{"as_of":"2026-08-18T09:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9f3a3408f63ae59e60ca9501280f9fcc9a35c9355719997a242b60583dc086bc","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:59:12.475245Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.03265/citation-record","integrity":"/paper/2505.03265/integrity","json":"/paper/2505.03265/citation-record.json","paper":"/paper/2505.03265"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.360501Z","title":"The state-of-practice in require- ments specification: an extended interview study at 12 companies","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.360501Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:1b689403fe840c56919e8f7642b14bccd6f25281c063b6601d26f5f03559d444","observation_id":"454ce293-768f-4e82-994d-0f218fef56ce","resolution":{"observed_at":"2026-08-15T23:59:12.360501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-15T23:59:12.365131Z","title":"DeepSeek-V3 Technical Report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.365131Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:2a455eee6f81c8e939de859dbd753005fd462e21fceba3894c22fd6cff0cc344","observation_id":"1ae80e22-5223-48ac-a984-82a94146cddb","resolution":{"observed_at":"2026-08-15T23:59:12.365131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5619.15556","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.846408Z","title":"Design science as nested problem solving","venue":null,"work_id":"276d20a6-385f-4cbc-964e-c52599fcc5fd","year":2009},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.369020Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:84cdb0ddc240c7a919ed7bcfc68cdfba064c70713c9178a9aab6d808f2757b29","observation_id":"88df4f0a-0308-4fd6-9d73-a2069add83ba","resolution":{"observed_at":"2026-08-15T23:59:12.852581Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09608","last_updated":"2023-05-16T17:00:36Z","snapshot_observed_at":"2026-08-18T08:03:23.676074Z","submitted_at":"2023-05-16T17:00:36Z","title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs","version":1},"cited_work":{"arxiv_id":"2305.09608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.09608","snapshot_observed_at":"2026-08-15T23:59:12.778337Z","title":"Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs","venue":"cs.SE","work_id":"da9ad294-38e2-43bb-9346-7fe43a95b2e5","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.373101Z"},"links":{"cited_paper":"/paper/2305.09608","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:0a694bc4406e4ad798de8b4a3cde6bf0c9b0863d87adc64504f4157fc7b790ff","observation_id":"d780f2eb-d3ac-439b-abc6-d162f68aeb1d","resolution":{"observed_at":"2026-08-15T23:59:12.782643Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.376996Z","title":"Multi-type requirements traceability prediction by code data augmentation and fine-tuning MS-CodeBERT","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.376996Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:ea362045684686ef058aa0b1f05c39b0f3bf2db3348e103464a27e2fdd632bdc","observation_id":"8ddf912a-64ef-4344-9f75-d5f07558d53c","resolution":{"observed_at":"2026-08-15T23:59:12.376996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.380849Z","title":"EfficientExtractionofTechnicalRequirementsApplying Data Augmentation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.380849Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:729956ff0b7c09064f33980e73c3e161957e455f4ad4e1830e32778f1bc9ad58","observation_id":"e75772de-3350-4b6f-a485-307971c7f132","resolution":{"observed_at":"2026-08-15T23:59:12.380849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-15T23:59:12.385094Z","title":"Language Models are Few-Shot Learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.385094Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:7b4918704a70d1bd9333cc08a3753dd113011077389332a0d3ae51dcd78b57d9","observation_id":"8ddeb7a6-2b10-48c1-91e6-d035fcb86e34","resolution":{"observed_at":"2026-08-15T23:59:12.385094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.063256Z","title":"Few-shot fine-tuning vs. in-context learning: A fair comparison and evaluation","venue":null,"work_id":"a025a4ed-3dd7-40d9-93fb-c927d5a4789d","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.388849Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:1bd23a891c13904ef37f58e6867538b2b19f515680567c23d6dba9937ab1f4be","observation_id":"184410ce-009f-4dec-a59e-565476263203","resolution":{"observed_at":"2026-08-15T23:59:13.067492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.050860Z","title":"Natural