{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2VMRZ4P52DZHKEPZ6PQH6M7MQ2","short_pith_number":"pith:2VMRZ4P5","schema_version":"1.0","canonical_sha256":"d5591cf1fdd0f27511f9f3e07f33ec868e2656fe3b143cb2167a1b784df68795","source":{"kind":"arxiv","id":"2303.15822","version":1},"attestation_state":"computed","paper":{"title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Boxing Chen, Deze Wang, Shanshan Li, Shaoliang Peng, Wei Dong, Wei Luo, Xiangke Liao","submitted_at":"2023-03-28T08:49:54Z","abstract_excerpt":"As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks and models. However, we find that multilingual fine-tuning leads to performance degradation on recent models UniXcoder and CodeT5.\n  To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it. Updating only 0.6\\% of the overall p"},"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":"2303.15822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-28T08:49:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbe0fd17006c28c6f68266939a27e8baa7297c4a6a37a7c04863663305b81682","abstract_canon_sha256":"6f4e35e853ae0606e64f598591d848373079348b21f42b9533505d555ffc8004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:28.132360Z","signature_b64":"31mhg6XZTlzEJANg/r9Q24FcnlqibCv7cn/SYMZCxF0Um9O06WcVyPiOukeUeP+f7IY3I/auUKC1BlUIURuwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5591cf1fdd0f27511f9f3e07f33ec868e2656fe3b143cb2167a1b784df68795","last_reissued_at":"2026-07-05T05:55:28.132011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:28.132011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Boxing Chen, Deze Wang, Shanshan Li, Shaoliang Peng, Wei Dong, Wei Luo, Xiangke Liao","submitted_at":"2023-03-28T08:49:54Z","abstract_excerpt":"As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks and models. However, we find that multilingual fine-tuning leads to performance degradation on recent models UniXcoder and CodeT5.\n  To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it. Updating only 0.6\\% of the overall p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15822","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/2303.15822/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":"2303.15822","created_at":"2026-07-05T05:55:28.132066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.15822v1","created_at":"2026-07-05T05:55:28.132066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15822","created_at":"2026-07-05T05:55:28.132066+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VMRZ4P52DZH","created_at":"2026-07-05T05:55:28.132066+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VMRZ4P52DZHKEPZ","created_at":"2026-07-05T05:55:28.132066+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VMRZ4P5","created_at":"2026-07-05T05:55:28.132066+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/2VMRZ4P52DZHKEPZ6PQH6M7MQ2","json":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2.json","graph_json":"https://pith.science/api/pith-number/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/graph.json","events_json":"https://pith.science/api/pith-number/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/events.json","paper":"https://pith.science/paper/2VMRZ4P5"},"agent_actions":{"view_html":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2","download_json":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2.json","view_paper":"https://pith.science/paper/2VMRZ4P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.15822&json=true","fetch_graph":"https://pith.science/api/pith-number/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/action/storage_attestation","attest_author":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/action/author_attestation","sign_citation":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/action/citation_signature","submit_replication":"https://pith.science/pith/2VMRZ4P52DZHKEPZ6PQH6M7MQ2/action/replication_record"}},"created_at":"2026-07-05T05:55:28.132066+00:00","updated_at":"2026-07-05T05:55:28.132066+00:00"}