{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N6WXARGNMN7LB5AT4MHSIHDOBG","short_pith_number":"pith:N6WXARGN","schema_version":"1.0","canonical_sha256":"6fad7044cd637eb0f413e30f241c6e0981406611127011d69818adf70a6c2cb0","source":{"kind":"arxiv","id":"2607.20852","version":1},"attestation_state":"computed","paper":{"title":"Code Monitor Red Teaming for Public-Test-Passing Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuji Ren, Jiawen Deng, Junchi Liao","submitted_at":"2026-07-23T02:23:09Z","abstract_excerpt":"Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has passed public tests, can a weaker LLM verifier identify the residual hidden bugs? We introduce Code Monitor Red Teaming, a monitor-red-teaming protocol that fixes a public-check information boundary while varying generator pressure, verifier scaffolding, and weak-to-strong capability. We instantiate it as CodeMonitorBench, spanning function-level, data-science, and workflow code. Across 71,000 generated candidates, 43"},"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":"2607.20852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T02:23:09Z","cross_cats_sorted":[],"title_canon_sha256":"4fa0eb9e60930fa0a01fe666e9ba941cbef5a7529653b71140b835d6af0b9a4d","abstract_canon_sha256":"f4a2455c81dce7aa5c175e326b3beffbe74b9bb41e07da951fe906182a773e0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:38.190366Z","signature_b64":"bJ3fOFIvc4JkCxpELKZ6SXWq0rSQ7fotVo/WGmd40/jI9veilxylRQ3bnESZC2wNKKVfq2/8JlZL7rmWwpFVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fad7044cd637eb0f413e30f241c6e0981406611127011d69818adf70a6c2cb0","last_reissued_at":"2026-07-24T00:23:38.189470Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:38.189470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code Monitor Red Teaming for Public-Test-Passing Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuji Ren, Jiawen Deng, Junchi Liao","submitted_at":"2026-07-23T02:23:09Z","abstract_excerpt":"Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has passed public tests, can a weaker LLM verifier identify the residual hidden bugs? We introduce Code Monitor Red Teaming, a monitor-red-teaming protocol that fixes a public-check information boundary while varying generator pressure, verifier scaffolding, and weak-to-strong capability. We instantiate it as CodeMonitorBench, spanning function-level, data-science, and workflow code. Across 71,000 generated candidates, 43"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20852","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/2607.20852/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":"2607.20852","created_at":"2026-07-24T00:23:38.189930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20852v1","created_at":"2026-07-24T00:23:38.189930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20852","created_at":"2026-07-24T00:23:38.189930+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6WXARGNMN7L","created_at":"2026-07-24T00:23:38.189930+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6WXARGNMN7LB5AT","created_at":"2026-07-24T00:23:38.189930+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6WXARGN","created_at":"2026-07-24T00:23:38.189930+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/N6WXARGNMN7LB5AT4MHSIHDOBG","json":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG.json","graph_json":"https://pith.science/api/pith-number/N6WXARGNMN7LB5AT4MHSIHDOBG/graph.json","events_json":"https://pith.science/api/pith-number/N6WXARGNMN7LB5AT4MHSIHDOBG/events.json","paper":"https://pith.science/paper/N6WXARGN"},"agent_actions":{"view_html":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG","download_json":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG.json","view_paper":"https://pith.science/paper/N6WXARGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20852&json=true","fetch_graph":"https://pith.science/api/pith-number/N6WXARGNMN7LB5AT4MHSIHDOBG/graph.json","fetch_events":"https://pith.science/api/pith-number/N6WXARGNMN7LB5AT4MHSIHDOBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG/action/storage_attestation","attest_author":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG/action/author_attestation","sign_citation":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG/action/citation_signature","submit_replication":"https://pith.science/pith/N6WXARGNMN7LB5AT4MHSIHDOBG/action/replication_record"}},"created_at":"2026-07-24T00:23:38.189930+00:00","updated_at":"2026-07-24T00:23:38.189930+00:00"}