{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VXAM2E2VKWCUNAXJAC7GXMVOE6","short_pith_number":"pith:VXAM2E2V","schema_version":"1.0","canonical_sha256":"adc0cd135555854682e900be6bb2ae279c17b9eeba485e770b84e2cb27543d29","source":{"kind":"arxiv","id":"2606.18389","version":1},"attestation_state":"computed","paper":{"title":"Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniil Gurgurov, Jan Cegin, Simon Ostermann, Yusser Al Ghussin","submitted_at":"2026-06-16T18:34:21Z","abstract_excerpt":"Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Qu"},"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":"2606.18389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T18:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"77721b62895b8f148689969db04f5354eddd99457daed4acce9369819ef17753","abstract_canon_sha256":"03b330b258ef040d448307979d772de7dfffa23f2a09c332b782cddb49e80032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:00.051667Z","signature_b64":"9RzDOqoJLxM3yCBzFREx+4axgj22zAeoR3TB3laB/mK4+pKT7GDrY4CiOfoWZHQ5KC9BvreAk7uZA+SRjHRkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc0cd135555854682e900be6bb2ae279c17b9eeba485e770b84e2cb27543d29","last_reissued_at":"2026-06-19T16:11:00.051325Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:00.051325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniil Gurgurov, Jan Cegin, Simon Ostermann, Yusser Al Ghussin","submitted_at":"2026-06-16T18:34:21Z","abstract_excerpt":"Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18389","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/2606.18389/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":"2606.18389","created_at":"2026-06-19T16:11:00.051377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18389v1","created_at":"2026-06-19T16:11:00.051377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18389","created_at":"2026-06-19T16:11:00.051377+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXAM2E2VKWCU","created_at":"2026-06-19T16:11:00.051377+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXAM2E2VKWCUNAXJ","created_at":"2026-06-19T16:11:00.051377+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXAM2E2V","created_at":"2026-06-19T16:11:00.051377+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/VXAM2E2VKWCUNAXJAC7GXMVOE6","json":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6.json","graph_json":"https://pith.science/api/pith-number/VXAM2E2VKWCUNAXJAC7GXMVOE6/graph.json","events_json":"https://pith.science/api/pith-number/VXAM2E2VKWCUNAXJAC7GXMVOE6/events.json","paper":"https://pith.science/paper/VXAM2E2V"},"agent_actions":{"view_html":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6","download_json":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6.json","view_paper":"https://pith.science/paper/VXAM2E2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18389&json=true","fetch_graph":"https://pith.science/api/pith-number/VXAM2E2VKWCUNAXJAC7GXMVOE6/graph.json","fetch_events":"https://pith.science/api/pith-number/VXAM2E2VKWCUNAXJAC7GXMVOE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6/action/storage_attestation","attest_author":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6/action/author_attestation","sign_citation":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6/action/citation_signature","submit_replication":"https://pith.science/pith/VXAM2E2VKWCUNAXJAC7GXMVOE6/action/replication_record"}},"created_at":"2026-06-19T16:11:00.051377+00:00","updated_at":"2026-06-19T16:11:00.051377+00:00"}