{"as_of":"2026-08-08T19:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8ae3e86a168b4d19f0773de1ab3874ec698fe06c01e36d28188a6b4ac273f490","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T01:03:29.139102Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2602.10778/citation-record","integrity":"/paper/2602.10778/integrity","json":"/paper/2602.10778/citation-record.json","paper":"/paper/2602.10778"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T01:03:26.153888Z","title":"Application of large language models to software engineering tasks: Opportunities, risks, and implications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.153888Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:35c5b2b2ddbe893f2d9999651fae7cb1e36e5c2aefb6b06e1b2957853b6c6e8e","observation_id":"3f1e2f6b-e948-4686-bba6-979c9f4aeb3b","resolution":{"observed_at":"2026-08-03T01:03:26.153888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-03T01:03:26.217999Z","title":"Evaluating large language models trained on code,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.217999Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:c718ffd92fd6ecc647c0aa5b97f3f73ad632d51079c37ab94e6540afd9f26ed1","observation_id":"d72b9053-b364-41ce-ad5b-340ecf2e3f24","resolution":{"observed_at":"2026-08-03T01:03:26.217999Z","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":"2026-08-03T01:03:26.254732Z","title":"Gemini Code Assist: AI-first coding in your natural language,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.254732Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:c0f148e3f09ec578d153cd5900f849e42ea5eb013ce0c3cff064e79537ee400b","observation_id":"d5d28d0f-2d1b-475e-a965-145fdcc9e6ac","resolution":{"observed_at":"2026-08-03T01:03:26.254732Z","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":"2026-08-03T01:03:26.293563Z","title":"Survey reveals AI’s impact on the developer experience,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.293563Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:fcf7bbc19e5fcba6ccd4d3ac1fecb6d3dceb759630371ddb2423a934f021cd2e","observation_id":"490cfef5-90b5-4d85-bbcd-8b8640444215","resolution":{"observed_at":"2026-08-03T01:03:26.293563Z","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":"2026-08-03T01:03:26.351285Z","title":"A review on vibe coding: Fundamentals, state- of-the-art, challenges and future directions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.351285Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:2fc9be7627b7327902419b3c65b7f99800d7420ed7217c17f18fadfe111640cb","observation_id":"5edbc6fd-3f41-49ba-9108-121e42718fcc","resolution":{"observed_at":"2026-08-03T01:03:26.351285Z","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":"2026-08-03T01:03:26.396448Z","title":"Is vibe coding safe? benchmarking vulnerability of agent- generated code in real-world tasks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.396448Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:a01ed0b9d525975d3d1f8df755f7a02a3204c3490427a1418df0333dff106287","observation_id":"9502989b-12f2-4144-ac93-ca7cecefda9d","resolution":{"observed_at":"2026-08-03T01:03:26.396448Z","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":"2026-08-03T01:03:26.445892Z","title":"Security vulnerabilities in ai- generated code: A large-scale analysis of public github repositories,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.445892Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:8077c69c5592b9d85437cf92e4a4ce3c282f640ca8f3d58298f2fb69e62d4336","observation_id":"0562fc57-c92f-46b7-b911-adb9a757aea7","resolution":{"observed_at":"2026-08-03T01:03:26.445892Z","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":"2026-08-03T01:03:26.503533Z","title":"We have a package for you! a com- prehensive analysis of package hallucinations by code generating {LLMs},","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.503533Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:5392b57ac7241ce5f6d94c4b626fdb732b66fc25321bf139f9e4de444ed2224f","observation_id":"bbe6dc60-383c-402f-af14-2fddbcdcc640","resolution":{"observed_at":"2026-08-03T01:03:26.503533Z","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":"2026-08-03T01:03:26.520652Z","title":"Large language models for code: Security hardening and adversarial testing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.520652Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:1c847eff72b72a77e2b7906ed91d1b1429cfc091ef410782da70f9cb07dacbcb","observation_id":"10786c9f-cd34-477f-861b-0e759117a34b","resolution":{"observed_at":"2026-08-03T01:03:26.520652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09497","last_updated":"2024-07-12T15:45:57Z","snapshot_observed_at":"2026-08-07T20:39:53.804897Z","submitted_at":"2024-02-14T15:47:46Z","title":"Instruction Tuning for Secure