{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W5DPPVPK646BF6OKWUOID2BRVY","short_pith_number":"pith:W5DPPVPK","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"},"canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","source":{"kind":"arxiv","id":"2604.04806","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.04806","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.04806v4","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04806","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"W5DPPVPK646B","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"W5DPPVPK646BF6OK","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"W5DPPVPK","created_at":"2026-06-29T01:14:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W5DPPVPK646BF6OKWUOID2BRVY","target":"record","payload":{"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"},"canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","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"},"source_kind":"arxiv","source_id":"2604.04806","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-29T01:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTj5fPsukXBeGDwYF3Kar6YVLKOpqICvcFb+TFm+mrofmLGVlSkCfvxIGGEOWtQOR0UOqyqkobElci5JJUFqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:35:51.345403Z"},"content_sha256":"433ca9ca363b1457b180a50accbc98520f64325cf86c381ea4729ab6a223f0f5","schema_version":"1.0","event_id":"sha256:433ca9ca363b1457b180a50accbc98520f64325cf86c381ea4729ab6a223f0f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W5DPPVPK646BF6OKWUOID2BRVY","target":"graph","payload":{"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"},"verdict_id":"36b2400d-c1bc-4994-8981-cb9689ce9696"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-29T01:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XoZITP8nnZVmYMqBnRUoBvLD8vB4YARc9mBGQIHrZqhKtrNyrU4bPigco9EiVUV1WU1/DkdTHpfhrs71S4+eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:35:51.346549Z"},"content_sha256":"f295f6e43320c95fcdddd8570b259881d6ce765a5e0dd78104ee955e29ac949e","schema_version":"1.0","event_id":"sha256:f295f6e43320c95fcdddd8570b259881d6ce765a5e0dd78104ee955e29ac949e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/bundle.json","state_url":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5DPPVPK646BF6OKWUOID2BRVY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T22:35:51Z","links":{"resolver":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY","bundle":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/bundle.json","state":"https://pith.science/pith/W5DPPVPK646BF6OKWUOID2BRVY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5DPPVPK646BF6OKWUOID2BRVY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W5DPPVPK646BF6OKWUOID2BRVY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"158c537a9e5853fda6b2a132a86551fce20b50b021701ae2021c7991686eaf7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-06T16:10:23Z","title_canon_sha256":"a78f05fbe96befb9133fc4ade18fadce95a0803d1e18e91741b9f038a4e1d78a"},"schema_version":"1.0","source":{"id":"2604.04806","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.04806","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.04806v4","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04806","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"W5DPPVPK646B","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"W5DPPVPK646BF6OK","created_at":"2026-06-29T01:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"W5DPPVPK","created_at":"2026-06-29T01:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:f295f6e43320c95fcdddd8570b259881d6ce765a5e0dd78104ee955e29ac949e","target":"graph","created_at":"2026-06-29T01:14:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"9d4317d5ce23562f5bcc4e6e05751550fbda2a64be4cc9b17e08d356da59713e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.04806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xinran Zhang","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-06T16:10:23Z","title":"MIRAGE: Online LLM Simulation for Microservice Dependency Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.04806","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-10T19:39:22.817421Z","id":"36b2400d-c1bc-4994-8981-cb9689ce9696","model_set":{"reader":"grok-4.3"},"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","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.","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).","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."}},"verdict_id":"36b2400d-c1bc-4994-8981-cb9689ce9696"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:433ca9ca363b1457b180a50accbc98520f64325cf86c381ea4729ab6a223f0f5","target":"record","created_at":"2026-06-29T01:14:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"158c537a9e5853fda6b2a132a86551fce20b50b021701ae2021c7991686eaf7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-06T16:10:23Z","title_canon_sha256":"a78f05fbe96befb9133fc4ade18fadce95a0803d1e18e91741b9f038a4e1d78a"},"schema_version":"1.0","source":{"id":"2604.04806","kind":"arxiv","version":4}},"canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b746f7d5eaf73c12f9cab51c81e831ae05f2f7f9064b96e8e94a9f42105fc8d6","first_computed_at":"2026-06-29T01:14:30.943508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:30.943508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+VHB9O4C8aB6ykrOsZowmLV96mflKTPHNq9+J16aVCq01Fg3DgrKAxfOnPIht3sDerJl3oFvGJkFplLBzbmAA==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:30.943999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.04806","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:433ca9ca363b1457b180a50accbc98520f64325cf86c381ea4729ab6a223f0f5","sha256:f295f6e43320c95fcdddd8570b259881d6ce765a5e0dd78104ee955e29ac949e"],"state_sha256":"6c6abb019fdb3ee5d8baf0160b6bef54d029ead28123a3aa530a03339d12a7d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ltcNAnDmog2zA5LBli/VZTGIJX9ht6C3HjZkRCk7hU+VETkaffcRlExT/O3t0GpRzThrqo9MRuZy77YraQzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:35:51.354047Z","bundle_sha256":"5781137dc40c82b33d877a47226bb31c59dbdfaab3d02c51108985be64d68f5f"}}