{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FRLE5TP5BO3H3BX7ZXY67SL75S","short_pith_number":"pith:FRLE5TP5","schema_version":"1.0","canonical_sha256":"2c564ecdfd0bb67d86ffcdf1efc97fec9fab20e8ab857b506c8844de4dc38352","source":{"kind":"arxiv","id":"2501.10200","version":1},"attestation_state":"computed","paper":{"title":"Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Annibale Panichella, Azat Abdullin, Pouria Derakhshanfar","submitted_at":"2025-01-17T13:48:32Z","abstract_excerpt":"Generating tests automatically is a key and ongoing area of focus in software engineering research. The emergence of Large Language Models (LLMs) has opened up new opportunities, given their ability to perform a wide spectrum of tasks. However, the effectiveness of LLM-based approaches compared to traditional techniques such as search-based software testing (SBST) and symbolic execution remains uncertain. In this paper, we perform an extensive study of automatic test generation approaches based on three tools: EvoSuite for SBST, Kex for symbolic execution, and TestSpark for LLM-based test gene"},"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":"2501.10200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-17T13:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"35fd7c2c84de4a07c2a921f6a33bce843f151927b23e2d81434cf88d0d8f99e0","abstract_canon_sha256":"79665b816fbbb2bbf153ee250916a6f0130714c57082327b0587d6f0caee4280"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:18.212092Z","signature_b64":"rKqs1QwnM2/nRUbpQ9zLoNU96l5WoxdRhGlvw/nzh9EcUTu1nHP5Zp+qEPgyiubJ+kKsbXjzUcNZzqVpbBJzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c564ecdfd0bb67d86ffcdf1efc97fec9fab20e8ab857b506c8844de4dc38352","last_reissued_at":"2026-07-05T10:02:18.211692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:18.211692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Annibale Panichella, Azat Abdullin, Pouria Derakhshanfar","submitted_at":"2025-01-17T13:48:32Z","abstract_excerpt":"Generating tests automatically is a key and ongoing area of focus in software engineering research. The emergence of Large Language Models (LLMs) has opened up new opportunities, given their ability to perform a wide spectrum of tasks. However, the effectiveness of LLM-based approaches compared to traditional techniques such as search-based software testing (SBST) and symbolic execution remains uncertain. In this paper, we perform an extensive study of automatic test generation approaches based on three tools: EvoSuite for SBST, Kex for symbolic execution, and TestSpark for LLM-based test gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10200","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/2501.10200/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":"2501.10200","created_at":"2026-07-05T10:02:18.211747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10200v1","created_at":"2026-07-05T10:02:18.211747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10200","created_at":"2026-07-05T10:02:18.211747+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRLE5TP5BO3H","created_at":"2026-07-05T10:02:18.211747+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRLE5TP5BO3H3BX7","created_at":"2026-07-05T10:02:18.211747+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRLE5TP5","created_at":"2026-07-05T10:02:18.211747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.22880","citing_title":"Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S","json":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S.json","graph_json":"https://pith.science/api/pith-number/FRLE5TP5BO3H3BX7ZXY67SL75S/graph.json","events_json":"https://pith.science/api/pith-number/FRLE5TP5BO3H3BX7ZXY67SL75S/events.json","paper":"https://pith.science/paper/FRLE5TP5"},"agent_actions":{"view_html":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S","download_json":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S.json","view_paper":"https://pith.science/paper/FRLE5TP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10200&json=true","fetch_graph":"https://pith.science/api/pith-number/FRLE5TP5BO3H3BX7ZXY67SL75S/graph.json","fetch_events":"https://pith.science/api/pith-number/FRLE5TP5BO3H3BX7ZXY67SL75S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S/action/storage_attestation","attest_author":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S/action/author_attestation","sign_citation":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S/action/citation_signature","submit_replication":"https://pith.science/pith/FRLE5TP5BO3H3BX7ZXY67SL75S/action/replication_record"}},"created_at":"2026-07-05T10:02:18.211747+00:00","updated_at":"2026-07-05T10:02:18.211747+00:00"}