Code Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09497","snapshot_observed_at":"2026-08-03T01:03:26.558953Z","title":"In- struction tuning for secure code generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.558953Z"},"links":{"cited_paper":"/paper/2402.09497","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:6c56ac1d82157b035d563d362eff3c670af08628ba205557eb3de9dc8c3b1bf3","observation_id":"037ea091-0649-4a7c-ba1f-5021986dde67","resolution":{"observed_at":"2026-08-03T01:03:26.558953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03693","last_updated":"2023-10-05T17:12:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-05T17:12:17Z","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03693","snapshot_observed_at":"2026-08-03T01:03:26.620536Z","title":"Fine-tuning aligned language models compromises safety, even when users do not intend to!","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.620536Z"},"links":{"cited_paper":"/paper/2310.03693","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:6c03a6ff29c0bc762fdb45370d146e7ddb5905d8a5e4fdee1f1a7b609595cf9c","observation_id":"1ed04bff-1592-4333-bb14-6df82440f5cb","resolution":{"observed_at":"2026-08-03T01:03:26.620536Z","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":"2026-08-03T01:03:26.681292Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.681292Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:65225a6029c456d52ccd578fc1b47c35987b56ed4ff85c64ac3075f29dff61cb","observation_id":"77055b1c-9165-4323-86fb-3ac7ba744bfd","resolution":{"observed_at":"2026-08-03T01:03:26.681292Z","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":"2026-08-03T01:03:26.742186Z","title":"Parameter- efficient fine-tuning of large-scale pre-trained language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.742186Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:db4ae38718a94dcd9ba151b8a623773a857d9d02871e278189bfae04e3845636","observation_id":"9b4109f2-ec25-4845-af31-916234a40a3d","resolution":{"observed_at":"2026-08-03T01:03:26.742186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-07-06T16:10:07.931347Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-03T01:03:26.799474Z","title":"Code llama: Open foundation models for code,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.799474Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:513c420f7cae1dce1f185c2202967740b37ddb580a34935b5fccc84a0d845d12","observation_id":"76134f01-aef0-4ca4-8938-ea11e55f4694","resolution":{"observed_at":"2026-08-03T01:03:26.799474Z","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":"2026-08-03T01:03:26.832220Z","title":"Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.832220Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:15fd9b8395eee76cace49e7f4156339efacf7736e3be339c6611d31941d34c16","observation_id":"dcde22f4-f513-41ea-ae3d-9ed7a72c64bf","resolution":{"observed_at":"2026-08-03T01:03:26.832220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13787","last_updated":"2025-01-23T16:04:23Z","snapshot_observed_at":"2026-08-07T07:30:22.453328Z","submitted_at":"2025-01-23T16:04:23Z","title":"Parameter-Efficient Fine-Tuning for Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13787","snapshot_observed_at":"2026-08-03T01:03:26.865933Z","title":"Parameter-efficient fine-tuning for foundation models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.865933Z"},"links":{"cited_paper":"/paper/2501.13787","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:89f1cca2915ee0b5711553d2239e3bd33e396790b33f3efcbd700cacb391363b","observation_id":"ead16b97-e24b-4886-99e8-399c4f0b41f7","resolution":{"observed_at":"2026-08-03T01:03:26.865933Z","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":"2026-08-03T01:03:26.927413Z","title":"A mathematical framework for transformer circuits,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.927413Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:c09c3954521d115ec6e29f865e799e13b3a134270205972b64fddc4dde9adc3e","observation_id":"5946f8f6-1aa6-4fe9-ab79-27a10a1bbf5a","resolution":{"observed_at":"2026-08-03T01:03:26.927413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-03T01:03:26.984538Z","title":"Qwen3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:26.984538Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:3957e4a842bed5d4aa882ed5a76dd298ea19eb6428422c552da26a3787ccf9e5","observation_id":"2cd21833-85a4-43bb-9bac-ae512a433715","resolution":{"observed_at":"2026-08-03T01:03:26.984538Z","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":"2026-08-03T01:03:27.046213Z","title":"A survey on