{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5CGPNGMHJ6NT322L7ISH3J6UB7","short_pith_number":"pith:5CGPNGMH","schema_version":"1.0","canonical_sha256":"e88cf699874f9b3deb4bfa247da7d40fcf0c62887181c97447eeb08cb745d475","source":{"kind":"arxiv","id":"2608.04783","version":1},"attestation_state":"computed","paper":{"title":"RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alyssa Wu, Ji Luo, Richeng Xuan, Yuexi Yang, Yuhong Liu, Zhen Qin, Zhichao Hu","submitted_at":"2026-08-05T12:49:36Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose code modifications instead of understanding the existing repository architecture. Furthermore, current LLM-as-a-Judge scalar scoring suffers from high varia"},"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":"2608.04783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-05T12:49:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a3947152ae097b4e41f423483cab8b7245e0749bc580f6fd5443b485d43ef4e","abstract_canon_sha256":"8ad73ac7cb99ef2e75e01cac4aa363b008bf1ba2ab5b8c4bbd503797ad29d1a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:06.278238Z","signature_b64":"CvNFUaTZ9jOxbcnG3El5ZDz1JaezdYDyA+m61mmk84DO78t9c4DZ7tODkXPdznXcKWUa4sQthZNtbhmYrIXcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e88cf699874f9b3deb4bfa247da7d40fcf0c62887181c97447eeb08cb745d475","last_reissued_at":"2026-08-06T01:47:06.276725Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:06.276725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alyssa Wu, Ji Luo, Richeng Xuan, Yuexi Yang, Yuhong Liu, Zhen Qin, Zhichao Hu","submitted_at":"2026-08-05T12:49:36Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose code modifications instead of understanding the existing repository architecture. Furthermore, current LLM-as-a-Judge scalar scoring suffers from high varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04783","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/2608.04783/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":"2608.04783","created_at":"2026-08-06T01:47:06.278587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04783v1","created_at":"2026-08-06T01:47:06.278587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04783","created_at":"2026-08-06T01:47:06.278587+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CGPNGMHJ6NT","created_at":"2026-08-06T01:47:06.278587+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CGPNGMHJ6NT322L","created_at":"2026-08-06T01:47:06.278587+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CGPNGMH","created_at":"2026-08-06T01:47:06.278587+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/5CGPNGMHJ6NT322L7ISH3J6UB7","json":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7.json","graph_json":"https://pith.science/api/pith-number/5CGPNGMHJ6NT322L7ISH3J6UB7/graph.json","events_json":"https://pith.science/api/pith-number/5CGPNGMHJ6NT322L7ISH3J6UB7/events.json","paper":"https://pith.science/paper/5CGPNGMH"},"agent_actions":{"view_html":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7","download_json":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7.json","view_paper":"https://pith.science/paper/5CGPNGMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04783&json=true","fetch_graph":"https://pith.science/api/pith-number/5CGPNGMHJ6NT322L7ISH3J6UB7/graph.json","fetch_events":"https://pith.science/api/pith-number/5CGPNGMHJ6NT322L7ISH3J6UB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7/action/storage_attestation","attest_author":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7/action/author_attestation","sign_citation":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7/action/citation_signature","submit_replication":"https://pith.science/pith/5CGPNGMHJ6NT322L7ISH3J6UB7/action/replication_record"}},"created_at":"2026-08-06T01:47:06.278587+00:00","updated_at":"2026-08-06T01:47:06.278587+00:00"}