{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4NMV2G5KNJ7IY3IVOV3NOF76BE","short_pith_number":"pith:4NMV2G5K","schema_version":"1.0","canonical_sha256":"e3595d1baa6a7e8c6d157576d717fe0910e5486b5a4fb68df8b03b10bd95f9c1","source":{"kind":"arxiv","id":"2505.16460","version":1},"attestation_state":"computed","paper":{"title":"University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alfan Farizki Wicaksono, Eduardus Tjitrahardja, Eryawan Presma Yulianrifat, Ikhlasul Akmal Hanif, Jaycent Gunawan Ongris, Muhammad Falensi Azmi, Rahmat Bryan Naufal","submitted_at":"2025-05-22T09:42:11Z","abstract_excerpt":"This paper presents our approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.16460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T09:42:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d90a40840839b4ff447bdb01d94a01a66601b7f2c29e36a4ace7300bf823eba1","abstract_canon_sha256":"cf9aab2bcdee009cfee0b6f72ce9e2983fa19d024955c31dc9d7feb38885f915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:35.941567Z","signature_b64":"uG/o85BU8OpHNstN86IMJTSkj246zu59OY7wJk5RHLUUXAPjA6Q9tSkduz9Nbx7JASarAcTHUUBz+xozUGBMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3595d1baa6a7e8c6d157576d717fe0910e5486b5a4fb68df8b03b10bd95f9c1","last_reissued_at":"2026-07-05T11:07:35.941064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:35.941064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alfan Farizki Wicaksono, Eduardus Tjitrahardja, Eryawan Presma Yulianrifat, Ikhlasul Akmal Hanif, Jaycent Gunawan Ongris, Muhammad Falensi Azmi, Rahmat Bryan Naufal","submitted_at":"2025-05-22T09:42:11Z","abstract_excerpt":"This paper presents our approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16460","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/2505.16460/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.16460","created_at":"2026-07-05T11:07:35.941123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16460v1","created_at":"2026-07-05T11:07:35.941123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16460","created_at":"2026-07-05T11:07:35.941123+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NMV2G5KNJ7I","created_at":"2026-07-05T11:07:35.941123+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NMV2G5KNJ7IY3IV","created_at":"2026-07-05T11:07:35.941123+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NMV2G5K","created_at":"2026-07-05T11:07:35.941123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE","json":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE.json","graph_json":"https://pith.science/api/pith-number/4NMV2G5KNJ7IY3IVOV3NOF76BE/graph.json","events_json":"https://pith.science/api/pith-number/4NMV2G5KNJ7IY3IVOV3NOF76BE/events.json","paper":"https://pith.science/paper/4NMV2G5K"},"agent_actions":{"view_html":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE","download_json":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE.json","view_paper":"https://pith.science/paper/4NMV2G5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16460&json=true","fetch_graph":"https://pith.science/api/pith-number/4NMV2G5KNJ7IY3IVOV3NOF76BE/graph.json","fetch_events":"https://pith.science/api/pith-number/4NMV2G5KNJ7IY3IVOV3NOF76BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE/action/storage_attestation","attest_author":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE/action/author_attestation","sign_citation":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE/action/citation_signature","submit_replication":"https://pith.science/pith/4NMV2G5KNJ7IY3IVOV3NOF76BE/action/replication_record"}},"created_at":"2026-07-05T11:07:35.941123+00:00","updated_at":"2026-07-05T11:07:35.941123+00:00"}