{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NNDHAHAUPYIP2YCJDIGVWUPEK","short_pith_number":"pith:2NNDHAHA","schema_version":"1.0","canonical_sha256":"d35a3380e0a3f087eb0248d06ada8f22a85483cbcc12ca14b8adf13cef14c5bf","source":{"kind":"arxiv","id":"2402.05783","version":2},"attestation_state":"computed","paper":{"title":"Text-to-Code Generation with Modality-relative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fenia Christopoulou, Gerasimos Lampouras, Guchun Zhang","submitted_at":"2024-02-08T16:17:24Z","abstract_excerpt":"Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain both natural and (linearised) programming language. Such approaches effectively map both modalities of the sequence into the same embedding space. However, programming language keywords (e.g. \"while\") often have very strictly defined semantics. As such, transfer learning from their natural language usage may not necessarily be beneficial to their code applic"},"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":"2402.05783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T16:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"8fde9c65a75e8e48be0e9d1dbbd8ac0562406dc594742f0e3c24226ad1417610","abstract_canon_sha256":"7be478cb712e183c97d97acc753336ee2388cd7b2d459965413be5853d43afbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:00.725927Z","signature_b64":"9bl5iTsYph1v0GfBTxtYl/ft3u3OdotqfUImyO2SLkutr8LyVezrrlWDX4WdFt6RqDaA14qI6K2mAZl6U0lmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35a3380e0a3f087eb0248d06ada8f22a85483cbcc12ca14b8adf13cef14c5bf","last_reissued_at":"2026-07-05T07:44:00.725495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:00.725495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-Code Generation with Modality-relative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fenia Christopoulou, Gerasimos Lampouras, Guchun Zhang","submitted_at":"2024-02-08T16:17:24Z","abstract_excerpt":"Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain both natural and (linearised) programming language. Such approaches effectively map both modalities of the sequence into the same embedding space. However, programming language keywords (e.g. \"while\") often have very strictly defined semantics. As such, transfer learning from their natural language usage may not necessarily be beneficial to their code applic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05783","kind":"arxiv","version":2},"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/2402.05783/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":"2402.05783","created_at":"2026-07-05T07:44:00.725555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05783v2","created_at":"2026-07-05T07:44:00.725555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05783","created_at":"2026-07-05T07:44:00.725555+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NNDHAHAUPYI","created_at":"2026-07-05T07:44:00.725555+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NNDHAHAUPYIP2YC","created_at":"2026-07-05T07:44:00.725555+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NNDHAHA","created_at":"2026-07-05T07:44:00.725555+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/2NNDHAHAUPYIP2YCJDIGVWUPEK","json":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK.json","graph_json":"https://pith.science/api/pith-number/2NNDHAHAUPYIP2YCJDIGVWUPEK/graph.json","events_json":"https://pith.science/api/pith-number/2NNDHAHAUPYIP2YCJDIGVWUPEK/events.json","paper":"https://pith.science/paper/2NNDHAHA"},"agent_actions":{"view_html":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK","download_json":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK.json","view_paper":"https://pith.science/paper/2NNDHAHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05783&json=true","fetch_graph":"https://pith.science/api/pith-number/2NNDHAHAUPYIP2YCJDIGVWUPEK/graph.json","fetch_events":"https://pith.science/api/pith-number/2NNDHAHAUPYIP2YCJDIGVWUPEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK/action/storage_attestation","attest_author":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK/action/author_attestation","sign_citation":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK/action/citation_signature","submit_replication":"https://pith.science/pith/2NNDHAHAUPYIP2YCJDIGVWUPEK/action/replication_record"}},"created_at":"2026-07-05T07:44:00.725555+00:00","updated_at":"2026-07-05T07:44:00.725555+00:00"}