{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HIJJOLUBEK3KA23GUZL5HTITJK","short_pith_number":"pith:HIJJOLUB","schema_version":"1.0","canonical_sha256":"3a12972e8122b6a06b66a657d3cd134aa73517f49daa1c4096968d811bd24339","source":{"kind":"arxiv","id":"2606.27601","version":1},"attestation_state":"computed","paper":{"title":"Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ali Asgari, Annibale Panichella, Mitchell Olsthoorn","submitted_at":"2026-06-25T23:25:53Z","abstract_excerpt":"Recently, test case selection (TCS) techniques have been explored to support the operational evaluation of deep neural networks (DNNs) under limited testing budgets, where labeling cost is a primary concern and uncovering model failures early is a key objective. Although prior studies report promising results, existing empirical evaluations focus almost exclusively on vision-based DNNs and datasets, leaving it unclear whether prior findings generalize to LLM code models. This paper presents a large-scale replication study of TCS techniques in the context of LLM code models. We re-examine estab"},"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":"2606.27601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-25T23:25:53Z","cross_cats_sorted":[],"title_canon_sha256":"3ec00d75b294405971a130d27a7f290caec4d88efac761f9fb51df8c0c3cb343","abstract_canon_sha256":"f10a8aa25c0645e564acfbdd38a5f095f63ce31c4e4750731eb07d10921b54d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:11.235408Z","signature_b64":"qNDdyj6Om+hMbC8B1rVzsOB2Gw+PxPpQL0iC4I/R9zN7bLx3VLO7c98q4Hhms4kjchIfxYKCGVBEtHoqKBa+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a12972e8122b6a06b66a657d3cd134aa73517f49daa1c4096968d811bd24339","last_reissued_at":"2026-06-29T00:14:11.234993Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:11.234993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ali Asgari, Annibale Panichella, Mitchell Olsthoorn","submitted_at":"2026-06-25T23:25:53Z","abstract_excerpt":"Recently, test case selection (TCS) techniques have been explored to support the operational evaluation of deep neural networks (DNNs) under limited testing budgets, where labeling cost is a primary concern and uncovering model failures early is a key objective. Although prior studies report promising results, existing empirical evaluations focus almost exclusively on vision-based DNNs and datasets, leaving it unclear whether prior findings generalize to LLM code models. This paper presents a large-scale replication study of TCS techniques in the context of LLM code models. We re-examine estab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27601","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/2606.27601/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":"2606.27601","created_at":"2026-06-29T00:14:11.235053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27601v1","created_at":"2026-06-29T00:14:11.235053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27601","created_at":"2026-06-29T00:14:11.235053+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIJJOLUBEK3K","created_at":"2026-06-29T00:14:11.235053+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIJJOLUBEK3KA23G","created_at":"2026-06-29T00:14:11.235053+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIJJOLUB","created_at":"2026-06-29T00:14:11.235053+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/HIJJOLUBEK3KA23GUZL5HTITJK","json":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK.json","graph_json":"https://pith.science/api/pith-number/HIJJOLUBEK3KA23GUZL5HTITJK/graph.json","events_json":"https://pith.science/api/pith-number/HIJJOLUBEK3KA23GUZL5HTITJK/events.json","paper":"https://pith.science/paper/HIJJOLUB"},"agent_actions":{"view_html":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK","download_json":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK.json","view_paper":"https://pith.science/paper/HIJJOLUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27601&json=true","fetch_graph":"https://pith.science/api/pith-number/HIJJOLUBEK3KA23GUZL5HTITJK/graph.json","fetch_events":"https://pith.science/api/pith-number/HIJJOLUBEK3KA23GUZL5HTITJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK/action/storage_attestation","attest_author":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK/action/author_attestation","sign_citation":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK/action/citation_signature","submit_replication":"https://pith.science/pith/HIJJOLUBEK3KA23GUZL5HTITJK/action/replication_record"}},"created_at":"2026-06-29T00:14:11.235053+00:00","updated_at":"2026-06-29T00:14:11.235053+00:00"}