{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:27HZ6HPCL637IR4EH7EQQQ2TV7","short_pith_number":"pith:27HZ6HPC","schema_version":"1.0","canonical_sha256":"d7cf9f1de25fb7f447843fc9084353aff18415e6a34474af4a8650cffe12ca51","source":{"kind":"arxiv","id":"2606.07297","version":1},"attestation_state":"computed","paper":{"title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Jialiang Liang, Kai Cai, Maoquan Wang, Ningyuan Xu, Shaoqiu Zhang, Shilin He, Siyu Ye, Wenhao Zeng, Xiaodong Gu, Yuhang Wang, Yuling Shi","submitted_at":"2026-06-05T14:08:27Z","abstract_excerpt":"Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of re"},"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":"2606.07297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-05T14:08:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"575c7e898f27cf5a76292d64607ed0045732e0416495c3eedbaf8c37c7f143d4","abstract_canon_sha256":"7c5d7ec3d5232f1fa5b740d0cad1f9853564e2e8bd7bf8a88f7c78f2be66bfe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:18.183364Z","signature_b64":"xLvS3pTvl1RBSg1tgGYogYs6XFfhxFqWZPmmwBjrZycHcnQ+vMErLsSn60i9XaA+FuM+KMyxJPhknWcUMpIzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7cf9f1de25fb7f447843fc9084353aff18415e6a34474af4a8650cffe12ca51","last_reissued_at":"2026-06-08T01:05:18.182597Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:18.182597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Jialiang Liang, Kai Cai, Maoquan Wang, Ningyuan Xu, Shaoqiu Zhang, Shilin He, Siyu Ye, Wenhao Zeng, Xiaodong Gu, Yuhang Wang, Yuling Shi","submitted_at":"2026-06-05T14:08:27Z","abstract_excerpt":"Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07297","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/2606.07297/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":"2606.07297","created_at":"2026-06-08T01:05:18.182702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07297v1","created_at":"2026-06-08T01:05:18.182702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07297","created_at":"2026-06-08T01:05:18.182702+00:00"},{"alias_kind":"pith_short_12","alias_value":"27HZ6HPCL637","created_at":"2026-06-08T01:05:18.182702+00:00"},{"alias_kind":"pith_short_16","alias_value":"27HZ6HPCL637IR4E","created_at":"2026-06-08T01:05:18.182702+00:00"},{"alias_kind":"pith_short_8","alias_value":"27HZ6HPC","created_at":"2026-06-08T01:05:18.182702+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/27HZ6HPCL637IR4EH7EQQQ2TV7","json":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7.json","graph_json":"https://pith.science/api/pith-number/27HZ6HPCL637IR4EH7EQQQ2TV7/graph.json","events_json":"https://pith.science/api/pith-number/27HZ6HPCL637IR4EH7EQQQ2TV7/events.json","paper":"https://pith.science/paper/27HZ6HPC"},"agent_actions":{"view_html":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7","download_json":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7.json","view_paper":"https://pith.science/paper/27HZ6HPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07297&json=true","fetch_graph":"https://pith.science/api/pith-number/27HZ6HPCL637IR4EH7EQQQ2TV7/graph.json","fetch_events":"https://pith.science/api/pith-number/27HZ6HPCL637IR4EH7EQQQ2TV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7/action/storage_attestation","attest_author":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7/action/author_attestation","sign_citation":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7/action/citation_signature","submit_replication":"https://pith.science/pith/27HZ6HPCL637IR4EH7EQQQ2TV7/action/replication_record"}},"created_at":"2026-06-08T01:05:18.182702+00:00","updated_at":"2026-06-08T01:05:18.182702+00:00"}