{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z5G3RV2UDR6K37B5GXJKS3QNE4","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":"33a8b8d1f227f4c0a7f303511e2dc496482075986e131440b2b691c2b4c22b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-28T16:56:11Z","title_canon_sha256":"f035bfd62dc8b29b7b512915bf0725cb4dbeca0f57355da814260a91643f8d24"},"schema_version":"1.0","source":{"id":"2505.22583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22583","created_at":"2026-07-05T11:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22583v1","created_at":"2026-07-05T11:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22583","created_at":"2026-07-05T11:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"Z5G3RV2UDR6K","created_at":"2026-07-05T11:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"Z5G3RV2UDR6K37B5","created_at":"2026-07-05T11:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"Z5G3RV2U","created_at":"2026-07-05T11:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:fcf81258c5f1b8d7906db1973dc19d85235041bee2cab15124cea77fd332206d","target":"graph","created_at":"2026-07-05T11:11:27Z","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/2505.22583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Egor Bogomolov, Tobias Lindenbauer, Yaroslav Zharov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-28T16:56:11Z","title":"GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22583","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:bd32d41edf7c31e8fed294b51431fbac0e27c11fb242c7dad5aded6ce6a3bd27","target":"record","created_at":"2026-07-05T11:11:27Z","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":"33a8b8d1f227f4c0a7f303511e2dc496482075986e131440b2b691c2b4c22b47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-28T16:56:11Z","title_canon_sha256":"f035bfd62dc8b29b7b512915bf0725cb4dbeca0f57355da814260a91643f8d24"},"schema_version":"1.0","source":{"id":"2505.22583","kind":"arxiv","version":1}},"canonical_sha256":"cf4db8d7541c7cadfc3d35d2a96e0d273f79cf9d533217bfd684354f641eb4ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf4db8d7541c7cadfc3d35d2a96e0d273f79cf9d533217bfd684354f641eb4ea","first_computed_at":"2026-07-05T11:11:27.188201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:27.188201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zV8CjsjhhLB0E33KTPLHrQjYw0zAKcemlR6i5VNDA2tRQdsDQEOXJTbJZc3uEUjUcDwExviI2/rMG5RnwPPNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:27.188706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd32d41edf7c31e8fed294b51431fbac0e27c11fb242c7dad5aded6ce6a3bd27","sha256:fcf81258c5f1b8d7906db1973dc19d85235041bee2cab15124cea77fd332206d"],"state_sha256":"4236c09a7aec33d135abfc22a5ccff257fbfbed889dce4899313f2c33df89324"}