{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2XD7AD2DV4LE6DKOARAWLZULHA","short_pith_number":"pith:2XD7AD2D","canonical_record":{"source":{"id":"2605.12925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T03:00:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07872682c0cfb5124101ff197f31db38f83c886e616dae8057e2bc39abffda39","abstract_canon_sha256":"803d155a77ded41b300fe34dced984f3eb46a0af65c306e31432ddf0c8f2c16a"},"schema_version":"1.0"},"canonical_sha256":"d5c7f00f43af164f0d4e044165e68b380302144e136f8c90ba9bcc3473f5877d","source":{"kind":"arxiv","id":"2605.12925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12925","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12925v1","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12925","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"2XD7AD2DV4LE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2XD7AD2DV4LE6DKO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2XD7AD2D","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2XD7AD2DV4LE6DKOARAWLZULHA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T03:00:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07872682c0cfb5124101ff197f31db38f83c886e616dae8057e2bc39abffda39","abstract_canon_sha256":"803d155a77ded41b300fe34dced984f3eb46a0af65c306e31432ddf0c8f2c16a"},"schema_version":"1.0"},"canonical_sha256":"d5c7f00f43af164f0d4e044165e68b380302144e136f8c90ba9bcc3473f5877d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:10.101635Z","signature_b64":"t5jAyHzJ6WH8ts/9WL17z+PDjmmPs7j5Ynp59GedCrqQnODuZVxSDQiFYZxm5mtpRIo9y51ZUIcopL6M1bN9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c7f00f43af164f0d4e044165e68b380302144e136f8c90ba9bcc3473f5877d","last_reissued_at":"2026-05-18T03:09:10.100969Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:10.100969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12925","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":"2026-05-18T03:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yv2ta57MKY253g7afYWPCgFEG/aBQJTDPthh0us9ibzqRZ+RKYbmo8lFoZSJgUoEwuA2qaWMLGArc9aUDQzxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:41:57.166211Z"},"content_sha256":"7710c5082c6465967c4e94b3e6a845859df7f52d75a06020cc3b3e886279ca57","schema_version":"1.0","event_id":"sha256:7710c5082c6465967c4e94b3e6a845859df7f52d75a06020cc3b3e886279ca57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2XD7AD2DV4LE6DKOARAWLZULHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Benjamin Steenhoek, Gaurav Mittal, Pingping Lin, Priyam Sahoo, Shengjie Ma, Xiaomin Li, Yu Hu","submitted_at":"2026-05-13T03:00:57Z","abstract_excerpt":"Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Prefix Tree Acceptor references built by merging multiple passing solutions accurately represent principled behavior without incorporating lucky elements from the source trajectories.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"10.7% of passing SWE-agent trajectories are Lucky Passes with chaotic behaviors, and a quality score based on process references changes model rankings across eight backends.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"adce0b450020fee18eaa30704ab28f998777265f989745261d06c17949418e61"},"source":{"id":"2605.12925","kind":"arxiv","version":1},"verdict":{"id":"65a2b27d-f897-4cc8-8786-4ee98826b4a1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:46:32.801828Z","strongest_claim":"Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification.","one_line_summary":"10.7% of passing SWE-agent trajectories are Lucky Passes with chaotic behaviors, and a quality score based on process references changes model rankings across eight backends.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Prefix Tree Acceptor references built by merging multiple passing solutions accurately represent principled behavior without incorporating lucky elements from the source trajectories.","pith_extraction_headline":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones."},"references":{"count":61,"sample":[{"doi":"","year":null,"title":"arXiv preprint arXiv:2410.20285 , year=","work_id":"e26e6ec9-37e3-47d8-b494-e0a227e77e36","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Swe-rebench: An automated pipeline for task collection and decontaminated evaluation of software engineering agents","work_id":"c819f5fe-32b6-41d1-aeb5-2d80c6fa8474","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Islem Bouzenia, Premkumar Devanbu, and Michael Pradel","work_id":"9584953a-2ac8-49b2-bcd3-44924077f86d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"2026 , note =","work_id":"ad7bad76-b98f-4522-8476-a382ae24a4b8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.5281/zenodo.19357078","year":null,"title":"doi:10.5281/zenodo.19357078 , url =","work_id":"5aab64ed-4762-4aa1-922b-18ae4b5b8b27","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":61,"snapshot_sha256":"66df3e8e7819f1fb70a7bba3a29167044596023591235646b3882339a9f38ab8","internal_anchors":14},"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":"65a2b27d-f897-4cc8-8786-4ee98826b4a1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GZk6oB9Rj44v07Q5TWKXhF2wJefdqK5BHaC10VbAvEuAr0jMFLoFIuFLk0Zj75kiXAvb4hlSXSd/pWi7qq8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:41:57.166822Z"},"content_sha256":"8340795877791325c5d9ab593c559490d591b61f08eecc131ca6693052139e2b","schema_version":"1.0","event_id":"sha256:8340795877791325c5d9ab593c559490d591b61f08eecc131ca6693052139e2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XD7AD2DV4LE6DKOARAWLZULHA/bundle.json","state_url":"https://pith.science/pith/2XD7AD2DV4LE6DKOARAWLZULHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XD7AD2DV4LE6DKOARAWLZULHA/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