{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FWIPWPAMJMQETSRCZNTI7BOJ5M","short_pith_number":"pith:FWIPWPAM","canonical_record":{"source":{"id":"2104.03767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"e5806f5ab44e5e0bcc713ace3cb94cc252acd98a6338763f7d29a70bb768aac4","abstract_canon_sha256":"b7d63239c54a5c319a806cfcbd467d46f3f526ff58b7777f199e3c19876ff0da"},"schema_version":"1.0"},"canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","source":{"kind":"arxiv","id":"2104.03767","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03767","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03767v2","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03767","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_12","alias_value":"FWIPWPAMJMQE","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_16","alias_value":"FWIPWPAMJMQETSRC","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_8","alias_value":"FWIPWPAM","created_at":"2026-07-05T02:30:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FWIPWPAMJMQETSRCZNTI7BOJ5M","target":"record","payload":{"canonical_record":{"source":{"id":"2104.03767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"e5806f5ab44e5e0bcc713ace3cb94cc252acd98a6338763f7d29a70bb768aac4","abstract_canon_sha256":"b7d63239c54a5c319a806cfcbd467d46f3f526ff58b7777f199e3c19876ff0da"},"schema_version":"1.0"},"canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:33.217287Z","signature_b64":"Ce/i8YMCWpxRHq2vHYZ0Q8d5NadGVlXHvCWM2xaeu8FeFH2N1IdP0Ga/h/KjshTihDj9IRDFaOhXQRGoZSckBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","last_reissued_at":"2026-07-05T02:30:33.216830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:33.216830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.03767","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:30:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzoN5NcrdPjuZZTT1VCiH3fWNscqlTrxYhfqIIPrEBNr870zLqn2J+LZKKl3O0MXqYRWy+cl2rktJYQ90Y2TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:11:48.321197Z"},"content_sha256":"c2b9533b7aa183b4800806ee2ed8dd9a12d272a253ae5c48f89c5aa1ecaa5f0c","schema_version":"1.0","event_id":"sha256:c2b9533b7aa183b4800806ee2ed8dd9a12d272a253ae5c48f89c5aa1ecaa5f0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FWIPWPAMJMQETSRCZNTI7BOJ5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiling You, Sara Stymne, Xingran Zhu","submitted_at":"2021-04-08T13:40:41Z","abstract_excerpt":"We describe the Uppsala NLP submission to SemEval-2021 Task 2 on multilingual and cross-lingual word-in-context disambiguation. We explore the usefulness of three pre-trained multilingual language models, XLM-RoBERTa (XLMR), Multilingual BERT (mBERT) and multilingual distilled BERT (mDistilBERT). We compare these three models in two setups, fine-tuning and as feature extractors. In the second case we also experiment with using dependency-based information. We find that fine-tuning is better than feature extraction. XLMR performs better than mBERT in the cross-lingual setting both with fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03767","kind":"arxiv","version":2},"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/2104.03767/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":"2026-07-05T02:30:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/xfIQpkb6XmgbbbM5Lpxtit1DrsAMzwjLfAb/tE75O1fGMvxYzG139EdD0AyMzQa52cmZu+qjB4HDk5zx9xAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:11:48.321706Z"},"content_sha256":"85baee141c25d75bdb85ccd7ea10294c431f06ef0f52401a05e5798203bc62a3","schema_version":"1.0","event_id":"sha256:85baee141c25d75bdb85ccd7ea10294c431f06ef0f52401a05e5798203bc62a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/bundle.json","state_url":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/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":"2026-08-10T23:11:48Z","links":{"resolver":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M","bundle":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/bundle.json","state":"https://pith.science/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWIPWPAMJMQETSRCZNTI7BOJ5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FWIPWPAMJMQETSRCZNTI7BOJ5M","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":"b7d63239c54a5c319a806cfcbd467d46f3f526ff58b7777f199e3c19876ff0da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","title_canon_sha256":"e5806f5ab44e5e0bcc713ace3cb94cc252acd98a6338763f7d29a70bb768aac4"},"schema_version":"1.0","source":{"id":"2104.03767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03767","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03767v2","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03767","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_12","alias_value":"FWIPWPAMJMQE","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_16","alias_value":"FWIPWPAMJMQETSRC","created_at":"2026-07-05T02:30:33Z"},{"alias_kind":"pith_short_8","alias_value":"FWIPWPAM","created_at":"2026-07-05T02:30:33Z"}],"graph_snapshots":[{"event_id":"sha256:85baee141c25d75bdb85ccd7ea10294c431f06ef0f52401a05e5798203bc62a3","target":"graph","created_at":"2026-07-05T02:30:33Z","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/2104.03767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe the Uppsala NLP submission to SemEval-2021 Task 2 on multilingual and cross-lingual word-in-context disambiguation. We explore the usefulness of three pre-trained multilingual language models, XLM-RoBERTa (XLMR), Multilingual BERT (mBERT) and multilingual distilled BERT (mDistilBERT). We compare these three models in two setups, fine-tuning and as feature extractors. In the second case we also experiment with using dependency-based information. We find that fine-tuning is better than feature extraction. XLMR performs better than mBERT in the cross-lingual setting both with fine-tun","authors_text":"Huiling You, Sara Stymne, Xingran Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03767","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:c2b9533b7aa183b4800806ee2ed8dd9a12d272a253ae5c48f89c5aa1ecaa5f0c","target":"record","created_at":"2026-07-05T02:30:33Z","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":"b7d63239c54a5c319a806cfcbd467d46f3f526ff58b7777f199e3c19876ff0da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:40:41Z","title_canon_sha256":"e5806f5ab44e5e0bcc713ace3cb94cc252acd98a6338763f7d29a70bb768aac4"},"schema_version":"1.0","source":{"id":"2104.03767","kind":"arxiv","version":2}},"canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d90fb3c0c4b2049ca22cb668f85c9eb265d000d6d1b639c4897fc6a308f300c","first_computed_at":"2026-07-05T02:30:33.216830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:33.216830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ce/i8YMCWpxRHq2vHYZ0Q8d5NadGVlXHvCWM2xaeu8FeFH2N1IdP0Ga/h/KjshTihDj9IRDFaOhXQRGoZSckBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:33.217287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.03767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2b9533b7aa183b4800806ee2ed8dd9a12d272a253ae5c48f89c5aa1ecaa5f0c","sha256:85baee141c25d75bdb85ccd7ea10294c431f06ef0f52401a05e5798203bc62a3"],"state_sha256":"da67634f7eb6813969fa198442002e9a3dd4127a7ba1063ed4a380e5430c7262"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6lSZnD97UjhBvz9y93bISYUMs6WR7QEroHwCuz8x7ekVlRqBbuStKjf5ENQl8M/45ACMIIY/EZEpXvbrExVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:11:48.326314Z","bundle_sha256":"595657c0a9b6f2ad8cf133809a1edebfe46f929422cbedd38c41a3aea822b21e"}}