{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HET6KPFBYZ6UQH3FULC4QLM5LB","short_pith_number":"pith:HET6KPFB","schema_version":"1.0","canonical_sha256":"3927e53ca1c67d481f65a2c5c82d9d586429f0384f3049e1c4a7ca83a8b67630","source":{"kind":"arxiv","id":"2412.08955","version":1},"attestation_state":"computed","paper":{"title":"Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mateo Alejandro Rojas, Rafael Carranza","submitted_at":"2024-12-12T05:36:51Z","abstract_excerpt":"Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on external retrievers or task-specific fine-tuning, limiting their scalability and generalizability. In this paper, we propose a novel self-supervised framework that harnesses the generative capabilities of LLMs to internally select and utilize task-relevant examples. Our method introduces two key objectives: a retrieval-generation alignment loss to optimize the"},"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":"2412.08955","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"057ad86c616cdd326f8068cf7189be9009e042c56188bf3a07d6ae91d8769a76","abstract_canon_sha256":"93233b564dc5a9520326233019dc9b074ad8d7d21e47418cc93cb4fd89880da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:04.438892Z","signature_b64":"0wS9euPPKAe17SLjZb7WLX7p8ETG8W1dHGLJZdaikgRjySf3xHqh88kDT5TBuwo0os7bu7nwOiz200+GmqtJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3927e53ca1c67d481f65a2c5c82d9d586429f0384f3049e1c4a7ca83a8b67630","last_reissued_at":"2026-07-05T09:48:04.438411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:04.438411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mateo Alejandro Rojas, Rafael Carranza","submitted_at":"2024-12-12T05:36:51Z","abstract_excerpt":"Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on external retrievers or task-specific fine-tuning, limiting their scalability and generalizability. In this paper, we propose a novel self-supervised framework that harnesses the generative capabilities of LLMs to internally select and utilize task-relevant examples. Our method introduces two key objectives: a retrieval-generation alignment loss to optimize the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08955","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/2412.08955/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":"2412.08955","created_at":"2026-07-05T09:48:04.438476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08955v1","created_at":"2026-07-05T09:48:04.438476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08955","created_at":"2026-07-05T09:48:04.438476+00:00"},{"alias_kind":"pith_short_12","alias_value":"HET6KPFBYZ6U","created_at":"2026-07-05T09:48:04.438476+00:00"},{"alias_kind":"pith_short_16","alias_value":"HET6KPFBYZ6UQH3F","created_at":"2026-07-05T09:48:04.438476+00:00"},{"alias_kind":"pith_short_8","alias_value":"HET6KPFB","created_at":"2026-07-05T09:48:04.438476+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/HET6KPFBYZ6UQH3FULC4QLM5LB","json":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB.json","graph_json":"https://pith.science/api/pith-number/HET6KPFBYZ6UQH3FULC4QLM5LB/graph.json","events_json":"https://pith.science/api/pith-number/HET6KPFBYZ6UQH3FULC4QLM5LB/events.json","paper":"https://pith.science/paper/HET6KPFB"},"agent_actions":{"view_html":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB","download_json":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB.json","view_paper":"https://pith.science/paper/HET6KPFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08955&json=true","fetch_graph":"https://pith.science/api/pith-number/HET6KPFBYZ6UQH3FULC4QLM5LB/graph.json","fetch_events":"https://pith.science/api/pith-number/HET6KPFBYZ6UQH3FULC4QLM5LB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB/action/storage_attestation","attest_author":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB/action/author_attestation","sign_citation":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB/action/citation_signature","submit_replication":"https://pith.science/pith/HET6KPFBYZ6UQH3FULC4QLM5LB/action/replication_record"}},"created_at":"2026-07-05T09:48:04.438476+00:00","updated_at":"2026-07-05T09:48:04.438476+00:00"}