{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HAMKX2B3EIBTBOXGJOWNKOYHDY","short_pith_number":"pith:HAMKX2B3","schema_version":"1.0","canonical_sha256":"3818abe83b220330bae64bacd53b071e2e2fd47f6449b1e5c7dd6fb6af8ed44d","source":{"kind":"arxiv","id":"2606.19170","version":1},"attestation_state":"computed","paper":{"title":"Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Cheng, Hirokazu Kiyomaru, Shiho Matta, Takashi Kodama, Yin Jou Huang, Yugo Murawaki","submitted_at":"2026-06-17T15:13:19Z","abstract_excerpt":"We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While previous studies have explored SLA in language models, they have predominantly relied on smaller or non-decoder models, limiting their ability to generate open-ended text and reducing their suitability as practical L2 simulators. We identify a key challenge when scaling models to this size: L2 contamination within the \"monolingual\" pretraining corpus used for L1 acquisition. To address this, we propose a filtering metho"},"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":"2606.19170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T15:13:19Z","cross_cats_sorted":[],"title_canon_sha256":"89012c74733d2b032ac64381927f73b72bbe5aa83ab8c1097695b49efc189fdc","abstract_canon_sha256":"6868219d43858fe2e5e166c3258f4775fc78f905b1b8252c4eb5af6589a00bf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:58.476349Z","signature_b64":"6ra/KxHi4tmFNWvuqCENasB3e4wxOWfSP2nd8Uy9bvjGz17WkQf8PZWdgAEjF/Re5G1ttNzI7AtBvB3sxrUaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3818abe83b220330bae64bacd53b071e2e2fd47f6449b1e5c7dd6fb6af8ed44d","last_reissued_at":"2026-06-19T16:11:58.475975Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:58.475975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Cheng, Hirokazu Kiyomaru, Shiho Matta, Takashi Kodama, Yin Jou Huang, Yugo Murawaki","submitted_at":"2026-06-17T15:13:19Z","abstract_excerpt":"We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While previous studies have explored SLA in language models, they have predominantly relied on smaller or non-decoder models, limiting their ability to generate open-ended text and reducing their suitability as practical L2 simulators. We identify a key challenge when scaling models to this size: L2 contamination within the \"monolingual\" pretraining corpus used for L1 acquisition. To address this, we propose a filtering metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19170","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/2606.19170/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":"2606.19170","created_at":"2026-06-19T16:11:58.476041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19170v1","created_at":"2026-06-19T16:11:58.476041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19170","created_at":"2026-06-19T16:11:58.476041+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAMKX2B3EIBT","created_at":"2026-06-19T16:11:58.476041+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAMKX2B3EIBTBOXG","created_at":"2026-06-19T16:11:58.476041+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAMKX2B3","created_at":"2026-06-19T16:11:58.476041+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/HAMKX2B3EIBTBOXGJOWNKOYHDY","json":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY.json","graph_json":"https://pith.science/api/pith-number/HAMKX2B3EIBTBOXGJOWNKOYHDY/graph.json","events_json":"https://pith.science/api/pith-number/HAMKX2B3EIBTBOXGJOWNKOYHDY/events.json","paper":"https://pith.science/paper/HAMKX2B3"},"agent_actions":{"view_html":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY","download_json":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY.json","view_paper":"https://pith.science/paper/HAMKX2B3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19170&json=true","fetch_graph":"https://pith.science/api/pith-number/HAMKX2B3EIBTBOXGJOWNKOYHDY/graph.json","fetch_events":"https://pith.science/api/pith-number/HAMKX2B3EIBTBOXGJOWNKOYHDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY/action/storage_attestation","attest_author":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY/action/author_attestation","sign_citation":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY/action/citation_signature","submit_replication":"https://pith.science/pith/HAMKX2B3EIBTBOXGJOWNKOYHDY/action/replication_record"}},"created_at":"2026-06-19T16:11:58.476041+00:00","updated_at":"2026-06-19T16:11:58.476041+00:00"}