{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LJS2VB7XDGSZNWDGRTDIWKS7WH","short_pith_number":"pith:LJS2VB7X","canonical_record":{"source":{"id":"2506.09289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"df0887d63628893f5894a0a7a5c03e4fd5fb4f61d9538752a58baa856ec3de6c","abstract_canon_sha256":"fdb86117f6820c495f8eb62e96a737c3e7d242a9980c9a50b6c34f2c9f5e8cf6"},"schema_version":"1.0"},"canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","source":{"kind":"arxiv","id":"2506.09289","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09289","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09289v1","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09289","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"LJS2VB7XDGSZ","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"LJS2VB7XDGSZNWDG","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"LJS2VB7X","created_at":"2026-07-05T11:19:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LJS2VB7XDGSZNWDGRTDIWKS7WH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.09289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"df0887d63628893f5894a0a7a5c03e4fd5fb4f61d9538752a58baa856ec3de6c","abstract_canon_sha256":"fdb86117f6820c495f8eb62e96a737c3e7d242a9980c9a50b6c34f2c9f5e8cf6"},"schema_version":"1.0"},"canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:34.237162Z","signature_b64":"gX+oWjxESVZHxMVbDwt3ZQYJy539/LN49yz/fi87Rrv1FhwLZmWqFe1mf0bzqR0AnQ1gWueeZyB27ms8eGxwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","last_reissued_at":"2026-07-05T11:19:34.236606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:34.236606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.09289","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":"2026-07-05T11:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYuEW/FzpfufCy1XnM3JEfZYaErOsAv4bsWNYyRiHTummyGD21sUK6MFscNf7O2w/F6xsltqnpmTcYsVhfi8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T21:53:01.122725Z"},"content_sha256":"39d72f650042ed27843e8e5ef8a9c5e75c08350e81f5e7f3e934e8018d7bf055","schema_version":"1.0","event_id":"sha256:39d72f650042ed27843e8e5ef8a9c5e75c08350e81f5e7f3e934e8018d7bf055"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LJS2VB7XDGSZNWDGRTDIWKS7WH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Boxi Yu, Daniel Kang, Pinjia He, Yuxuan Zhu","submitted_at":"2025-06-10T22:56:49Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To address this challenge, we introduce UTGenerator, an LLM-driven test case generator that automatically ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09289","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/2506.09289/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":"2026-07-05T11:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AP+q9g1nLRdc0fkSNWuH+n0PnIK57CB9CIDTFFLboe75JKIodJZqkRZkn/+0a0daDKOqWk5su1RNy8SsWCxGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T21:53:01.123090Z"},"content_sha256":"bf43bd724bc6d5b2b150f892c4771f4ff87974d727135cd8cf5037348ae89d72","schema_version":"1.0","event_id":"sha256:bf43bd724bc6d5b2b150f892c4771f4ff87974d727135cd8cf5037348ae89d72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/bundle.json","state_url":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/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":"2026-07-26T21:53:01Z","links":{"resolver":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH","bundle":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/bundle.json","state":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LJS2VB7XDGSZNWDGRTDIWKS7WH","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":"fdb86117f6820c495f8eb62e96a737c3e7d242a9980c9a50b6c34f2c9f5e8cf6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","title_canon_sha256":"df0887d63628893f5894a0a7a5c03e4fd5fb4f61d9538752a58baa856ec3de6c"},"schema_version":"1.0","source":{"id":"2506.09289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09289","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09289v1","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09289","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"LJS2VB7XDGSZ","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"LJS2VB7XDGSZNWDG","created_at":"2026-07-05T11:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"LJS2VB7X","created_at":"2026-07-05T11:19:34Z"}],"graph_snapshots":[{"event_id":"sha256:bf43bd724bc6d5b2b150f892c4771f4ff87974d727135cd8cf5037348ae89d72","target":"graph","created_at":"2026-07-05T11:19:34Z","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/2506.09289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To address this challenge, we introduce UTGenerator, an LLM-driven test case generator that automatically ana","authors_text":"Boxi Yu, Daniel Kang, Pinjia He, Yuxuan Zhu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09289","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":"sha256:39d72f650042ed27843e8e5ef8a9c5e75c08350e81f5e7f3e934e8018d7bf055","target":"record","created_at":"2026-07-05T11:19:34Z","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":"fdb86117f6820c495f8eb62e96a737c3e7d242a9980c9a50b6c34f2c9f5e8cf6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","title_canon_sha256":"df0887d63628893f5894a0a7a5c03e4fd5fb4f61d9538752a58baa856ec3de6c"},"schema_version":"1.0","source":{"id":"2506.09289","kind":"arxiv","version":1}},"canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","first_computed_at":"2026-07-05T11:19:34.236606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:34.236606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gX+oWjxESVZHxMVbDwt3ZQYJy539/LN49yz/fi87Rrv1FhwLZmWqFe1mf0bzqR0AnQ1gWueeZyB27ms8eGxwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:34.237162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d72f650042ed27843e8e5ef8a9c5e75c08350e81f5e7f3e934e8018d7bf055","sha256:bf43bd724bc6d5b2b150f892c4771f4ff87974d727135cd8cf5037348ae89d72"],"state_sha256":"6de5de7fd72da4ee4172e3ec9d9c93b6c0fc1453f4ec935d7bb6563afea30434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UG96GQCj7XKkP/ovnmUdLO3oY3r7bJvK9avZhilxwW5S9AFF72u3yn8j79NJq22hAgifEHpPiWUA6HTXlJ7kDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T21:53:01.125246Z","bundle_sha256":"04c89172c16534c2a93c7055e0126cc19769dae866a6f84261d8ca9877ef7cc3"}}