{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H64JKEQUKFQHB2KLR7P54FQ65W","short_pith_number":"pith:H64JKEQU","schema_version":"1.0","canonical_sha256":"3fb8951214516070e94b8fdfde161eed9266c9a9a0854a1c927450eb1ac57433","source":{"kind":"arxiv","id":"2606.10417","version":1},"attestation_state":"computed","paper":{"title":"Beyond Coverage and Kill Scores: Empirically Measuring Test Suite Behavioural Gaps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Partha Protim Paul, Reid Holmes","submitted_at":"2026-06-09T04:46:32Z","abstract_excerpt":"Traditional test adequacy metrics measure a system's implementation, not whether it adheres to its expected behaviour. While developers rely heavily on code coverage and mutation testing to assess test suite quality, these metrics are fundamentally implementation-centric and cannot detect gaps between what the code is expected to do and what it actually does. Unfortunately, there has been no way to reliably detect these discrepancies; in this paper we introduce an automated proof-of-concept approach to investigate these gaps. The approach extracts expected method-level behaviours from natural "},"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":"2606.10417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-09T04:46:32Z","cross_cats_sorted":[],"title_canon_sha256":"63904ab97937d4e9383e17f6ad1ee3086eac968409d3dd1a82c0d7e3147db754","abstract_canon_sha256":"dd531b64ae5a945a728d840e1a179da0b2532d7e9434621e1f1103e09e344a1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:17.840795Z","signature_b64":"miVpOmgw2LpmyS0h6gr5QXnbWSGJUGJWmbkv7lDJmMHWAobY8q+leF9Uex87KB5JBBn623sHcc2R7sQZ3XMpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb8951214516070e94b8fdfde161eed9266c9a9a0854a1c927450eb1ac57433","last_reissued_at":"2026-06-10T01:10:17.839882Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:17.839882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Coverage and Kill Scores: Empirically Measuring Test Suite Behavioural Gaps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Partha Protim Paul, Reid Holmes","submitted_at":"2026-06-09T04:46:32Z","abstract_excerpt":"Traditional test adequacy metrics measure a system's implementation, not whether it adheres to its expected behaviour. While developers rely heavily on code coverage and mutation testing to assess test suite quality, these metrics are fundamentally implementation-centric and cannot detect gaps between what the code is expected to do and what it actually does. Unfortunately, there has been no way to reliably detect these discrepancies; in this paper we introduce an automated proof-of-concept approach to investigate these gaps. The approach extracts expected method-level behaviours from natural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10417","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/2606.10417/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":"2606.10417","created_at":"2026-06-10T01:10:17.840040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10417v1","created_at":"2026-06-10T01:10:17.840040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10417","created_at":"2026-06-10T01:10:17.840040+00:00"},{"alias_kind":"pith_short_12","alias_value":"H64JKEQUKFQH","created_at":"2026-06-10T01:10:17.840040+00:00"},{"alias_kind":"pith_short_16","alias_value":"H64JKEQUKFQHB2KL","created_at":"2026-06-10T01:10:17.840040+00:00"},{"alias_kind":"pith_short_8","alias_value":"H64JKEQU","created_at":"2026-06-10T01:10:17.840040+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/H64JKEQUKFQHB2KLR7P54FQ65W","json":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W.json","graph_json":"https://pith.science/api/pith-number/H64JKEQUKFQHB2KLR7P54FQ65W/graph.json","events_json":"https://pith.science/api/pith-number/H64JKEQUKFQHB2KLR7P54FQ65W/events.json","paper":"https://pith.science/paper/H64JKEQU"},"agent_actions":{"view_html":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W","download_json":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W.json","view_paper":"https://pith.science/paper/H64JKEQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10417&json=true","fetch_graph":"https://pith.science/api/pith-number/H64JKEQUKFQHB2KLR7P54FQ65W/graph.json","fetch_events":"https://pith.science/api/pith-number/H64JKEQUKFQHB2KLR7P54FQ65W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W/action/storage_attestation","attest_author":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W/action/author_attestation","sign_citation":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W/action/citation_signature","submit_replication":"https://pith.science/pith/H64JKEQUKFQHB2KLR7P54FQ65W/action/replication_record"}},"created_at":"2026-06-10T01:10:17.840040+00:00","updated_at":"2026-06-10T01:10:17.840040+00:00"}