":"2026-05-26T15:41:57Z","links":{"resolver":"https://pith.science/pith/2XD7AD2DV4LE6DKOARAWLZULHA","bundle":"https://pith.science/pith/2XD7AD2DV4LE6DKOARAWLZULHA/bundle.json","state":"https://pith.science/pith/2XD7AD2DV4LE6DKOARAWLZULHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XD7AD2DV4LE6DKOARAWLZULHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2XD7AD2DV4LE6DKOARAWLZULHA","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":"803d155a77ded41b300fe34dced984f3eb46a0af65c306e31432ddf0c8f2c16a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T03:00:57Z","title_canon_sha256":"07872682c0cfb5124101ff197f31db38f83c886e616dae8057e2bc39abffda39"},"schema_version":"1.0","source":{"id":"2605.12925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12925","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12925v1","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12925","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"2XD7AD2DV4LE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2XD7AD2DV4LE6DKO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2XD7AD2D","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8340795877791325c5d9ab593c559490d591b61f08eecc131ca6693052139e2b","target":"graph","created_at":"2026-05-18T03:09:10Z","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":"Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That Prefix Tree Acceptor references built by merging multiple passing solutions accurately represent principled behavior without incorporating lucky elements from the source trajectories."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"10.7% of passing SWE-agent trajectories are Lucky Passes with chaotic behaviors, and a quality score based on process references changes model rankings across eight backends."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones."}],"snapshot_sha256":"adce0b450020fee18eaa30704ab28f998777265f989745261d06c17949418e61"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pa","authors_text":"Benjamin Steenhoek, Gaurav Mittal, Pingping Lin, Priyam Sahoo, Shengjie Ma, Xiaomin Li, Yu Hu","cross_cats":["cs.AI"],"headline":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T03:00:57Z","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation"},"references":{"count":61,"internal_anchors":14,"resolved_work":61,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"arXiv preprint arXiv:2410.20285 , year=","work_id":"e26e6ec9-37e3-47d8-b494-e0a227e77e36","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Swe-rebench: An automated pipeline for task collection and decontaminated evaluation of software engineering agents","work_id":"c819f5fe-32b6-41d1-aeb5-2d80c6fa8474","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Islem Bouzenia, Premkumar Devanbu, and Michael Pradel","work_id":"9584953a-2ac8-49b2-bcd3-44924077f86d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"2026 , note =","work_id":"ad7bad76-b98f-4522-8476-a382ae24a4b8","year":2026},{"cited_arxiv_id":"","doi":"10.5281/zenodo.19357078","is_internal_anchor":false,"ref_index":5,"title":"doi:10.5281/zenodo.19357078 , url =","work_id":"5aab64ed-4762-4aa1-922b-18ae4b5b8b27","year":null}],"snapshot_sha256":"66df3e8e7819f1fb70a7bba3a29167044596023591235646b3882339a9f38ab8"},"source":{"id":"2605.12925","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:46:32.801828Z","id":"65a2b27d-f897-4cc8-8786-4ee98826b4a1","model_set":{"reader":"grok-4.3"},"one_line_summary":"10.7% of passing SWE-agent trajectories are Lucky Passes with chaotic behaviors, and a quality score based on process references changes model rankings across eight backends.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Binary pass rates in SWE-agent tests equate chaotic trial-and-error successes with systematic ones.","strongest_claim":"Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification.","weakest_assumption":"That Prefix Tree Acceptor references built by merging multiple passing solutions accurately represent principled behavior without incorporating lucky elements from the source trajectories."}},"verdict_id":"65a2b27d-f897-4cc8-8786-4ee98826b4a1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7710c5082c6465967c4e94b3e6a845859df7f52d75a06020cc3b3e886279ca57","target":"record","created_at":"2026-05-18T03:09:10Z","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":"803d155a77ded41b300fe34dced984f3eb46a0af65c306e31432ddf0c8f2c16a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T03:00:57Z","title_canon_sha256":"07872682c0cfb5124101ff197f31db38f83c886e616dae8057e2bc39abffda39"},"schema_version":"1.0","source":{"id":"2605.12925","kind":"arxiv","version":1}},"canonical_sha256":"d5c7f00f43af164f0d4e044165e68b380302144e136f8c90ba9bcc3473f5877d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5c7f00f43af164f0d4e044165e68b380302144e136f8c90ba9bcc3473f5877d","first_computed_at":"2026-05-18T03:09:10.100969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:10.100969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5jAyHzJ6WH8ts/9WL17z+PDjmmPs7j5Ynp59GedCrqQnODuZVxSDQiFYZxm5mtpRIo9y51ZUIcopL6M1bN9CA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:10.101635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7710c5082c6465967c4e94b3e6a845859df7f52d75a06020cc3b3e886279ca57","sha256:8340795877791325c5d9ab593c559490d591b61f08eecc131ca6693052139e2b"],"state_sha256":"ffdec1d8fe338ecd3147807d19ae3e3d02a6ba89e4823e93865d2f3f2aac3d9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MxuyDVjXcwQNt1HTdyHU0LiVY/cwQdK0Az4grNKJjHpVlZKj6AThcWu4/KUd6Q7srqoOr30fYvnMyXwlCNm8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T15:41:57.169904Z","bundle_sha256":"1aebbc065c1033f2b9ea4d7eb2880191748180e8873eb81d65bb4a7eae68dc33"}}