{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5PXD56BA7H4PJLD3PTT6KUHS3O","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":"d35f80681186fc930709345a8b9333f237fb24b5471e0ff0488312945ddeb4c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T18:17:28Z","title_canon_sha256":"1cefa0545aca986aaf4585b61f48484df9427388be9d2c5ecad96e6f5c47fe28"},"schema_version":"1.0","source":{"id":"2605.24110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24110","created_at":"2026-05-26T01:02:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24110v1","created_at":"2026-05-26T01:02:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24110","created_at":"2026-05-26T01:02:46Z"},{"alias_kind":"pith_short_12","alias_value":"5PXD56BA7H4P","created_at":"2026-05-26T01:02:46Z"},{"alias_kind":"pith_short_16","alias_value":"5PXD56BA7H4PJLD3","created_at":"2026-05-26T01:02:46Z"},{"alias_kind":"pith_short_8","alias_value":"5PXD56BA","created_at":"2026-05-26T01:02:46Z"}],"graph_snapshots":[{"event_id":"sha256:d41dad75a88dcb6e2fec5e2a5a9cdeb893c06c42c6d88e2cb145eb1bb63de0c1","target":"graph","created_at":"2026-05-26T01:02:46Z","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/2605.24110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as requirements change? We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, states requirements through observable behavior, and uses cumulative executable tests to check new requirements and still-active prior ones. We evaluate 13 coding agents with two metrics: ","authors_text":"Haiyang Shen, Kuan Li, Liang Chen, Wendong Xu, Xuanzhong Chen, Yun Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T18:17:28Z","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24110","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":"sha256:82dc60a96ac152ff8e8983ea7740c03641b7071300a48ac610676f6b96f0e16f","target":"record","created_at":"2026-05-26T01:02:46Z","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":"d35f80681186fc930709345a8b9333f237fb24b5471e0ff0488312945ddeb4c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T18:17:28Z","title_canon_sha256":"1cefa0545aca986aaf4585b61f48484df9427388be9d2c5ecad96e6f5c47fe28"},"schema_version":"1.0","source":{"id":"2605.24110","kind":"arxiv","version":1}},"canonical_sha256":"ebee3ef820f9f8f4ac7b7ce7e550f2dbb87a1d759d479bc04e3f65f5d8616958","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebee3ef820f9f8f4ac7b7ce7e550f2dbb87a1d759d479bc04e3f65f5d8616958","first_computed_at":"2026-05-26T01:02:46.718675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:46.718675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dpo7h57Sx7dQJt1fM1gIto/tz2PRtYOWrIFTyRPKxl8XmWFOdvHvv9dTQJf0kJz2U6S8cjNKt/dE2c2grpviAg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:46.719479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82dc60a96ac152ff8e8983ea7740c03641b7071300a48ac610676f6b96f0e16f","sha256:d41dad75a88dcb6e2fec5e2a5a9cdeb893c06c42c6d88e2cb145eb1bb63de0c1"],"state_sha256":"6891e112c7024ab9bfded6fef51af8e99bf7ea44fbdd05f99442535849bc735a"}