN6ASXYTTDS3I7GZYNLUT2BYE7","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":"69c6b67a8a5931ac9db12a441e3869e52a834a85b43551121049942e2184bd2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T05:46:27Z","title_canon_sha256":"43561de21836869bc92e374d8202fe354cd1bd06e7c73189094a62ac50ae0b49"},"schema_version":"1.0","source":{"id":"2501.12660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12660","created_at":"2026-07-05T10:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12660v1","created_at":"2026-07-05T10:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12660","created_at":"2026-07-05T10:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"LN6ASXYTTDS3","created_at":"2026-07-05T10:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"LN6ASXYTTDS3I7GZ","created_at":"2026-07-05T10:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"LN6ASXYT","created_at":"2026-07-05T10:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:16f20f5ad1644407ebf02dfce3ee5d7c6f42058e6f7a166fa0d9ab7c8b0c3209","target":"graph","created_at":"2026-07-05T10:03:56Z","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/2501.12660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose the use of simple knowledge distillation to produce smaller and more efficient single-language transformers from Massively Multilingual Transformers (MMTs) to alleviate tradeoffs associated with the use of such in low-resource settings. Using Tagalog as a case study, we show that these smaller single-language models perform on-par with strong baselines in a variety of benchmark tasks in a much more efficient manner. Furthermore, we investigate additional steps during the distillation process that improves the soft-supervision of the target language, and provide a numb","authors_text":"Alham Fikri Aji, Jan Christian Blaise Cruz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T05:46:27Z","title":"Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12660","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":"sha256:8e269812fbe1d1ffadff00cd1019c21d57069c824170cca60a42f2640464bb2e","target":"record","created_at":"2026-07-05T10:03:56Z","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":"69c6b67a8a5931ac9db12a441e3869e52a834a85b43551121049942e2184bd2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T05:46:27Z","title_canon_sha256":"43561de21836869bc92e374d8202fe354cd1bd06e7c73189094a62ac50ae0b49"},"schema_version":"1.0","source":{"id":"2501.12660","kind":"arxiv","version":1}},"canonical_sha256":"5b7c095f1398e5b47cd9c35749e83827f357a8d5eb3247d04a96084472312099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b7c095f1398e5b47cd9c35749e83827f357a8d5eb3247d04a96084472312099","first_computed_at":"2026-07-05T10:03:56.559973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:56.559973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6IeKaQHjMqw3cvTK+S4R0L8XZqvIUxLLb+MSL0YMlZtloo0y1l+985zk414JUEUkBFCR+fU6n6wugXm87vQqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:56.560501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e269812fbe1d1ffadff00cd1019c21d57069c824170cca60a42f2640464bb2e","sha256:16f20f5ad1644407ebf02dfce3ee5d7c6f42058e6f7a166fa0d9ab7c8b0c3209"],"state_sha256":"f7b2858bb8b1e7b6e389f364128b03d89576b2c6c51c62c97f4f82e657612dcd"}