{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SKK2DPKJJ5RLPDPP2NLMYCBCXX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"175b452318ad6361e62714c5cff923e5f8ae5bd1c0ea73172844239416462690","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T12:24:25Z","title_canon_sha256":"ec79e651b2babf3d9aa22c45f6d0124c19564f0e558690bf6c86ed2b716e96af"},"schema_version":"1.0","source":{"id":"2607.09345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09345","created_at":"2026-07-13T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09345v1","created_at":"2026-07-13T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09345","created_at":"2026-07-13T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"SKK2DPKJJ5RL","created_at":"2026-07-13T01:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"SKK2DPKJJ5RLPDPP","created_at":"2026-07-13T01:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"SKK2DPKJ","created_at":"2026-07-13T01:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:d5a3cf3253fe56222cde15bff170f64756137413dc506b53713f1bed771b89bb","target":"graph","created_at":"2026-07-13T01:19:04Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.09345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flaky tests pass and fail on the same code version, weakening the signal of test results and disrupting continuous integration (CI) pipelines. Code-based flakiness detectors report strong benchmark results, yet their use in practice remains limited. We argue that the field is studying the wrong problem: Flakiness is not a static property of test code, which often lacks the information needed to decide whether a test is flaky. Analyzing three code-based detectors operating on test code, we found that widely used benchmarks contain shortcuts that inflate reported F1 scores and that evaluation pr","authors_text":"Alexander Berndt, Jonathan Bell, \\\"Omer Oktay G\\\"ultekin, Sebastian Baltes, Thomas Bach","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T12:24:25Z","title":"How Far Are We from Detecting Flaky Tests? On the Limits of Code-Based Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09345","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:98ac57ea8466e4a310c929f72ae5a1c7f60130dc44866e863870c7b9643e1c1a","target":"record","created_at":"2026-07-13T01:19:04Z","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":"175b452318ad6361e62714c5cff923e5f8ae5bd1c0ea73172844239416462690","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T12:24:25Z","title_canon_sha256":"ec79e651b2babf3d9aa22c45f6d0124c19564f0e558690bf6c86ed2b716e96af"},"schema_version":"1.0","source":{"id":"2607.09345","kind":"arxiv","version":1}},"canonical_sha256":"9295a1bd494f62b78defd356cc0822bdd0919b31698393ae7ac479223148d3f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9295a1bd494f62b78defd356cc0822bdd0919b31698393ae7ac479223148d3f4","first_computed_at":"2026-07-13T01:19:04.095261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:19:04.095261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IZOIHBuuHdc0ypvDAoJl3fKqwNVlwqAqL1laU+lcHjDQLtR5BSXflft/GphVsKktbF8WbbL+z5pSu/12Mg9JBw==","signature_status":"signed_v1","signed_at":"2026-07-13T01:19:04.096331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98ac57ea8466e4a310c929f72ae5a1c7f60130dc44866e863870c7b9643e1c1a","sha256:d5a3cf3253fe56222cde15bff170f64756137413dc506b53713f1bed771b89bb"],"state_sha256":"42b93342bca035bcb7551a2dc5a23d0d7f8cae8f634fe7159cfe59fe2798177c"}