{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SGPTAII74CWGOZG3F43LOCFY53","short_pith_number":"pith:SGPTAII7","schema_version":"1.0","canonical_sha256":"919f30211fe0ac6764db2f36b708b8eeec0b15092959780b99f130bebdeaadf0","source":{"kind":"arxiv","id":"2605.06754","version":2},"attestation_state":"computed","paper":{"title":"ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Advait Pavuluri, Ashita Saxena, Baishakhi Ray, Bridget McGinn, George Safta, Michele Merler, Rahul Krishna, Raju Pavuluri, Srikanth Tamilselvam","submitted_at":"2026-05-07T16:05:35Z","abstract_excerpt":"Java remains central to enterprise software, and many applications outlive their original architecture. Migrating them across frameworks is a behavior-preserving refactoring spanning build configuration, dependency injection, persistence, request handling, and deployment. Existing software-engineering benchmarks cover bug fixing, feature implementation, and language or version modernization, but leave cross-framework refactoring largely unmeasured.\n  We introduce ScarfBench, a benchmark for behavior-preserving cross-framework refactoring of enterprise Java applications. It is built from expert"},"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":true},"canonical_record":{"source":{"id":"2605.06754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-07T16:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"6374c34f88af8b23f0a2f66ed70f1117573f354813749da088f8d75b947169e3","abstract_canon_sha256":"89b95648366ba9972ed07ff2c097015f3408bba83125a424dc0e0f4a96603636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:46.361465Z","signature_b64":"PM0Mayy+XwcYhD1l1ul1A4R4l96+5UNucWc2YISHpuUpyNEMw2+XfFjp6TQawwYgnLrL0Zlrh6np7Y+AQ6QCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"919f30211fe0ac6764db2f36b708b8eeec0b15092959780b99f130bebdeaadf0","last_reissued_at":"2026-05-20T00:05:46.360763Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:46.360763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Advait Pavuluri, Ashita Saxena, Baishakhi Ray, Bridget McGinn, George Safta, Michele Merler, Rahul Krishna, Raju Pavuluri, Srikanth Tamilselvam","submitted_at":"2026-05-07T16:05:35Z","abstract_excerpt":"Java remains central to enterprise software, and many applications outlive their original architecture. Migrating them across frameworks is a behavior-preserving refactoring spanning build configuration, dependency injection, persistence, request handling, and deployment. Existing software-engineering benchmarks cover bug fixing, feature implementation, and language or version modernization, but leave cross-framework refactoring largely unmeasured.\n  We introduce ScarfBench, a benchmark for behavior-preserving cross-framework refactoring of enterprise Java applications. It is built from expert"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The strongest agent achieves only 15.3% aggregate test pass on focused-layer migrations and 12.2% on whole applications, and only one of the 204 tasks yields a fully behaviorally equivalent target.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 34 expert-written application triples and their associated test oracles are representative of real-world cross-framework migration difficulty and that passing the oracles guarantees behavior preservation outside the tested interface.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ScarfBench supplies 204 cross-framework Java migration tasks where the best agent passes only 15.3% of focused and 12.2% of whole-application tests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d19b79440a8d1d591c98a408f3b2f3a8cca8f85685ee8feef12f2dec7c5ab64a"},"source":{"id":"2605.06754","kind":"arxiv","version":2},"verdict":{"id":"a69dcdd9-4f52-45ec-9f43-2d387a4d2053","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:45:27.015711Z","strongest_claim":"The strongest agent achieves only 15.3% aggregate test pass on focused-layer migrations and 12.2% on whole applications, and only one of the 204 tasks yields a fully behaviorally equivalent target.","one_line_summary":"ScarfBench supplies 204 cross-framework Java migration tasks where the best agent passes only 15.3% of focused and 12.2% of whole-application tests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 34 expert-written application triples and their associated test oracles are representative of real-world cross-framework migration difficulty and that passing the oracles guarantees behavior preservation outside the tested interface.","pith_extraction_headline":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java."},"integrity":{"clean":false,"summary":{"advisory":1,"critical":0,"by_detector":{"doi_compliance":{"total":1,"advisory":1,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.06754/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1145/3793302.3793331.Keycloak) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":1,"audited_at":"2026-05-19T12:38:00.120586Z","detected_doi":"10.1145/3793302.3793331.Keycloak","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.864973Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:38:00.120586Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"2b73a4899fd74ae8c99b98bd081fda8771aa73f51fa46fa62e9cff33c5d1fddc"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"060f4b69c6962250900948366c608656b338bd0d6eb8c9caa0231aea82e216e6"},"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":"2605.06754","created_at":"2026-05-20T00:05:46.360877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06754v2","created_at":"2026-05-20T00:05:46.360877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06754","created_at":"2026-05-20T00:05:46.360877+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGPTAII74CWG","created_at":"2026-05-20T00:05:46.360877+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGPTAII74CWGOZG3","created_at":"2026-05-20T00:05:46.360877+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGPTAII7","created_at":"2026-05-20T00:05:46.360877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53","json":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53.json","graph_json":"https://pith.science/api/pith-number/SGPTAII74CWGOZG3F43LOCFY53/graph.json","events_json":"https://pith.science/api/pith-number/SGPTAII74CWGOZG3F43LOCFY53/events.json","paper":"https://pith.science/paper/SGPTAII7"},"agent_actions":{"view_html":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53","download_json":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53.json","view_paper":"https://pith.science/paper/SGPTAII7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06754&json=true","fetch_graph":"https://pith.science/api/pith-number/SGPTAII74CWGOZG3F43LOCFY53/graph.json","fetch_events":"https://pith.science/api/pith-number/SGPTAII74CWGOZG3F43LOCFY53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53/action/storage_attestation","attest_author":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53/action/author_attestation","sign_citation":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53/action/citation_signature","submit_replication":"https://pith.science/pith/SGPTAII74CWGOZG3F43LOCFY53/action/replication_record"}},"created_at":"2026-05-20T00:05:46.360877+00:00","updated_at":"2026-05-20T00:05:46.360877+00:00"}