{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XWO4ZVOJFJDOXFC23ALQUM3EKG","short_pith_number":"pith:XWO4ZVOJ","schema_version":"1.0","canonical_sha256":"bd9dccd5c92a46eb945ad8170a33645198cf87998de563e487f8ad023a4ffc3c","source":{"kind":"arxiv","id":"2604.17134","version":2},"attestation_state":"computed","paper":{"title":"RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Aureliu Valentin Antonie, Cosmin-Mircea Croitoru, Dumitru-Clementin Cercel, Vlad Andrei Muntean","submitted_at":"2026-04-18T20:21:40Z","abstract_excerpt":"We present RoIt-XMASA, a multilingual dataset that extends the Cross-lingual Multi-domain Amazon Sentiment Analysis to Italian and Romanian, comprising 36,000 labeled reviews across three domains (books, movies, and music) and 202,141 unlabeled samples. To address cross-lingual and cross-domain challenges, we propose a multi-target adversarial training framework that employs loss reversal with meta-learned coefficients to dynamically balance sentiment discrimination with domain and language invariance. XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%."},"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":"2604.17134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-18T20:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"de8849f467388cc2efdbc3ed214273652d31abe765138d84ec7821532d6b5223","abstract_canon_sha256":"03721e9cb3f5d43b67f1ecc098f618eda6dd81d0059d59fe4cf26538b56d9400"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:15.409310Z","signature_b64":"UX7SOL5uQoMWgHQhGynZc5hmoZyGs2S4BLxvFjrUqwlo7A5CIhi6EU7oMHmgAJbiO5jtmceQ3r1TGKs9GpLhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd9dccd5c92a46eb945ad8170a33645198cf87998de563e487f8ad023a4ffc3c","last_reissued_at":"2026-05-25T02:02:15.408738Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:15.408738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Aureliu Valentin Antonie, Cosmin-Mircea Croitoru, Dumitru-Clementin Cercel, Vlad Andrei Muntean","submitted_at":"2026-04-18T20:21:40Z","abstract_excerpt":"We present RoIt-XMASA, a multilingual dataset that extends the Cross-lingual Multi-domain Amazon Sentiment Analysis to Italian and Romanian, comprising 36,000 labeled reviews across three domains (books, movies, and music) and 202,141 unlabeled samples. To address cross-lingual and cross-domain challenges, we propose a multi-target adversarial training framework that employs loss reversal with meta-learned coefficients to dynamically balance sentiment discrimination with domain and language invariance. XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The meta-learned coefficients successfully balance sentiment discrimination against domain and language invariance without causing training instability or overfitting on the specific dataset splits.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"New dataset for Romanian and Italian multi-domain sentiment analysis combined with an adversarial framework that improves XLM-R F1 by 4.64% over baseline.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7742646e7a7d307326cb3748975d65fda3d47c5594569dfe6e469a8c9ba9141f"},"source":{"id":"2604.17134","kind":"arxiv","version":2},"verdict":{"id":"ccf97bba-ccc0-4934-b37d-c4bedc1c256b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:24:26.488092Z","strongest_claim":"XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%.","one_line_summary":"New dataset for Romanian and Italian multi-domain sentiment analysis combined with an adversarial framework that improves XLM-R F1 by 4.64% over baseline.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The meta-learned coefficients successfully balance sentiment discrimination against domain and language invariance without causing training instability or overfitting on the specific dataset splits.","pith_extraction_headline":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17134/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":"2604.17134","created_at":"2026-05-25T02:02:15.408818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17134v2","created_at":"2026-05-25T02:02:15.408818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17134","created_at":"2026-05-25T02:02:15.408818+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWO4ZVOJFJDO","created_at":"2026-05-25T02:02:15.408818+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWO4ZVOJFJDOXFC2","created_at":"2026-05-25T02:02:15.408818+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWO4ZVOJ","created_at":"2026-05-25T02:02:15.408818+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/XWO4ZVOJFJDOXFC23ALQUM3EKG","json":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG.json","graph_json":"https://pith.science/api/pith-number/XWO4ZVOJFJDOXFC23ALQUM3EKG/graph.json","events_json":"https://pith.science/api/pith-number/XWO4ZVOJFJDOXFC23ALQUM3EKG/events.json","paper":"https://pith.science/paper/XWO4ZVOJ"},"agent_actions":{"view_html":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG","download_json":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG.json","view_paper":"https://pith.science/paper/XWO4ZVOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17134&json=true","fetch_graph":"https://pith.science/api/pith-number/XWO4ZVOJFJDOXFC23ALQUM3EKG/graph.json","fetch_events":"https://pith.science/api/pith-number/XWO4ZVOJFJDOXFC23ALQUM3EKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG/action/storage_attestation","attest_author":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG/action/author_attestation","sign_citation":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG/action/citation_signature","submit_replication":"https://pith.science/pith/XWO4ZVOJFJDOXFC23ALQUM3EKG/action/replication_record"}},"created_at":"2026-05-25T02:02:15.408818+00:00","updated_at":"2026-05-25T02:02:15.408818+00:00"}