{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W5DPPVPK646BF6OKWUOID2BRVY","short_pith_number":"pith:W5DPPVPK","schema_version":"1.0","canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","source":{"kind":"arxiv","id":"2604.04806","version":4},"attestation_state":"computed","paper":{"title":"MIRAGE: Online LLM Simulation for Microservice Dependency Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Online LLM simulation lets microservice tests generate dependency responses at runtime, reaching 99 percent status-code and response-shape fidelity where record-replay reaches only 62 and 16 percent.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Xinran Zhang","submitted_at":"2026-04-06T16:10:23Z","abstract_excerpt":"Existing approaches to microservice dependency simulation--record-replay, pattern-mining, and specification-driven stubs--generate static artifacts before test execution. These artifacts can only reproduce behaviors encoded at generation time; on error-handling and code-reasoning scenarios, which are underrepresented in typical trace corpora, record-replay achieves 0% and 12% fidelity in our evaluation.\n  We propose online LLM simulation, a runtime approach where the LLM answers each dependency request as it arrives, maintaining cross-request state throughout a test scenario. The model reads t"},"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":"2604.04806","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-06T16:10:23Z","cross_cats_sorted":[],"title_canon_sha256":"a78f05fbe96befb9133fc4ade18fadce95a0803d1e18e91741b9f038a4e1d78a","abstract_canon_sha256":"158c537a9e5853fda6b2a132a86551fce20b50b021701ae2021c7991686eaf7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:30.943999Z","signature_b64":"O+VHB9O4C8aB6ykrOsZowmLV96mflKTPHNq9+J16aVCq01Fg3DgrKAxfOnPIht3sDerJl3oFvGJkFplLBzbmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","last_reissued_at":"2026-06-29T01:14:30.943508Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:30.943508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIRAGE: Online LLM Simulation for Microservice Dependency Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Online LLM simulation lets microservice tests generate dependency responses at runtime, reaching 99 percent status-code and response-shape fidelity where record-replay reaches only 62 and 16 percent.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Xinran Zhang","submitted_at":"2026-04-06T16:10:23Z","abstract_excerpt":"Existing approaches to microservice dependency simulation--record-replay, pattern-mining, and specification-driven stubs--generate static artifacts before test execution. These artifacts can only reproduce behaviors encoded at generation time; on error-handling and code-reasoning scenarios, which are underrepresented in typical trace corpora, record-replay achieves 0% and 12% fidelity in our evaluation.\n  We propose online LLM simulation, a runtime approach where the LLM answers each dependency request as it arrives, maintaining cross-request state throughout a test scenario. The model reads t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In white-box mode, MIRAGE achieves 99% status-code and 99% response-shape fidelity, compared to 62% / 16% for record-replay. Caller integration tests produce the same pass/fail outcomes with MIRAGE as with real dependencies (8/8 scenarios).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an LLM prompted with source code and traces will produce behavior that generalizes to unseen error-handling and reasoning scenarios without introducing hallucinations or inconsistencies that would alter test outcomes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Online LLM simulation of microservice dependencies achieves 99% status-code and response-shape fidelity across 110 scenarios on three systems, far exceeding record-replay baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Online LLM simulation lets microservice tests generate dependency responses at runtime, reaching 99 percent status-code and response-shape fidelity where record-replay reaches only 62 and 16 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d4317d5ce23562f5bcc4e6e05751550fbda2a64be4cc9b17e08d356da59713e"},"source":{"id":"2604.04806","kind":"arxiv","version":4},"verdict":{"id":"36b2400d-c1bc-4994-8981-cb9689ce9696","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:39:22.817421Z","strongest_claim":"In white-box mode, MIRAGE achieves 99% status-code and 99% response-shape fidelity, compared to 62% / 16% for record-replay. Caller integration tests produce the same pass/fail outcomes with MIRAGE as with real dependencies (8/8 scenarios).","one_line_summary":"Online LLM simulation of microservice dependencies achieves 99% status-code and response-shape fidelity across 110 scenarios on three systems, far exceeding record-replay baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an LLM prompted with source code and traces will produce behavior that generalizes to unseen error-handling and reasoning scenarios without introducing hallucinations or inconsistencies that would alter test outcomes.","pith_extraction_headline":"Online LLM simulation lets microservice tests generate dependency responses at runtime, reaching 99 percent status-code and response-shape fidelity where record-replay reaches only 62 and 16 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04806/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":"2604.04806","created_at":"2026-06-29T01:14:30.943562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04806v4","created_at":"2026-06-29T01:14:30.943562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04806","created_at":"2026-06-29T01:14:30.943562+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5DPPVPK646B","created_at":"2026-06-29T01:14:30.943562+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5DPPVPK646BF6OK","created_at":"2026-06-29T01:14:30.943562+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5DPPVPK","created_at":"2026-06-29T01:14:30.943562+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/W5DPPVPK646BF6OKWUOID2BRVY","json":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY.json","graph_json":"https://pith.science/api/pith-number/W5DPPVPK646BF6OKWUOID2BRVY/graph.json","events_json":"https://pith.science/api/pith-number/W5DPPVPK646BF6OKWUOID2BRVY/events.json","paper":"https://pith.science/paper/W5DPPVPK"},"agent_actions":{"view_html":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY","download_json":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY.json","view_paper":"https://pith.science/paper/W5DPPVPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04806&json=true","fetch_graph":"https://pith.science/api/pith-number/W5DPPVPK646BF6OKWUOID2BRVY/graph.json","fetch_events":"https://pith.science/api/pith-number/W5DPPVPK646BF6OKWUOID2BRVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/action/storage_attestation","attest_author":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/action/author_attestation","sign_citation":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/action/citation_signature","submit_replication":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/action/replication_record"}},"created_at":"2026-06-29T01:14:30.943562+00:00","updated_at":"2026-06-29T01:14:30.943562+00:00"}