{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SGPTAII74CWGOZG3F43LOCFY53","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89b95648366ba9972ed07ff2c097015f3408bba83125a424dc0e0f4a96603636","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-07T16:05:35Z","title_canon_sha256":"6374c34f88af8b23f0a2f66ed70f1117573f354813749da088f8d75b947169e3"},"schema_version":"1.0","source":{"id":"2605.06754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.06754","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.06754v2","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06754","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"SGPTAII74CWG","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"SGPTAII74CWGOZG3","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"SGPTAII7","created_at":"2026-05-20T00:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:1583a85a23923435ddca21b0a196385eba90cf03d6cc2d28ea8ea018b838e687","target":"graph","created_at":"2026-05-20T00:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java."}],"snapshot_sha256":"d19b79440a8d1d591c98a408f3b2f3a8cca8f85685ee8feef12f2dec7c5ab64a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"060f4b69c6962250900948366c608656b338bd0d6eb8c9caa0231aea82e216e6"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.864973Z","status":"completed","version":"1.0.0"},{"findings_count":1,"name":"doi_compliance","ran_at":"2026-05-19T12:38:00.120586Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.06754/integrity.json","findings":[{"audited_at":"2026-05-19T12:38:00.120586Z","detected_arxiv_id":null,"detected_doi":"10.1145/3793302.3793331.Keycloak","detector":"doi_compliance","finding_type":"recoverable_identifier","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.","ref_index":1,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"2b73a4899fd74ae8c99b98bd081fda8771aa73f51fa46fa62e9cff33c5d1fddc","summary":{"advisory":1,"by_detector":{"doi_compliance":{"advisory":1,"critical":0,"informational":0,"total":1}},"critical":0,"informational":0}},"paper":{"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","authors_text":"Advait Pavuluri, Ashita Saxena, Baishakhi Ray, Bridget McGinn, George Safta, Michele Merler, Rahul Krishna, Raju Pavuluri, Srikanth Tamilselvam","cross_cats":[],"headline":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-07T16:05:35Z","title":"ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.06754","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T00:45:27.015711Z","id":"a69dcdd9-4f52-45ec-9f43-2d387a4d2053","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Current coding agents succeed on only 15 percent of behavior-preserving cross-framework migrations in enterprise Java.","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.","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."}},"verdict_id":"a69dcdd9-4f52-45ec-9f43-2d387a4d2053"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4003ee158ef79b2c428af4745ebe59f5098d831938ddf32dd0e4b93acadd6e0c","target":"record","created_at":"2026-05-20T00:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89b95648366ba9972ed07ff2c097015f3408bba83125a424dc0e0f4a96603636","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-07T16:05:35Z","title_canon_sha256":"6374c34f88af8b23f0a2f66ed70f1117573f354813749da088f8d75b947169e3"},"schema_version":"1.0","source":{"id":"2605.06754","kind":"arxiv","version":2}},"canonical_sha256":"919f30211fe0ac6764db2f36b708b8eeec0b15092959780b99f130bebdeaadf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"919f30211fe0ac6764db2f36b708b8eeec0b15092959780b99f130bebdeaadf0","first_computed_at":"2026-05-20T00:05:46.360763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:46.360763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PM0Mayy+XwcYhD1l1ul1A4R4l96+5UNucWc2YISHpuUpyNEMw2+XfFjp6TQawwYgnLrL0Zlrh6np7Y+AQ6QCCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:46.361465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.06754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25056bc27286b43a2873ac2e10b2ba531e90d1967482c613d6caf5f48c46355c","sha256:4003ee158ef79b2c428af4745ebe59f5098d831938ddf32dd0e4b93acadd6e0c","sha256:1583a85a23923435ddca21b0a196385eba90cf03d6cc2d28ea8ea018b838e687"],"state_sha256":"bb91c40347cd68958e1d9aa182e1b4f6e9df0e9e3db10874085fd9a1b05089db"}