{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7HV3C43ME7IETMFOTR2MKLF3XJ","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":"a789a42e2294d6b09c99a75b98718d0b13df2c6b357dec7e83b35f2dae638d62","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:12:16Z","title_canon_sha256":"d704cf5a8045b11251ecad8ef794044ef070d9cf00b9d6850f36e73e1fc0edbd"},"schema_version":"1.0","source":{"id":"2503.03285","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03285","created_at":"2026-07-05T10:25:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03285v2","created_at":"2026-07-05T10:25:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03285","created_at":"2026-07-05T10:25:19Z"},{"alias_kind":"pith_short_12","alias_value":"7HV3C43ME7IE","created_at":"2026-07-05T10:25:19Z"},{"alias_kind":"pith_short_16","alias_value":"7HV3C43ME7IETMFO","created_at":"2026-07-05T10:25:19Z"},{"alias_kind":"pith_short_8","alias_value":"7HV3C43M","created_at":"2026-07-05T10:25:19Z"}],"graph_snapshots":[{"event_id":"sha256:8c66a835804115c34503a0da66edb145b3fdffc89aaea205855dab8c343e450d","target":"graph","created_at":"2026-07-05T10:25:19Z","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/2503.03285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) is a multimodal task requiring reasoning across textual and visual inputs, which becomes particularly challenging in low-resource languages like Vietnamese due to linguistic variability and the lack of high-quality datasets. Traditional methods often rely heavily on extensive annotated datasets, computationally expensive pipelines, and large pre-trained models, specifically in the domain of Vietnamese VQA, limiting their applicability in such scenarios. To address these limitations, we propose a training framework that combines a paraphrase-based feature augment","authors_text":"Huy Thanh Nguyen, Khoi Anh Nguyen, Linh Yen Vu, Thang Dinh Duong, Thuan Nguyen Duong, Vinh Quang Dinh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:12:16Z","title":"Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03285","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":"sha256:745744391a4baf05699ab4d8f22fee31f831077f1da62c666380e5fd524a5aa4","target":"record","created_at":"2026-07-05T10:25:19Z","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":"a789a42e2294d6b09c99a75b98718d0b13df2c6b357dec7e83b35f2dae638d62","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:12:16Z","title_canon_sha256":"d704cf5a8045b11251ecad8ef794044ef070d9cf00b9d6850f36e73e1fc0edbd"},"schema_version":"1.0","source":{"id":"2503.03285","kind":"arxiv","version":2}},"canonical_sha256":"f9ebb1736c27d049b0ae9c74c52cbbba79dfee02bca95f6fe50092f6fa2049a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9ebb1736c27d049b0ae9c74c52cbbba79dfee02bca95f6fe50092f6fa2049a2","first_computed_at":"2026-07-05T10:25:19.856472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:19.856472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"alBnngpOnTuNESaRNAnO0l7isPRj6WjWeTuJMXx8VJHGP0jmCMOx6x9FM4zaTecPFwexaHOYI7Y0vnzEZ93hBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:19.856932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03285","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:745744391a4baf05699ab4d8f22fee31f831077f1da62c666380e5fd524a5aa4","sha256:8c66a835804115c34503a0da66edb145b3fdffc89aaea205855dab8c343e450d"],"state_sha256":"c6db49e7a92f07d17d589889efe125069e396cd2e564f63de598086d9f5eb74b"}