Language Processing for Requirements Engineering: A Systematic Mapping Study","venue":null,"work_id":"09d7eed6-df40-4113-aeca-ccd558d3265b","year":2022},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.392713Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:05cd20152b7274f23169271c5dfc1e7b7fee82528044061a61b2b92d09778824","observation_id":"72b4f816-73d0-4480-bd25-0d1eb917ad86","resolution":{"observed_at":"2026-08-15T23:59:13.054777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.038415Z","title":"Machine learning for requirements engineering (ML4RE): A systematic literature review complemented by practitioners’ voices from Stack Overflow","venue":null,"work_id":"404f177e-7f48-4746-8671-5fe2ba278863","year":2024},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.396463Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:4a74eb97b58304303ea6ecaf40fe0c938dda46fbc69e935fa6f38d44e3b089ec","observation_id":"e5721dd1-c37e-4b70-af08-e6fa4c9cee40","resolution":{"observed_at":"2026-08-15T23:59:13.042583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.025617Z","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","venue":null,"work_id":"1e87dd8c-920d-4547-b059-bca0ab9b9ba9","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.399886Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:84f46d5df10ac04d0ee0f4af0c06c501161f53fa3b9da24fe1a0597038b2eb46","observation_id":"c4e0fc2a-c97c-4290-9e32-78a235bdc1c7","resolution":{"observed_at":"2026-08-15T23:59:13.030257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.014120Z","title":"ChatGPT outperforms crowd workers for text-annotation tasks","venue":null,"work_id":"cf6fc43a-d542-4d3a-8b47-1dfdf92223f4","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.404794Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:6b9ced82346db68e7d3e42e7f856d355ce00012a48634a5b37ba97bdc6a1afb1","observation_id":"ba2ea137-d2bf-466f-a114-cfb9f57cdeb1","resolution":{"observed_at":"2026-08-15T23:59:13.017880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07922","last_updated":"2022-10-22T01:32:03Z","snapshot_observed_at":"2026-08-18T07:59:14.405715Z","submitted_at":"2022-02-16T08:18:02Z","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07922","snapshot_observed_at":"2026-08-15T23:59:12.408190Z","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.408190Z"},"links":{"cited_paper":"/paper/2202.07922","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:53725d224b7c9c42dd2a7ff0e31115ebb8d51db00281f490f443c678f84c686f","observation_id":"447994e4-bca2-45d1-99e4-4788cf74e38a","resolution":{"observed_at":"2026-08-15T23:59:12.408190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15126","last_updated":"2024-06-14T07:47:09Z","snapshot_observed_at":"2026-08-18T08:00:35.964338Z","submitted_at":"2024-06-14T07:47:09Z","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15126","snapshot_observed_at":"2026-08-15T23:59:12.412170Z","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.412170Z"},"links":{"cited_paper":"/paper/2406.15126","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:d1870b589dbd205d262048ec4e71090b4faceee8256dc1a159639be4a18ea8a9","observation_id":"166ef1c9-c26d-4673-ad75-efa0262ac122","resolution":{"observed_at":"2026-08-15T23:59:12.412170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11547","last_updated":"2024-04-16T09:06:25Z","snapshot_observed_at":"2026-08-16T14:41:58.040198Z","submitted_at":"2023-11-20T05:55:05Z","title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","version":2},"cited_work":{"arxiv_id":"2311.11547","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.11547","snapshot_observed_at":"2026-08-15T23:59:12.565205Z","title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","venue":"cs.AI","work_id":"d296f44d-dcbb-4ac6-bb9c-eef39fc8d1ea","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.416493Z"},"links":{"cited_paper":"/paper/2311.11547","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:a38739f7063cb8e952d66bf960a63c66ebca4af6e1e8145ee45ccc107d41ffee","observation_id":"d2afb829-6e15-43d1-93dc-724fb719a186","resolution":{"observed_at":"2026-08-15T23:59:12.569442Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