{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3VITAVFOVWD6QIYQ3ALEH6USIO","short_pith_number":"pith:3VITAVFO","schema_version":"1.0","canonical_sha256":"dd513054aead87e82310d81643fa924385d3ea640711425213f14b639e896c8c","source":{"kind":"arxiv","id":"2605.15607","version":1},"attestation_state":"computed","paper":{"title":"Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Disha Makhija, Manoj Ghuhan Arivazhagan, Rashmi Gangadharaiah, Vinayshekhar Bannihatti Kumar","submitted_at":"2026-05-15T04:37:31Z","abstract_excerpt":"Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative language absent from all pretraining corpora, and evaluate frontier models zero-shot and fine-tuned Qwen3 (4B, 8B, 32B) on 352 problems. We find that fine-tuning quickly teaches syntax but fails to transfer semantic competence: Python outperforms PyLang by up to 19% across all configurations, and no intervention (multi-task learning, preference tuning, code infilli"},"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":"2605.15607","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T04:37:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"085295bb5be72585364936b29a5aaf8d26ce72567bbad12c9bb0e6072af74b92","abstract_canon_sha256":"3012c70e895b0d02f1c85c4a3a6e6c1ddd215b0dae07ae6be3d1e7e28a889490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:07.833838Z","signature_b64":"814RFnShZXDHLU+7mzyqdVX7UahnixHLdTWaUTZDF/0ygQfKptexTezh14zPYebFpWQtNwfPLHrfDfU9y86mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd513054aead87e82310d81643fa924385d3ea640711425213f14b639e896c8c","last_reissued_at":"2026-05-20T00:01:07.833045Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:07.833045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Disha Makhija, Manoj Ghuhan Arivazhagan, Rashmi Gangadharaiah, Vinayshekhar Bannihatti Kumar","submitted_at":"2026-05-15T04:37:31Z","abstract_excerpt":"Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative language absent from all pretraining corpora, and evaluate frontier models zero-shot and fine-tuned Qwen3 (4B, 8B, 32B) on 352 problems. We find that fine-tuning quickly teaches syntax but fails to transfer semantic competence: Python outperforms PyLang by up to 19% across all configurations, and no intervention (multi-task learning, preference tuning, code infilli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15607","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/2605.15607/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.622671Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.049229Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ccb408f124ae5e1c74237fa5306df3ed627b0977fdd421a3bc4a30995803f0e4"},"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":"2605.15607","created_at":"2026-05-20T00:01:07.833178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15607v1","created_at":"2026-05-20T00:01:07.833178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15607","created_at":"2026-05-20T00:01:07.833178+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VITAVFOVWD6","created_at":"2026-05-20T00:01:07.833178+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VITAVFOVWD6QIYQ","created_at":"2026-05-20T00:01:07.833178+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VITAVFO","created_at":"2026-05-20T00:01:07.833178+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/3VITAVFOVWD6QIYQ3ALEH6USIO","json":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO.json","graph_json":"https://pith.science/api/pith-number/3VITAVFOVWD6QIYQ3ALEH6USIO/graph.json","events_json":"https://pith.science/api/pith-number/3VITAVFOVWD6QIYQ3ALEH6USIO/events.json","paper":"https://pith.science/paper/3VITAVFO"},"agent_actions":{"view_html":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO","download_json":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO.json","view_paper":"https://pith.science/paper/3VITAVFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15607&json=true","fetch_graph":"https://pith.science/api/pith-number/3VITAVFOVWD6QIYQ3ALEH6USIO/graph.json","fetch_events":"https://pith.science/api/pith-number/3VITAVFOVWD6QIYQ3ALEH6USIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO/action/storage_attestation","attest_author":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO/action/author_attestation","sign_citation":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO/action/citation_signature","submit_replication":"https://pith.science/pith/3VITAVFOVWD6QIYQ3ALEH6USIO/action/replication_record"}},"created_at":"2026-05-20T00:01:07.833178+00:00","updated_at":"2026-05-20T00:01:07.833178+00:00"}