{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H4D4QHPR62H74RIEN3DWGCQCNQ","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":"1e8e55aa3b38233048216ebc0356c277e9225ac9985c3c9f9d6834886deef512","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-16T11:21:01Z","title_canon_sha256":"5364f74e6b7ebe7f67c37273280ca66bc9cb25c4e79294d46a993445f4b53c70"},"schema_version":"1.0","source":{"id":"2606.17799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17799","created_at":"2026-06-19T16:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17799v1","created_at":"2026-06-19T16:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17799","created_at":"2026-06-19T16:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"H4D4QHPR62H7","created_at":"2026-06-19T16:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"H4D4QHPR62H74RIE","created_at":"2026-06-19T16:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"H4D4QHPR","created_at":"2026-06-19T16:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:ee47530b9eb54f4ba03c7e7c23889b9ea1e66bed6ccd7ea9138e38f3e8413595","target":"graph","created_at":"2026-06-19T16:10:22Z","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/2606.17799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and environment into a single end-to-end score, typically computed against one reference solution, with no component-level signal for iteration. We argue that current coding benchmarks are misaligned with agentic software engineering. A coding agent in practice is not a model: it is a system harness -- a composite of models, harnesses, contexts, environments, and feedback signals, any one of which can move the benchmark score ","authors_text":"Amy Heineike, Dru Knox, Macey Baker, Maksim Shaposhnikov, Maria I. Gorinova, Rob Willoughby","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-16T11:21:01Z","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17799","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":"sha256:56c09235e77ccd68197aedc6504b7dcd442e30427e9389a278b6cb10d46ef402","target":"record","created_at":"2026-06-19T16:10:22Z","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":"1e8e55aa3b38233048216ebc0356c277e9225ac9985c3c9f9d6834886deef512","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-16T11:21:01Z","title_canon_sha256":"5364f74e6b7ebe7f67c37273280ca66bc9cb25c4e79294d46a993445f4b53c70"},"schema_version":"1.0","source":{"id":"2606.17799","kind":"arxiv","version":1}},"canonical_sha256":"3f07c81df1f68ffe45046ec7630a026c0466d66857bc28602663e0f233ebbbd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f07c81df1f68ffe45046ec7630a026c0466d66857bc28602663e0f233ebbbd1","first_computed_at":"2026-06-19T16:10:22.045594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:22.045594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9+yD1akYe2FVk5t64BaEVTIFtWvYrJxdmlj/wFo3IhO4GDGKe2mPIgs2az4Nlb/nNIzhMFNXCFXn6K6fjN0Bw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:22.045992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56c09235e77ccd68197aedc6504b7dcd442e30427e9389a278b6cb10d46ef402","sha256:ee47530b9eb54f4ba03c7e7c23889b9ea1e66bed6ccd7ea9138e38f3e8413595"],"state_sha256":"12f9f4d92f57aa9da7ae73a94f135d81e580192fe13e7035b5579f698f5cac2a"}