:13.001631Z","title":"PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees","venue":null,"work_id":"47788300-fdff-4487-96d1-2a0cdbfec347","year":2019},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.420294Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:d1c98152a8c8a4d2ccb5bc39c31b36998000633f0d3e5bc2f7b6ea6152ee5110","observation_id":"38d78fdb-d4b1-441d-b293-93e1bda8da0f","resolution":{"observed_at":"2026-08-15T23:59:13.006169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10265","last_updated":"2024-04-18T09:20:13Z","snapshot_observed_at":"2026-08-17T00:02:02.613409Z","submitted_at":"2023-04-20T12:45:21Z","title":"Replication in Requirements Engineering: the NLP for RE Case","version":2},"cited_work":{"arxiv_id":"2304.10265","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.10265","snapshot_observed_at":"2026-08-15T23:59:12.547671Z","title":"Replication in Requirements Engineering: the NLP for RE Case","venue":"cs.SE","work_id":"5787d701-e884-4277-ae50-564db16f3a3e","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.423705Z"},"links":{"cited_paper":"/paper/2304.10265","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:13f744fea492141a427b3b0d67db457470d9adc37e8865db6de9b82486e8d4ae","observation_id":"63eb4a28-6d6b-480c-a4aa-d09b17736daf","resolution":{"observed_at":"2026-08-15T23:59:12.553354Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00618","last_updated":"2023-02-01T17:33:12Z","snapshot_observed_at":"2026-08-16T15:58:26.853622Z","submitted_at":"2023-02-01T17:33:12Z","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.00618","snapshot_observed_at":"2026-08-15T23:59:12.427599Z","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.427599Z"},"links":{"cited_paper":"/paper/2302.00618","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:9c0bc9672422bcb76f2ffefd133f6f2dcaf5c55fa021642f64328023bdf1c80f","observation_id":"20cdd47f-a35c-40c9-a409-b0448f696754","resolution":{"observed_at":"2026-08-15T23:59:12.427599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.989903Z","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","venue":null,"work_id":"999b17fe-9884-4e2d-85cd-8ea86eb4f18f","year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.431531Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:6f86df80ec4a913f25e003f4c2467b35f73f65641a39d9c227ceb1b00c7712ff","observation_id":"e777a550-3f60-40b7-83f3-45069cc3cb32","resolution":{"observed_at":"2026-08-15T23:59:12.993770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.435088Z","title":"BERT: Pre-training of Deep Bidirectional Trans- formers for Language Understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.435088Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:2c118ddc040cc0fccad37c0e167d5ccf1ba5b9f432d8a5b383beb7cc93fb6f05","observation_id":"857a67c9-d211-4a78-8f9b-15119309d76c","resolution":{"observed_at":"2026-08-15T23:59:12.435088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.977932Z","title":null,"venue":null,"work_id":"0f16d454-993e-4b95-b166-a1a1d8cbe8b1","year":2005},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.438921Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:ae00aed4a12db5b8a781400f99e4c71520ecc15c48938429590fedf70bbb6d29","observation_id":"fef5b97c-2b82-423e-8137-e2004a4fc2be","resolution":{"observed_at":"2026-08-15T23:59:12.981759Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.966292Z","title":null,"venue":null,"work_id":"2cdf5299-c5d0-4638-b937-ae25efccf338","year":2013},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.442472Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:fa27f5b0e71d35b7af8b9c526e9449cd604ed559c00b5805fca41e509073839b","observation_id":"de3f6b16-792f-44fd-8b0c-3aaefa86d540","resolution":{"observed_at":"2026-08-15T23:59:12.970209Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.953347Z","title":"Software product lines essentials","venue":null,"work_id":"435c9cf9-83a3-42c2-93c3-46724d4ac91a","year":2008},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.445937Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:82bd384e1dbf936abd5a596f0282dc9896b7573c0bf890c336e6aa724d428299","observation_id":"b5e8bc7b-9a85-4d08-992b-1453bf729f11","resolution":{"observed_at":"2026-08-15T23:59:12.957285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.941140Z","title":"Preventing Requirement Defects: An Experiment in