{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QBOA5EG5MH4NA4XTE3G2RH4WKQ","short_pith_number":"pith:QBOA5EG5","schema_version":"1.0","canonical_sha256":"805c0e90dd61f8d072f326cda89f96543aafc1a3c9b414975f85e2bcf8e9fcf3","source":{"kind":"arxiv","id":"2605.21930","version":1},"attestation_state":"computed","paper":{"title":"PITMuS: A Tool for Automated Bug Dataset Generation via Source-Level Mutant Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Soneya Binta Hossain, Tasfia Tasnim","submitted_at":"2026-05-21T02:59:19Z","abstract_excerpt":"LLM-based software engineering increasingly depends on executable, context-rich bug artifacts: paired correct and buggy code, methods under test (MUTs), documentation, and metadata. These artifacts support the training and evaluation of automated bug localization and repair techniques, testing and test oracle generation methods, and documentation-driven automation. Although curated benchmarks (e.g., Defects4J) remain valuable, they are static and increasingly vulnerable to contamination as code models are trained on large public corpora. A complementary strategy is to generate fresh, cutoff-aw"},"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":"2605.21930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-21T02:59:19Z","cross_cats_sorted":[],"title_canon_sha256":"77b0136c8618b6baf681b4bcc9cbb7184da316d97ee7a1a6f1dbefbf557c5e7f","abstract_canon_sha256":"d6f171b968599239d5200f666f287a0019256ef0b2632c14447332195d08ab75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:15.393979Z","signature_b64":"ufYgINf0GmevtoUf1Z+A2e7O6aOtGQLWFs+qqDSJWm8Ipu8faRcJHKs8eyRQfu8jHNsV0IrVLU6Jowe0pLt6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"805c0e90dd61f8d072f326cda89f96543aafc1a3c9b414975f85e2bcf8e9fcf3","last_reissued_at":"2026-05-22T01:04:15.393160Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:15.393160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PITMuS: A Tool for Automated Bug Dataset Generation via Source-Level Mutant Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Soneya Binta Hossain, Tasfia Tasnim","submitted_at":"2026-05-21T02:59:19Z","abstract_excerpt":"LLM-based software engineering increasingly depends on executable, context-rich bug artifacts: paired correct and buggy code, methods under test (MUTs), documentation, and metadata. These artifacts support the training and evaluation of automated bug localization and repair techniques, testing and test oracle generation methods, and documentation-driven automation. Although curated benchmarks (e.g., Defects4J) remain valuable, they are static and increasingly vulnerable to contamination as code models are trained on large public corpora. A complementary strategy is to generate fresh, cutoff-aw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21930","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/2605.21930/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":"2605.21930","created_at":"2026-05-22T01:04:15.393296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21930v1","created_at":"2026-05-22T01:04:15.393296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21930","created_at":"2026-05-22T01:04:15.393296+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBOA5EG5MH4N","created_at":"2026-05-22T01:04:15.393296+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBOA5EG5MH4NA4XT","created_at":"2026-05-22T01:04:15.393296+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBOA5EG5","created_at":"2026-05-22T01:04:15.393296+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/QBOA5EG5MH4NA4XTE3G2RH4WKQ","json":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ.json","graph_json":"https://pith.science/api/pith-number/QBOA5EG5MH4NA4XTE3G2RH4WKQ/graph.json","events_json":"https://pith.science/api/pith-number/QBOA5EG5MH4NA4XTE3G2RH4WKQ/events.json","paper":"https://pith.science/paper/QBOA5EG5"},"agent_actions":{"view_html":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ","download_json":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ.json","view_paper":"https://pith.science/paper/QBOA5EG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21930&json=true","fetch_graph":"https://pith.science/api/pith-number/QBOA5EG5MH4NA4XTE3G2RH4WKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QBOA5EG5MH4NA4XTE3G2RH4WKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ/action/storage_attestation","attest_author":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ/action/author_attestation","sign_citation":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ/action/citation_signature","submit_replication":"https://pith.science/pith/QBOA5EG5MH4NA4XTE3G2RH4WKQ/action/replication_record"}},"created_at":"2026-05-22T01:04:15.393296+00:00","updated_at":"2026-05-22T01:04:15.393296+00:00"}