{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TAHFZLR7YSKJ23U6SX45WT6RUL","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":"dcda1959940a83519812dc0fc32eed433d565859b6e6ac3df26eeb28a4242015","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:35:15Z","title_canon_sha256":"6bfe3f766810092c11cd86a204430018e48125a2d576e50d78b5a27577f78925"},"schema_version":"1.0","source":{"id":"2606.29957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29957","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29957v1","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29957","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"TAHFZLR7YSKJ","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"TAHFZLR7YSKJ23U6","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"TAHFZLR7","created_at":"2026-06-30T02:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:a40b57b9b85529c9599a362ee1f011e0d135c31495272509fdde327c629f7905","target":"graph","created_at":"2026-06-30T02:17:42Z","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/2606.29957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with users clarifying goals, adding constraints, and correcting mistakes over multiple turns. We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions. To make real interactions verifiable, we curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes. To replay these interaction","authors_text":"Ho Hin Lee, Jiacheng Zhu, Lizhu Zhang, Serena Li, Shengzhi Li, Shirley Wu, Songlin Li, Tianhe Yu, Xiangjun Fan, Yifan Wu, Zhuokai Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:35:15Z","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29957","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":"sha256:2d7a7b703b8dbd423ccf722751b3da83c193e04526c9dfcf4c13d0ece61acff9","target":"record","created_at":"2026-06-30T02:17:42Z","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":"dcda1959940a83519812dc0fc32eed433d565859b6e6ac3df26eeb28a4242015","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:35:15Z","title_canon_sha256":"6bfe3f766810092c11cd86a204430018e48125a2d576e50d78b5a27577f78925"},"schema_version":"1.0","source":{"id":"2606.29957","kind":"arxiv","version":1}},"canonical_sha256":"980e5cae3fc4949d6e9e95f9db4fd1a2cfb42d8c60a28c6e4db1e09a60380dde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"980e5cae3fc4949d6e9e95f9db4fd1a2cfb42d8c60a28c6e4db1e09a60380dde","first_computed_at":"2026-06-30T02:17:42.728512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:42.728512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VsT4lhMbVtreBPVfmKedkR6S9mbKUoHI0bQbzRGOxRtNn+Ed954qsxWv/wam+JNDHz3xN2RHvsx/1URLLK07Bg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:42.728951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d7a7b703b8dbd423ccf722751b3da83c193e04526c9dfcf4c13d0ece61acff9","sha256:a40b57b9b85529c9599a362ee1f011e0d135c31495272509fdde327c629f7905"],"state_sha256":"aa57ab81b7a317b2fd0ec9c2ad4386a602136ae58a5227950d7e90e280e32426"}