llm-as-a- judge,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.046213Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:52cce34dda79f1e2cd8370e46e390a84b9dcf95e707aae08df7dfdd15ea8af06","observation_id":"3da79648-f267-4e02-89ba-182736ee5f3c","resolution":{"observed_at":"2026-08-03T01:03:27.046213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-03T01:03:27.097367Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.097367Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:4ca0a8391747abacba0687cd3640fcb761d293849b97b2de0aa5f41cd615fb2a","observation_id":"3ce46035-df0e-4376-8c86-4f52cede3576","resolution":{"observed_at":"2026-08-03T01:03:27.097367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-03T01:03:27.162810Z","title":"Training verifiers to solve math word problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.162810Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:91526679d2900a09766fd28996c8a953485f37ed985753fb607c6c492cbf5863","observation_id":"2af4969f-42a3-4df2-add1-534f16927664","resolution":{"observed_at":"2026-08-03T01:03:27.162810Z","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":"2026-08-03T01:03:27.223708Z","title":"Measuring massive mul- titask language understanding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.223708Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:6e2170a099822a81b3865fb0790253289799a7200cbfba8806eab0613814a964","observation_id":"2fa40ce2-5acb-4b9d-81bc-fad8f4083f07","resolution":{"observed_at":"2026-08-03T01:03:27.223708Z","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":"2026-08-03T01:03:27.255169Z","title":"The llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.255169Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:32c3d8a4e6675fc4a8ce9344e8d7b9173c90394e0bf0e9fad4bdb8abb7d325d5","observation_id":"fa2e3480-9e50-4d3d-b9b9-a78a38e5785d","resolution":{"observed_at":"2026-08-03T01:03:27.255169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-03T01:03:27.326400Z","title":"Gemma 3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.326400Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:9117480238749e0fb95d88dfdb5a6f3c694dd31df166f25b308658ea7c169b3a","observation_id":"997a726e-51d9-4013-ae37-4277599376fa","resolution":{"observed_at":"2026-08-03T01:03:27.326400Z","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":"2026-08-03T01:03:27.500936Z","title":"Cybernative.ai code vulnerabil- ity and security dataset,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.500936Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:ebe090eb16265785463cb1b2c907d971988b0eedc1f646e1ad57b0f2699b36b7","observation_id":"e5e61285-b326-4f5b-8604-0586c7c9fe42","resolution":{"observed_at":"2026-08-03T01:03:27.500936Z","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":"2026-08-03T01:03:27.616984Z","title":"Learning from mistakes: a comprehensive study on real world concur- rency bug characteristics,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.616984Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:b443cb8a4453f8bba0e999a42c4fab9c7b51ea8d6baded12f0a84617af3839d6","observation_id":"cf6b20d3-a2b8-474b-b2f1-b9abd6cdc521","resolution":{"observed_at":"2026-08-03T01:03:27.616984Z","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":"2026-08-03T01:03:27.681273Z","title":"Sok: Eter- nal war in memory,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.681273Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:7b7efcfa773884c45540f0fd936830e7a3a8525726c8ed96624e940138b172ed","observation_id":"0e07cc92-27b5-46d7-bdda-2c1f126a39d5","resolution":{"observed_at":"2026-08-03T01:03:27.681273Z","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":"2026-08-03T01:03:27.802316Z","title":"A survey of mobile malware in the wild,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.802316Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:f3110e24ec9098713e0d272ad855103a1645a6666fb1f31c3638ec4fab7a4ea9","observation_id":"7ec5c137-2148-4b1e-81e4-5da2e0ae3b1f","resolution":{"observed_at":"2026-08-03T01:03:27.802316Z","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":"2026-08-03T01:03:27.954268Z","title":"Flowdroid: Precise context, flow, field, object-sensitive and lifecycle-aware taint analysis for android apps,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:27.954268Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:0766b7a5c5253ca2991d7ea541e40fcc4005b10ad394411dda632c55ef8b692e","observation_id":"3d0e9292-899b-4943-a313-442b1bdc5fc3","resolution":{"observed_at":"2026-08-03T01:03:27.954268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.07596","last_updated":"2025-06-09T09:54:25Z","snapshot_observed_at":"2026-08-08T10:55:00.360207Z","submitted_at":"2025-06-09T09:54:25Z","title":"TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.07596","snapshot_observed_at":"2026-08-03T01:03:28.012736Z","title":"Twin- break: Jailbreaking llm security alignments based on twin