{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z5G3RV2UDR6K37B5GXJKS3QNE4","short_pith_number":"pith:Z5G3RV2U","schema_version":"1.0","canonical_sha256":"cf4db8d7541c7cadfc3d35d2a96e0d273f79cf9d533217bfd684354f641eb4ea","source":{"kind":"arxiv","id":"2505.22583","version":1},"attestation_state":"computed","paper":{"title":"GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Tobias Lindenbauer, Yaroslav Zharov","submitted_at":"2025-05-28T16:56:11Z","abstract_excerpt":"Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS) operations. To address this issue, we present GitGoodBench, a novel benchmark for evaluating AI agent performance on VCS tasks. GitGoodBench covers three core Git scenarios extracted from permissive open-source Python, Java, and Kotlin repositories. Our benchmark provides three datasets: a comprehensive evaluation suite (900 samples), a rapid prototyping version (120"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.22583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-28T16:56:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f035bfd62dc8b29b7b512915bf0725cb4dbeca0f57355da814260a91643f8d24","abstract_canon_sha256":"33a8b8d1f227f4c0a7f303511e2dc496482075986e131440b2b691c2b4c22b47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:27.188706Z","signature_b64":"zV8CjsjhhLB0E33KTPLHrQjYw0zAKcemlR6i5VNDA2tRQdsDQEOXJTbJZc3uEUjUcDwExviI2/rMG5RnwPPNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4db8d7541c7cadfc3d35d2a96e0d273f79cf9d533217bfd684354f641eb4ea","last_reissued_at":"2026-07-05T11:11:27.188201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:27.188201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Tobias Lindenbauer, Yaroslav Zharov","submitted_at":"2025-05-28T16:56:11Z","abstract_excerpt":"Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS) operations. To address this issue, we present GitGoodBench, a novel benchmark for evaluating AI agent performance on VCS tasks. GitGoodBench covers three core Git scenarios extracted from permissive open-source Python, Java, and Kotlin repositories. Our benchmark provides three datasets: a comprehensive evaluation suite (900 samples), a rapid prototyping version (120"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22583","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/2505.22583/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.22583","created_at":"2026-07-05T11:11:27.188261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22583v1","created_at":"2026-07-05T11:11:27.188261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22583","created_at":"2026-07-05T11:11:27.188261+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5G3RV2UDR6K","created_at":"2026-07-05T11:11:27.188261+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5G3RV2UDR6K37B5","created_at":"2026-07-05T11:11:27.188261+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5G3RV2U","created_at":"2026-07-05T11:11:27.188261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25890","citing_title":"Merge-Bench: Resolve Merge Conflicts with Large Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4","json":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4.json","graph_json":"https://pith.science/api/pith-number/Z5G3RV2UDR6K37B5GXJKS3QNE4/graph.json","events_json":"https://pith.science/api/pith-number/Z5G3RV2UDR6K37B5GXJKS3QNE4/events.json","paper":"https://pith.science/paper/Z5G3RV2U"},"agent_actions":{"view_html":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4","download_json":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4.json","view_paper":"https://pith.science/paper/Z5G3RV2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22583&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5G3RV2UDR6K37B5GXJKS3QNE4/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5G3RV2UDR6K37B5GXJKS3QNE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4/action/storage_attestation","attest_author":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4/action/author_attestation","sign_citation":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4/action/citation_signature","submit_replication":"https://pith.science/pith/Z5G3RV2UDR6K37B5GXJKS3QNE4/action/replication_record"}},"created_at":"2026-07-05T11:11:27.188261+00:00","updated_at":"2026-07-05T11:11:27.188261+00:00"}