{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NBJR3HNTYBBLAB23T7GOZMONH2","short_pith_number":"pith:NBJR3HNT","schema_version":"1.0","canonical_sha256":"68531d9db3c042b0075b9fccecb1cd3eb3f508875fca8e8d966cf5a4e544166c","source":{"kind":"arxiv","id":"2412.08581","version":1},"attestation_state":"computed","paper":{"title":"Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chong Wang, Chunyang Chen, Liming Zhu, Qinghua Lu, Xiwei Xu, Yanqi Su, Zhenchang Xing","submitted_at":"2024-12-11T17:57:23Z","abstract_excerpt":"Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from the end-user's perspective. Although ET has proven effective in system-level testing of interactive systems, the need for manual execution has hindered large-scale adoption. In this work, we explore the feasibility, challenges and road ahead of automated scenario-based ET (a.k.a soap opera testing). We conduct a formative study, identifying key insights for effective manual soap opera testing and challenges in automating the process. We then develop a mult"},"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":"2412.08581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-11T17:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"03e3e6b5b9a78f6878da78ceec1a0b70fb31b3ef28bd15ef5ca5dc5e754ea628","abstract_canon_sha256":"e7f76cf1aaec3b0dfc80bf833dca30e7a48feadbead21f12c2b41949b3b75d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:52.226013Z","signature_b64":"8kFEoI9i3+7nq0urE2ialWUmfhtfnu4/BkA65VMCanOnedJe8vku4k6pzlWLhjGcCrQzbT0ws+yXUc8FrRcFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68531d9db3c042b0075b9fccecb1cd3eb3f508875fca8e8d966cf5a4e544166c","last_reissued_at":"2026-07-05T09:47:52.225550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:52.225550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chong Wang, Chunyang Chen, Liming Zhu, Qinghua Lu, Xiwei Xu, Yanqi Su, Zhenchang Xing","submitted_at":"2024-12-11T17:57:23Z","abstract_excerpt":"Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from the end-user's perspective. Although ET has proven effective in system-level testing of interactive systems, the need for manual execution has hindered large-scale adoption. In this work, we explore the feasibility, challenges and road ahead of automated scenario-based ET (a.k.a soap opera testing). We conduct a formative study, identifying key insights for effective manual soap opera testing and challenges in automating the process. We then develop a mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08581","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/2412.08581/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":"2412.08581","created_at":"2026-07-05T09:47:52.225608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08581v1","created_at":"2026-07-05T09:47:52.225608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08581","created_at":"2026-07-05T09:47:52.225608+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBJR3HNTYBBL","created_at":"2026-07-05T09:47:52.225608+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBJR3HNTYBBLAB23","created_at":"2026-07-05T09:47:52.225608+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBJR3HNT","created_at":"2026-07-05T09:47:52.225608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16136","citing_title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","ref_index":93,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2","json":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2.json","graph_json":"https://pith.science/api/pith-number/NBJR3HNTYBBLAB23T7GOZMONH2/graph.json","events_json":"https://pith.science/api/pith-number/NBJR3HNTYBBLAB23T7GOZMONH2/events.json","paper":"https://pith.science/paper/NBJR3HNT"},"agent_actions":{"view_html":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2","download_json":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2.json","view_paper":"https://pith.science/paper/NBJR3HNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08581&json=true","fetch_graph":"https://pith.science/api/pith-number/NBJR3HNTYBBLAB23T7GOZMONH2/graph.json","fetch_events":"https://pith.science/api/pith-number/NBJR3HNTYBBLAB23T7GOZMONH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2/action/storage_attestation","attest_author":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2/action/author_attestation","sign_citation":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2/action/citation_signature","submit_replication":"https://pith.science/pith/NBJR3HNTYBBLAB23T7GOZMONH2/action/replication_record"}},"created_at":"2026-07-05T09:47:52.225608+00:00","updated_at":"2026-07-05T09:47:52.225608+00:00"}