{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X7B3LEK65DFUZ55BTMK7SG54NY","short_pith_number":"pith:X7B3LEK6","schema_version":"1.0","canonical_sha256":"bfc3b5915ee8cb4cf7a19b15f91bbc6e0130e9778fb1804358acc7e48044cf01","source":{"kind":"arxiv","id":"2607.01980","version":1},"attestation_state":"computed","paper":{"title":"Epic-Organized vs. Requirement-Aligned Gherkin: An Empirical Evaluation of LLM-Based Acceptance Criteria Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fran\\c{c}ois Christophe, Jussi Rasku, Mateen Abbasi, Pekka Abrahamsson, Shahbaz Siddeeq, Tommi Mikkonen, Zheying Zhang","submitted_at":"2026-07-02T10:12:29Z","abstract_excerpt":"Automated authoring of Gherkin Behavior-Driven Development (BDD) acceptance criteria remains a manual bottleneck in requirements engineering. This study investigates whether epic-organized LLM-generated Gherkin produces higher quality and coverage than requirement-aligned generation. We compare our Timeless (an epic-organized LLM pipeline) approach against a naive large language model (LLM) baseline on four requirements documents (107 requirements) from the PURE dataset. Evaluation covers structural metrics, automated requirement coverage via TF-IDF and dense embeddings, and blind expert asses"},"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":"2607.01980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-02T10:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"119da5738ba7dac3122e911c1702ab5a6e27796a55bb74e856b4e689a6152abd","abstract_canon_sha256":"f47f85c740a9ac594e92de46d0269a031db7c41d357f6c3139d2f573a562cdce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:36.180679Z","signature_b64":"ffzkn1YozD7YXCRdu9dvj4HVnbm1kdah7DATzmz9A0+uZZR2xkkD0qSEeBHxKxNeDqciqx3uM2Nm5LQ9dBOCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfc3b5915ee8cb4cf7a19b15f91bbc6e0130e9778fb1804358acc7e48044cf01","last_reissued_at":"2026-07-03T01:17:36.180242Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:36.180242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epic-Organized vs. Requirement-Aligned Gherkin: An Empirical Evaluation of LLM-Based Acceptance Criteria Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fran\\c{c}ois Christophe, Jussi Rasku, Mateen Abbasi, Pekka Abrahamsson, Shahbaz Siddeeq, Tommi Mikkonen, Zheying Zhang","submitted_at":"2026-07-02T10:12:29Z","abstract_excerpt":"Automated authoring of Gherkin Behavior-Driven Development (BDD) acceptance criteria remains a manual bottleneck in requirements engineering. This study investigates whether epic-organized LLM-generated Gherkin produces higher quality and coverage than requirement-aligned generation. We compare our Timeless (an epic-organized LLM pipeline) approach against a naive large language model (LLM) baseline on four requirements documents (107 requirements) from the PURE dataset. Evaluation covers structural metrics, automated requirement coverage via TF-IDF and dense embeddings, and blind expert asses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01980","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/2607.01980/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":"2607.01980","created_at":"2026-07-03T01:17:36.180304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01980v1","created_at":"2026-07-03T01:17:36.180304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01980","created_at":"2026-07-03T01:17:36.180304+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7B3LEK65DFU","created_at":"2026-07-03T01:17:36.180304+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7B3LEK65DFUZ55B","created_at":"2026-07-03T01:17:36.180304+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7B3LEK6","created_at":"2026-07-03T01:17:36.180304+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/X7B3LEK65DFUZ55BTMK7SG54NY","json":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY.json","graph_json":"https://pith.science/api/pith-number/X7B3LEK65DFUZ55BTMK7SG54NY/graph.json","events_json":"https://pith.science/api/pith-number/X7B3LEK65DFUZ55BTMK7SG54NY/events.json","paper":"https://pith.science/paper/X7B3LEK6"},"agent_actions":{"view_html":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY","download_json":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY.json","view_paper":"https://pith.science/paper/X7B3LEK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01980&json=true","fetch_graph":"https://pith.science/api/pith-number/X7B3LEK65DFUZ55BTMK7SG54NY/graph.json","fetch_events":"https://pith.science/api/pith-number/X7B3LEK65DFUZ55BTMK7SG54NY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY/action/storage_attestation","attest_author":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY/action/author_attestation","sign_citation":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY/action/citation_signature","submit_replication":"https://pith.science/pith/X7B3LEK65DFUZ55BTMK7SG54NY/action/replication_record"}},"created_at":"2026-07-03T01:17:36.180304+00:00","updated_at":"2026-07-03T01:17:36.180304+00:00"}