{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DAF436ATFSBHSRMI7SNZBYSKC7","short_pith_number":"pith:DAF436AT","canonical_record":{"source":{"id":"1805.10267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T17:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"e54c1e17f98a642262bb39003d8dcb3e167a034f427e95ce49e1165546e178ae","abstract_canon_sha256":"c98949fac625a3e5c1f9c7743d98a7453b88c2e364516d880072b84dea946c1c"},"schema_version":"1.0"},"canonical_sha256":"180bcdf8132c82794588fc9b90e24a17e0fda58a69c212877adf92e1e6a00ced","source":{"kind":"arxiv","id":"1805.10267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10267","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10267v1","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10267","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DAF436ATFSBH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DAF436ATFSBHSRMI","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DAF436AT","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DAF436ATFSBHSRMI7SNZBYSKC7","target":"record","payload":{"canonical_record":{"source":{"id":"1805.10267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T17:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"e54c1e17f98a642262bb39003d8dcb3e167a034f427e95ce49e1165546e178ae","abstract_canon_sha256":"c98949fac625a3e5c1f9c7743d98a7453b88c2e364516d880072b84dea946c1c"},"schema_version":"1.0"},"canonical_sha256":"180bcdf8132c82794588fc9b90e24a17e0fda58a69c212877adf92e1e6a00ced","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:57.811557Z","signature_b64":"JbHVAkuU5wHYwC0+pyntl965K2ubFXlBKO2sZD4MpLEiOkbWkPdyxTKVMAi7ljkhuZkt2dxpfh/p45MDu/y3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"180bcdf8132c82794588fc9b90e24a17e0fda58a69c212877adf92e1e6a00ced","last_reissued_at":"2026-05-18T00:14:57.810862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:57.810862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.10267","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":"2026-05-18T00:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o87rzXia3sBW+Oloy/2kdMVRdlruqrkMe2IkDHFK4oEPybFITrQJjECVaIX+KiDZPt76Uo44QcQ4do8ICbSXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:29:50.481743Z"},"content_sha256":"a5145d51be342a2b3fc6b40891df362336dee570a0a292f21b9b3049cf1e3bdb","schema_version":"1.0","event_id":"sha256:a5145d51be342a2b3fc6b40891df362336dee570a0a292f21b9b3049cf1e3bdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DAF436ATFSBHSRMI7SNZBYSKC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Duluth UROP at SemEval-2018 Task 2: Multilingual Emoji Prediction with Ensemble Learning and Oversampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuning Jin, Ted Pedersen","submitted_at":"2018-05-25T17:36:51Z","abstract_excerpt":"This paper describes the Duluth UROP systems that participated in SemEval--2018 Task 2, Multilingual Emoji Prediction. We relied on a variety of ensembles made up of classifiers using Naive Bayes, Logistic Regression, and Random Forests. We used unigram and bigram features and tried to offset the skewness of the data through the use of oversampling. Our task evaluation results place us 19th of 48 systems in the English evaluation, and 5th of 21 in the Spanish. After the evaluation we realized that some simple changes to preprocessing could significantly improve our results. After making these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10267","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":""},"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":"2026-05-18T00:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xve20IWXV9jRQHSeDIBosxenvQGBWUqpt2S4TmwhX61qQse4yzmQevRAstgGy6kTxp0mWqQxxKsJbikNiMwSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:29:50.482302Z"},"content_sha256":"10203ab73818f4eaf2367eff3d09b0a501cf995fe7af1898c249683b22b01938","schema_version":"1.0","event_id":"sha256:10203ab73818f4eaf2367eff3d09b0a501cf995fe7af1898c249683b22b01938"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAF436ATFSBHSRMI7SNZBYSKC7/bundle.json","state_url":"https://pith.science/pith/DAF436ATFSBHSRMI7SNZBYSKC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAF436ATFSBHSRMI7SNZBYSKC7/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":"2026-05-29T20:29:50Z","links":{"resolver":"https://pith.science/pith/DAF436ATFSBHSRMI7SNZBYSKC7","bundle":"https://pith.science/pith/DAF436ATFSBHSRMI7SNZBYSKC7/bundle.json","state":"https://pith.science/pith/DAF436ATFSBHSRMI7SNZBYSKC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAF436ATFSBHSRMI7SNZBYSKC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DAF436ATFSBHSRMI7SNZBYSKC7","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":"c98949fac625a3e5c1f9c7743d98a7453b88c2e364516d880072b84dea946c1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T17:36:51Z","title_canon_sha256":"e54c1e17f98a642262bb39003d8dcb3e167a034f427e95ce49e1165546e178ae"},"schema_version":"1.0","source":{"id":"1805.10267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10267","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10267v1","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10267","created_at":"2026-05-18T00:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DAF436ATFSBH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DAF436ATFSBHSRMI","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DAF436AT","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:10203ab73818f4eaf2367eff3d09b0a501cf995fe7af1898c249683b22b01938","target":"graph","created_at":"2026-05-18T00:14:57Z","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"},"paper":{"abstract_excerpt":"This paper describes the Duluth UROP systems that participated in SemEval--2018 Task 2, Multilingual Emoji Prediction. We relied on a variety of ensembles made up of classifiers using Naive Bayes, Logistic Regression, and Random Forests. We used unigram and bigram features and tried to offset the skewness of the data through the use of oversampling. Our task evaluation results place us 19th of 48 systems in the English evaluation, and 5th of 21 in the Spanish. After the evaluation we realized that some simple changes to preprocessing could significantly improve our results. After making these ","authors_text":"Shuning Jin, Ted Pedersen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T17:36:51Z","title":"Duluth UROP at SemEval-2018 Task 2: Multilingual Emoji Prediction with Ensemble Learning and Oversampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10267","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:a5145d51be342a2b3fc6b40891df362336dee570a0a292f21b9b3049cf1e3bdb","target":"record","created_at":"2026-05-18T00:14:57Z","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":"c98949fac625a3e5c1f9c7743d98a7453b88c2e364516d880072b84dea946c1c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T17:36:51Z","title_canon_sha256":"e54c1e17f98a642262bb39003d8dcb3e167a034f427e95ce49e1165546e178ae"},"schema_version":"1.0","source":{"id":"1805.10267","kind":"arxiv","version":1}},"canonical_sha256":"180bcdf8132c82794588fc9b90e24a17e0fda58a69c212877adf92e1e6a00ced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"180bcdf8132c82794588fc9b90e24a17e0fda58a69c212877adf92e1e6a00ced","first_computed_at":"2026-05-18T00:14:57.810862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:57.810862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JbHVAkuU5wHYwC0+pyntl965K2ubFXlBKO2sZD4MpLEiOkbWkPdyxTKVMAi7ljkhuZkt2dxpfh/p45MDu/y3DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:57.811557Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5145d51be342a2b3fc6b40891df362336dee570a0a292f21b9b3049cf1e3bdb","sha256:10203ab73818f4eaf2367eff3d09b0a501cf995fe7af1898c249683b22b01938"],"state_sha256":"283876f2b15cd19f1c5e736c9a1fc8e7c5dee35948c1f05a7aed0c9b96708a7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7v0Axg4fQi1GTT4s102Z3DxSiDDNjffnZZRumV+M1c3tg00FP8H8cOkYKY2MP4OzsUeEKHCDxtsFaD7SJwf7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:29:50.485133Z","bundle_sha256":"3673b9bdb3226befbead8be2afc88e2d2d7b7ef69139808d9cbf6599a0d4aaef"}}