{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GA6TTCZLHIN6HTGPLDY5P7XTSU","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":"867eda0a753152c06cd958226f0fea74c3b682c92f370cc2fdb3bacd2ceee11e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T05:26:12Z","title_canon_sha256":"10c1e9153a918af2221de0ea3615ef61787550bda31f38b7f0f52131697de225"},"schema_version":"1.0","source":{"id":"2404.18071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18071","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18071v2","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18071","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"GA6TTCZLHIN6","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"GA6TTCZLHIN6HTGP","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"GA6TTCZL","created_at":"2026-07-05T11:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:1052bb9794a832ee35eeda4487c1289ad9cc5190940eb04a0c0ff36bb15cb58f","target":"graph","created_at":"2026-07-05T11:51:15Z","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/2404.18071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impact of subword tokenization on language model performance is well-documented for perplexity, with finer granularity consistently reducing this intrinsic metric. However, research on how different tokenization schemes affect a model's understanding capabilities remains limited, particularly for non-Latin script languages. Addressing this gap, we conducted a comprehensive evaluation of six distinct tokenization strategies by pretraining transformer-based language models for Nepali and evaluating their performance across multiple downstream tasks. While recent prominent models like GPT, Ro","authors_text":"Anand Kumar Sah, Nirajan Bekoju, Nishant Luitel, Subarna Shakya","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T05:26:12Z","title":"Can Perplexity Predict Fine-tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18071","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":"sha256:93eba5609096488dda06ff9416cf9b6b2a80af326cd0b47b474fdbcdedb5e0d6","target":"record","created_at":"2026-07-05T11:51:15Z","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":"867eda0a753152c06cd958226f0fea74c3b682c92f370cc2fdb3bacd2ceee11e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T05:26:12Z","title_canon_sha256":"10c1e9153a918af2221de0ea3615ef61787550bda31f38b7f0f52131697de225"},"schema_version":"1.0","source":{"id":"2404.18071","kind":"arxiv","version":2}},"canonical_sha256":"303d398b2b3a1be3cccf58f1d7fef39520af5519fca81e98981a26f5876c713a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"303d398b2b3a1be3cccf58f1d7fef39520af5519fca81e98981a26f5876c713a","first_computed_at":"2026-07-05T11:51:15.606062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:15.606062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2lrIigaw7JJ7OZ4tkhQPJyPUY05FbJdGjxvzQeGK3pytb50iwTUkAlicUuUZrqLuOcKn7urX9KHci0zoT7y2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:15.606636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93eba5609096488dda06ff9416cf9b6b2a80af326cd0b47b474fdbcdedb5e0d6","sha256:1052bb9794a832ee35eeda4487c1289ad9cc5190940eb04a0c0ff36bb15cb58f"],"state_sha256":"3c97bb110faab22899e17a5b42500e9a979e8a836d82d99db628f327502c709b"}