{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H4D4QHPR62H74RIEN3DWGCQCNQ","short_pith_number":"pith:H4D4QHPR","schema_version":"1.0","canonical_sha256":"3f07c81df1f68ffe45046ec7630a026c0466d66857bc28602663e0f233ebbbd1","source":{"kind":"arxiv","id":"2606.17799","version":1},"attestation_state":"computed","paper":{"title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Amy Heineike, Dru Knox, Macey Baker, Maksim Shaposhnikov, Maria I. Gorinova, Rob Willoughby","submitted_at":"2026-06-16T11:21:01Z","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 "},"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":"2606.17799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-16T11:21:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5364f74e6b7ebe7f67c37273280ca66bc9cb25c4e79294d46a993445f4b53c70","abstract_canon_sha256":"1e8e55aa3b38233048216ebc0356c277e9225ac9985c3c9f9d6834886deef512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:22.045992Z","signature_b64":"n9+yD1akYe2FVk5t64BaEVTIFtWvYrJxdmlj/wFo3IhO4GDGKe2mPIgs2az4Nlb/nNIzhMFNXCFXn6K6fjN0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f07c81df1f68ffe45046ec7630a026c0466d66857bc28602663e0f233ebbbd1","last_reissued_at":"2026-06-19T16:10:22.045594Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:22.045594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Amy Heineike, Dru Knox, Macey Baker, Maksim Shaposhnikov, Maria I. Gorinova, Rob Willoughby","submitted_at":"2026-06-16T11:21:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17799","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/2606.17799/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":"2606.17799","created_at":"2026-06-19T16:10:22.045655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17799v1","created_at":"2026-06-19T16:10:22.045655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17799","created_at":"2026-06-19T16:10:22.045655+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4D4QHPR62H7","created_at":"2026-06-19T16:10:22.045655+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4D4QHPR62H74RIE","created_at":"2026-06-19T16:10:22.045655+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4D4QHPR","created_at":"2026-06-19T16:10:22.045655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ","json":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ.json","graph_json":"https://pith.science/api/pith-number/H4D4QHPR62H74RIEN3DWGCQCNQ/graph.json","events_json":"https://pith.science/api/pith-number/H4D4QHPR62H74RIEN3DWGCQCNQ/events.json","paper":"https://pith.science/paper/H4D4QHPR"},"agent_actions":{"view_html":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ","download_json":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ.json","view_paper":"https://pith.science/paper/H4D4QHPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17799&json=true","fetch_graph":"https://pith.science/api/pith-number/H4D4QHPR62H74RIEN3DWGCQCNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/H4D4QHPR62H74RIEN3DWGCQCNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ/action/storage_attestation","attest_author":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ/action/author_attestation","sign_citation":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ/action/citation_signature","submit_replication":"https://pith.science/pith/H4D4QHPR62H74RIEN3DWGCQCNQ/action/replication_record"}},"created_at":"2026-06-19T16:10:22.045655+00:00","updated_at":"2026-06-19T16:10:22.045655+00:00"}