Process Improvement","venue":null,"work_id":"c92bf3ab-13b8-4a35-81bf-a8dbc13e9b05","year":2001},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.449770Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:cd7b1483ccac653822b01c3eb00e7c8e82528c3c97138c2fc14a08e7b814d1a4","observation_id":"1b06e5e7-0468-4893-9c21-594d8a0ba268","resolution":{"observed_at":"2026-08-15T23:59:12.945312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.926929Z","title":"Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks","venue":null,"work_id":"3076b585-5e13-4593-98ab-45778c766f54","year":2024},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.453292Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:5a702983d462ee3597a1dc63875c61eea6f83d8d11d226a6eb56e8e09d852736","observation_id":"cfb359b5-5d28-46f2-b6b3-9e796166a780","resolution":{"observed_at":"2026-08-15T23:59:12.931889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.912347Z","title":"SDP-BB: A Software Defect Prediction Model Using BiLSTM and BERT-Based Se- mantic Features","venue":null,"work_id":"b60effed-774e-4036-adb3-dd4403f8f901","year":2022},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.456936Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:eba1ec255aa3e5686564f37405cba6497667005352d3ad49d3e9d2bcaeaa3376","observation_id":"ced2332b-c5bb-4e1c-840f-b73923bd4c66","resolution":{"observed_at":"2026-08-15T23:59:12.917626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.900164Z","title":"Automated Quality Defect Detection in Software Development Documents","venue":null,"work_id":"5bd10848-9f54-44fe-8419-7fbb321726a5","year":2011},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.460472Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:c0d087ff17f064b1db6acaf0e2a2c98dabe8271de3b90e52785d3d50640acdb0","observation_id":"beb0eea6-df4e-44f2-84fa-e0a29f2e1b67","resolution":{"observed_at":"2026-08-15T23:59:12.904096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.887028Z","title":"Ambiguity in Requirements Specification","venue":null,"work_id":"a5697848-cceb-4b62-aa56-bf7321fbb4b0","year":2004},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.464487Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:46044df7cb986a32df701728de02211b281e35ebeb246bc531fccb1e7907be4b","observation_id":"fa62cd2a-66be-4073-a7b9-39d2adde9183","resolution":{"observed_at":"2026-08-15T23:59:12.891196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03277","last_updated":"2023-04-06T17:58:09Z","snapshot_observed_at":"2026-08-16T13:26:40.822276Z","submitted_at":"2023-04-06T17:58:09Z","title":"Instruction Tuning with GPT-4","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03277","snapshot_observed_at":"2026-08-15T23:59:12.467945Z","title":"Instruction Tuning with GPT-4","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.467945Z"},"links":{"cited_paper":"/paper/2304.03277","citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:b3005acb54b0e4ce677a5e47a607231933426c9cda15b25adb5ff1a8f1ce7c3c","observation_id":"0d1e1319-f67c-42f5-b021-9e51808609b0","resolution":{"observed_at":"2026-08-15T23:59:12.467945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.874638Z","title":"True Few-Shot Learning with Language Models","venue":null,"work_id":"9941fc93-523f-47fe-ab8d-0b3c67fb978f","year":2021},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.471692Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:b244d42aa2d225816522c988a325744cf4ddc6053857ed934e5fd403dc762ac1","observation_id":"f995f775-0bc7-4f7a-806e-29b08416c804","resolution":{"observed_at":"2026-08-15T23:59:12.878613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:12.475245Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:12.475245Z"},"links":{"citing_paper":"/paper/2505.03265"},"observation_digest":"sha256:cfef8f6fc03894fd63eb46b789808692299da71b4132f35f13def5e759b0639d","observation_id":"df6a7186-ef94-4d16-a27b-d20ba27660b8","resolution":{"observed_at":"2026-08-15T23:59:12.475245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.03265","last_updated":"2025-05-06T07:57:16Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-18T08:02:47.035602Z","submitted_at":"2025-05-06T07:57:16Z","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":13,"verified_exact":3,"verified_fuzzy":14},"total_outbound_references":31},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2505.03265."}