{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4FOCGFXKLQ4MEUIKMQHW5EUIK7","short_pith_number":"pith:4FOCGFXK","canonical_record":{"source":{"id":"2501.02631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T19:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"954f84f95db6c79b6b17fba5750e0716c004a5f315ff4d128d6478e732f1bd78","abstract_canon_sha256":"52c25e1d75fe2168990a16d87e1dec29857bc72e92d8b1ceb882f2a6a3195a87"},"schema_version":"1.0"},"canonical_sha256":"e15c2316ea5c38c2510a640f6e928857c207482342b14266d024e386149982d8","source":{"kind":"arxiv","id":"2501.02631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02631","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02631v1","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02631","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_12","alias_value":"4FOCGFXKLQ4M","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_16","alias_value":"4FOCGFXKLQ4MEUIK","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_8","alias_value":"4FOCGFXK","created_at":"2026-07-05T09:57:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4FOCGFXKLQ4MEUIKMQHW5EUIK7","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T19:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"954f84f95db6c79b6b17fba5750e0716c004a5f315ff4d128d6478e732f1bd78","abstract_canon_sha256":"52c25e1d75fe2168990a16d87e1dec29857bc72e92d8b1ceb882f2a6a3195a87"},"schema_version":"1.0"},"canonical_sha256":"e15c2316ea5c38c2510a640f6e928857c207482342b14266d024e386149982d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:10.007521Z","signature_b64":"osOB1PIgLrTV8lwLhJUn6+FjdYgN0pv8Dl8e/qEaOrPe6SW9DJjWw7xIVZgDnKYog7cVWMBflxwBonboFbBoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e15c2316ea5c38c2510a640f6e928857c207482342b14266d024e386149982d8","last_reissued_at":"2026-07-05T09:57:10.007041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:10.007041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02631","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9Bfin3YYtgm6sYKv7wSZ/O2MHIT0V5rJQKqQmB873ZU1+yYXjj5iNMOso28zF7l53SgxYp1m5CmS1WESEDLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:57:45.998508Z"},"content_sha256":"2df394704cebbd0e36d0a95454b09a6093c70f451b2b0c6032402c7ba51e4cb6","schema_version":"1.0","event_id":"sha256:2df394704cebbd0e36d0a95454b09a6093c70f451b2b0c6032402c7ba51e4cb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4FOCGFXKLQ4MEUIKMQHW5EUIK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksei Dorkin, Kairit Sirts, Taido Purason","submitted_at":"2025-01-05T19:21:45Z","abstract_excerpt":"Adapting multilingual language models to specific languages can enhance both their efficiency and performance. In this study, we explore how modifying the vocabulary of a multilingual encoder model to better suit the Estonian language affects its downstream performance on the Named Entity Recognition (NER) task. The motivations for adjusting the vocabulary are twofold: practical benefits affecting the computational cost, such as reducing the input sequence length and the model size, and performance enhancements by tailoring the vocabulary to the particular language. We evaluate the effectivene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02631","kind":"arxiv","version":1},"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/2501.02631/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTEF1EGR0PM+tr0mlwKF5XG4q2MIBLSCXrrp9yYN8lqG0hIGFf6WRLuuRvmPnB/sCdVsY87HgdH9t/hd/wSRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:57:45.999162Z"},"content_sha256":"dd6640af58c6f6844aa1e6fa0e11c2e1bbe1f690da4e7ecb2c0f757a16b34025","schema_version":"1.0","event_id":"sha256:dd6640af58c6f6844aa1e6fa0e11c2e1bbe1f690da4e7ecb2c0f757a16b34025"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/bundle.json","state_url":"https://pith.science/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T12:57:46Z","links":{"resolver":"https://pith.science/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7","bundle":"https://pith.science/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/bundle.json","state":"https://pith.science/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FOCGFXKLQ4MEUIKMQHW5EUIK7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4FOCGFXKLQ4MEUIKMQHW5EUIK7","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":"52c25e1d75fe2168990a16d87e1dec29857bc72e92d8b1ceb882f2a6a3195a87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T19:21:45Z","title_canon_sha256":"954f84f95db6c79b6b17fba5750e0716c004a5f315ff4d128d6478e732f1bd78"},"schema_version":"1.0","source":{"id":"2501.02631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02631","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02631v1","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02631","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_12","alias_value":"4FOCGFXKLQ4M","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_16","alias_value":"4FOCGFXKLQ4MEUIK","created_at":"2026-07-05T09:57:10Z"},{"alias_kind":"pith_short_8","alias_value":"4FOCGFXK","created_at":"2026-07-05T09:57:10Z"}],"graph_snapshots":[{"event_id":"sha256:dd6640af58c6f6844aa1e6fa0e11c2e1bbe1f690da4e7ecb2c0f757a16b34025","target":"graph","created_at":"2026-07-05T09:57:10Z","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/2501.02631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting multilingual language models to specific languages can enhance both their efficiency and performance. In this study, we explore how modifying the vocabulary of a multilingual encoder model to better suit the Estonian language affects its downstream performance on the Named Entity Recognition (NER) task. The motivations for adjusting the vocabulary are twofold: practical benefits affecting the computational cost, such as reducing the input sequence length and the model size, and performance enhancements by tailoring the vocabulary to the particular language. We evaluate the effectivene","authors_text":"Aleksei Dorkin, Kairit Sirts, Taido Purason","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T19:21:45Z","title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02631","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":"sha256:2df394704cebbd0e36d0a95454b09a6093c70f451b2b0c6032402c7ba51e4cb6","target":"record","created_at":"2026-07-05T09:57:10Z","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":"52c25e1d75fe2168990a16d87e1dec29857bc72e92d8b1ceb882f2a6a3195a87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-05T19:21:45Z","title_canon_sha256":"954f84f95db6c79b6b17fba5750e0716c004a5f315ff4d128d6478e732f1bd78"},"schema_version":"1.0","source":{"id":"2501.02631","kind":"arxiv","version":1}},"canonical_sha256":"e15c2316ea5c38c2510a640f6e928857c207482342b14266d024e386149982d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e15c2316ea5c38c2510a640f6e928857c207482342b14266d024e386149982d8","first_computed_at":"2026-07-05T09:57:10.007041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:10.007041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"osOB1PIgLrTV8lwLhJUn6+FjdYgN0pv8Dl8e/qEaOrPe6SW9DJjWw7xIVZgDnKYog7cVWMBflxwBonboFbBoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:10.007521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2df394704cebbd0e36d0a95454b09a6093c70f451b2b0c6032402c7ba51e4cb6","sha256:dd6640af58c6f6844aa1e6fa0e11c2e1bbe1f690da4e7ecb2c0f757a16b34025"],"state_sha256":"8337e969f0692793135501f1cf8db78f58efc85b3769984958119a3863ecd351"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1W/Ok+iqrqcuIqv65ajo+XlerXH+G0TNZ4bVIznTfkt/FLBEW+Yu0Ai/zW7oszK+fpwPbwmSfsE6UyL/4XDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:57:46.004595Z","bundle_sha256":"7f562156aed979925ae0983d607fa4e4eae367b65c666dbb1084f500ba5b3e8c"}}