prompts,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.012736Z"},"links":{"cited_paper":"/paper/2506.07596","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:2ab54675d1ac03d00c0b0c50530aaedb5c69d1d6d8a82505f1bca54e6a8d4e85","observation_id":"05abea8d-e50b-41c8-97f6-31c40d0436e9","resolution":{"observed_at":"2026-08-03T01:03:28.012736Z","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":"2026-08-03T01:03:28.099609Z","title":"Neurostrike: Neuron-level attacks on aligned llms,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.099609Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:1da0fc9e97e5efee7f54f39255b8995d76ac4c33a0c82cbf766353f9bbeca1d0","observation_id":"b937da33-e5ca-47f6-ace3-2c80ab97f7fc","resolution":{"observed_at":"2026-08-03T01:03:28.099609Z","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":"2026-08-03T01:03:28.212216Z","title":"An empiri- cal study of the copy and paste behavior during devel- opment,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.212216Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:1d2cf590540a3a2701c5f701821add8a7821544c32733c93151d4903e0bb7391","observation_id":"78a06eb3-7ae3-4237-87fd-b38ff6065027","resolution":{"observed_at":"2026-08-03T01:03:28.212216Z","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":"2026-08-03T01:03:28.333454Z","title":"Secure-instruct: An automated pipeline for synthesizing instruction-tuning datasets using llms for secure code generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.333454Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:5cfbdfbceee9d4d9c91a8bfdd866cf384d2c4da59ca83f9da525c6739cc80f8b","observation_id":"716d5d5c-a079-44fd-8c2a-2c30eeabba69","resolution":{"observed_at":"2026-08-03T01:03:28.333454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.06446","last_updated":"2024-09-10T12:01:43Z","snapshot_observed_at":"2026-07-06T19:13:11.744186Z","submitted_at":"2024-09-10T12:01:43Z","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.06446","snapshot_observed_at":"2026-08-03T01:03:28.545990Z","title":"Hex- acoder: Secure code generation via oracle-guided syn- thetic training data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.545990Z"},"links":{"cited_paper":"/paper/2409.06446","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:5ec289f37f9eb6ef5878db6169be07a7c402849ac1a784c1c99971e3790cbe02","observation_id":"8322e328-448e-46be-b103-7c8b10b8dec6","resolution":{"observed_at":"2026-08-03T01:03:28.545990Z","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":"2026-08-03T01:03:28.719125Z","title":"Prom- sec: Prompt optimization for secure generation of func- tional source code with large language models (llms),","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.719125Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:f23dfb0fc501fa5e0edbeaac15d74ce63e3c8f8c0345602560ae20fccc5b81cf","observation_id":"617080bc-c755-4596-9f65-4b78caf03d48","resolution":{"observed_at":"2026-08-03T01:03:28.719125Z","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":"2026-08-03T01:03:28.892913Z","title":"Sgcode: A flex- ible prompt-optimizing system for secure generation of code,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:28.892913Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:c7dbd5a68e3560ffef6632bf32f56dfde1614494fb2e87c9b8777d4074402930","observation_id":"6482bb64-758d-4bec-92a2-69db7e34d6ab","resolution":{"observed_at":"2026-08-03T01:03:28.892913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01488","last_updated":"2024-10-02T12:36:53Z","snapshot_observed_at":"2026-08-05T12:13:28.163041Z","submitted_at":"2024-10-02T12:36:53Z","title":"SecCoder: Towards Generalizable and Robust Secure Code Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01488","snapshot_observed_at":"2026-08-03T01:03:29.052610Z","title":"Seccoder: Towards generaliz- able and robust secure code generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:29.052610Z"},"links":{"cited_paper":"/paper/2410.01488","citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:d746e28cd64d1048906a1926a6639b6ad428d461564d876ea857e5e35f3bf379","observation_id":"bd22b598-4887-422f-bb0c-60153f2692d6","resolution":{"observed_at":"2026-08-03T01:03:29.052610Z","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":"2026-08-03T01:03:29.139102Z","title":"The menlo report,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T01:03:29.139102Z"},"links":{"citing_paper":"/paper/2602.10778"},"observation_digest":"sha256:49d20bb33a55f08d996dfda6d38339602ba1df9411f8eb7f66a3a16bd122e0ce","observation_id":"4eb9ce41-044e-4f5c-94e2-a6607bccda53","resolution":{"observed_at":"2026-08-03T01:03:29.139102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.10778","last_updated":"2026-05-29T10:02:55Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T14:04:47.739056Z","submitted_at":"2026-02-11T12:10:14Z","title":"GoodVibe: Security-by-Vibe for LLM-Based Code Generation"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":38},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2602.10778."}