{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IQPNJNQKQD2BHVVGDETURSLOKO","short_pith_number":"pith:IQPNJNQK","canonical_record":{"source":{"id":"2011.04784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T21:33:53Z","cross_cats_sorted":[],"title_canon_sha256":"107ef1338289e8b2ed898d9fbb3b83a4457530956a243a4d78f4dcf443d995a0","abstract_canon_sha256":"ad71ee368cc144d36be38aa8e6875aa6d57fb86737d3d5bfe34438abce103885"},"schema_version":"1.0"},"canonical_sha256":"441ed4b60a80f413d6a6192748c96e53a7099862f00c35898c0f73dd63d8d91c","source":{"kind":"arxiv","id":"2011.04784","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04784","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04784v3","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04784","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"IQPNJNQKQD2B","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"IQPNJNQKQD2BHVVG","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"IQPNJNQK","created_at":"2026-07-05T02:35:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IQPNJNQKQD2BHVVGDETURSLOKO","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T21:33:53Z","cross_cats_sorted":[],"title_canon_sha256":"107ef1338289e8b2ed898d9fbb3b83a4457530956a243a4d78f4dcf443d995a0","abstract_canon_sha256":"ad71ee368cc144d36be38aa8e6875aa6d57fb86737d3d5bfe34438abce103885"},"schema_version":"1.0"},"canonical_sha256":"441ed4b60a80f413d6a6192748c96e53a7099862f00c35898c0f73dd63d8d91c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:51.813595Z","signature_b64":"IxQtVEId9UcsH3wTRLfOf8Elo4JpjaCQaUQN9QVLKpSGgy395n9ZoCHyA8C3r43nqKzuJ1vhptmdn08MuR2EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"441ed4b60a80f413d6a6192748c96e53a7099862f00c35898c0f73dd63d8d91c","last_reissued_at":"2026-07-05T02:35:51.813144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:51.813144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04784","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FcqugRJW+mIybrXk6zbTpBIF6bBNOJounkoszw0uAJ0FRbEWstkEyEr5oo2ru9+q/Hlf0b6tx5sM7zH2aHg5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:17:20.926876Z"},"content_sha256":"29aa30eb959c46b2c98cf2c3516a8e123ef598c5c1c2fc91d020e6bb28f7762f","schema_version":"1.0","event_id":"sha256:29aa30eb959c46b2c98cf2c3516a8e123ef598c5c1c2fc91d020e6bb28f7762f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IQPNJNQKQD2BHVVGDETURSLOKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EstBERT: A Pretrained Language-Specific BERT for Estonian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claudia Kittask, Hasan Tanvir, Kairit Sirts, Sandra Eiche","submitted_at":"2020-11-09T21:33:53Z","abstract_excerpt":"This paper presents EstBERT, a large pretrained transformer-based language-specific BERT model for Estonian. Recent work has evaluated multilingual BERT models on Estonian tasks and found them to outperform the baselines. Still, based on existing studies on other languages, a language-specific BERT model is expected to improve over the multilingual ones. We first describe the EstBERT pretraining process and then present the results of the models based on finetuned EstBERT for multiple NLP tasks, including POS and morphological tagging, named entity recognition and text classification. The eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04784","kind":"arxiv","version":3},"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/2011.04784/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":"2026-07-05T02:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zAeIMX2iieE2WCSRRuwTyMZQb9jYvqKfX1KhnpwbG6YqzaIMGdIL3qdBEWld6xnhl0rRxhG/+JHEP6AzsqsBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:17:20.927584Z"},"content_sha256":"7e79074d57edb89eba85487a886c7459ebb0d8a8ebfce825609f92d3671ae2ac","schema_version":"1.0","event_id":"sha256:7e79074d57edb89eba85487a886c7459ebb0d8a8ebfce825609f92d3671ae2ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQPNJNQKQD2BHVVGDETURSLOKO/bundle.json","state_url":"https://pith.science/pith/IQPNJNQKQD2BHVVGDETURSLOKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQPNJNQKQD2BHVVGDETURSLOKO/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":"2026-08-13T21:17:20Z","links":{"resolver":"https://pith.science/pith/IQPNJNQKQD2BHVVGDETURSLOKO","bundle":"https://pith.science/pith/IQPNJNQKQD2BHVVGDETURSLOKO/bundle.json","state":"https://pith.science/pith/IQPNJNQKQD2BHVVGDETURSLOKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQPNJNQKQD2BHVVGDETURSLOKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IQPNJNQKQD2BHVVGDETURSLOKO","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":"ad71ee368cc144d36be38aa8e6875aa6d57fb86737d3d5bfe34438abce103885","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T21:33:53Z","title_canon_sha256":"107ef1338289e8b2ed898d9fbb3b83a4457530956a243a4d78f4dcf443d995a0"},"schema_version":"1.0","source":{"id":"2011.04784","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04784","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04784v3","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04784","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"IQPNJNQKQD2B","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"IQPNJNQKQD2BHVVG","created_at":"2026-07-05T02:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"IQPNJNQK","created_at":"2026-07-05T02:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:7e79074d57edb89eba85487a886c7459ebb0d8a8ebfce825609f92d3671ae2ac","target":"graph","created_at":"2026-07-05T02:35:51Z","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/2011.04784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents EstBERT, a large pretrained transformer-based language-specific BERT model for Estonian. Recent work has evaluated multilingual BERT models on Estonian tasks and found them to outperform the baselines. Still, based on existing studies on other languages, a language-specific BERT model is expected to improve over the multilingual ones. We first describe the EstBERT pretraining process and then present the results of the models based on finetuned EstBERT for multiple NLP tasks, including POS and morphological tagging, named entity recognition and text classification. The eval","authors_text":"Claudia Kittask, Hasan Tanvir, Kairit Sirts, Sandra Eiche","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T21:33:53Z","title":"EstBERT: A Pretrained Language-Specific BERT for Estonian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04784","kind":"arxiv","version":3},"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":"sha256:29aa30eb959c46b2c98cf2c3516a8e123ef598c5c1c2fc91d020e6bb28f7762f","target":"record","created_at":"2026-07-05T02:35:51Z","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":"ad71ee368cc144d36be38aa8e6875aa6d57fb86737d3d5bfe34438abce103885","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T21:33:53Z","title_canon_sha256":"107ef1338289e8b2ed898d9fbb3b83a4457530956a243a4d78f4dcf443d995a0"},"schema_version":"1.0","source":{"id":"2011.04784","kind":"arxiv","version":3}},"canonical_sha256":"441ed4b60a80f413d6a6192748c96e53a7099862f00c35898c0f73dd63d8d91c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"441ed4b60a80f413d6a6192748c96e53a7099862f00c35898c0f73dd63d8d91c","first_computed_at":"2026-07-05T02:35:51.813144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:35:51.813144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IxQtVEId9UcsH3wTRLfOf8Elo4JpjaCQaUQN9QVLKpSGgy395n9ZoCHyA8C3r43nqKzuJ1vhptmdn08MuR2EDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:35:51.813595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04784","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29aa30eb959c46b2c98cf2c3516a8e123ef598c5c1c2fc91d020e6bb28f7762f","sha256:7e79074d57edb89eba85487a886c7459ebb0d8a8ebfce825609f92d3671ae2ac"],"state_sha256":"61060c07e042c875ab58294c56e451ed7178b6d57ebfc22ed52d7c60cbe72454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrA66iDWSZ+WSAjJXzfB32CxBvy13f2f4/ZjNuxi74FClHrTzoi4Vur9rJo5BzV06+IKhBQCcGw+4OMeu1lpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:17:20.941614Z","bundle_sha256":"0b8e63f74a0e88471d7682559e3fd5de6b771920ae42fe3bfb673544b5ce1c20"}}