{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SKK2DPKJJ5RLPDPP2NLMYCBCXX","short_pith_number":"pith:SKK2DPKJ","canonical_record":{"source":{"id":"2607.09345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T12:24:25Z","cross_cats_sorted":[],"title_canon_sha256":"ec79e651b2babf3d9aa22c45f6d0124c19564f0e558690bf6c86ed2b716e96af","abstract_canon_sha256":"175b452318ad6361e62714c5cff923e5f8ae5bd1c0ea73172844239416462690"},"schema_version":"1.0"},"canonical_sha256":"9295a1bd494f62b78defd356cc0822bdd0919b31698393ae7ac479223148d3f4","source":{"kind":"arxiv","id":"2607.09345","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SKK2DPKJJ5RLPDPP2NLMYCBCXX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T12:24:25Z","cross_cats_sorted":[],"title_canon_sha256":"ec79e651b2babf3d9aa22c45f6d0124c19564f0e558690bf6c86ed2b716e96af","abstract_canon_sha256":"175b452318ad6361e62714c5cff923e5f8ae5bd1c0ea73172844239416462690"},"schema_version":"1.0"},"canonical_sha256":"9295a1bd494f62b78defd356cc0822bdd0919b31698393ae7ac479223148d3f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:04.096331Z","signature_b64":"IZOIHBuuHdc0ypvDAoJl3fKqwNVlwqAqL1laU+lcHjDQLtR5BSXflft/GphVsKktbF8WbbL+z5pSu/12Mg9JBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9295a1bd494f62b78defd356cc0822bdd0919b31698393ae7ac479223148d3f4","last_reissued_at":"2026-07-13T01:19:04.095261Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:04.095261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09345","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9hAthThugMBao/AtptSRZ/VE/hVaRLMX1jQ+skgv5YpwdUvnfUe1pPVHlT5FcyjE32z6gEp4pUfPo/JCzleAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:03:48.513998Z"},"content_sha256":"98ac57ea8466e4a310c929f72ae5a1c7f60130dc44866e863870c7b9643e1c1a","schema_version":"1.0","event_id":"sha256:98ac57ea8466e4a310c929f72ae5a1c7f60130dc44866e863870c7b9643e1c1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SKK2DPKJJ5RLPDPP2NLMYCBCXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Far Are We from Detecting Flaky Tests? On the Limits of Code-Based Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexander Berndt, Jonathan Bell, \\\"Omer Oktay G\\\"ultekin, Sebastian Baltes, Thomas Bach","submitted_at":"2026-07-10T12:24:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09345","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/2607.09345/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMe5u3eq6AJ7wCuuAzumkflu8bXeOMpy2joFjVYaEIXMm+r3/lsxIM6N+50vlhtfE1AIyzDtzDe24NMJo6nvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:03:48.514380Z"},"content_sha256":"d5a3cf3253fe56222cde15bff170f64756137413dc506b53713f1bed771b89bb","schema_version":"1.0","event_id":"sha256:d5a3cf3253fe56222cde15bff170f64756137413dc506b53713f1bed771b89bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/bundle.json","state_url":"https://pith.science/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:03:48Z","links":{"resolver":"https://pith.science/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX","bundle":"https://pith.science/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/bundle.json","state":"https://pith.science/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKK2DPKJJ5RLPDPP2NLMYCBCXX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c72HqSBdVKAxMBC01/t751L6Z5f521PJi94Lt5N64z1OqQn9qi+u/sWB09seM37aBzlXkBxzOWcRarCIXo3WDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:03:48.516897Z","bundle_sha256":"6cfd3e79c3ab6df7cfee9bd76af873b44f1bfae5cf49d338dea6ef5c6e909a76"}}