{"as_of":"2026-08-17T14:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83f0263d593f3d55e540ff8c30a6cbc44dad99894fe9f5e144b1a646fc01b615","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:19:11.444452Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2506.12100/citation-record","integrity":"/paper/2506.12100/integrity","json":"/paper/2506.12100/citation-record.json","paper":"/paper/2506.12100"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:19:17.274561Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","venue":null,"work_id":"e7af2de8-dcc3-481e-b79a-580b3a187bf0","year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:08.853595Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:54c4e16be19d3e9ef179275a73e13018220f34d513e688d359bb8aba1354c030","observation_id":"c1aac59d-b64f-46c6-8a34-118c9eb41e70","resolution":{"observed_at":"2026-08-07T04:19:17.432370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:16.864634Z","title":"Improving Language Models by Retrieving from Trillions of Tokens","venue":null,"work_id":"ddc65665-aad6-4646-9fce-27366be2ad1d","year":2022},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:08.900458Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:92b2b3d99f14aa67cad429bc86dc579dcf53b57f614e82dead5d2a361b7fd30e","observation_id":"0e37ef6a-b929-4fcf-9227-c5e1867d75ba","resolution":{"observed_at":"2026-08-07T04:19:17.094506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07232","last_updated":"2023-04-12T17:24:03Z","snapshot_observed_at":"2026-08-16T15:40:55.761406Z","submitted_at":"2023-04-12T17:24:03Z","title":"Evaluation of ChatGPT Model for Vulnerability Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07232","snapshot_observed_at":"2026-08-07T04:19:09.055205Z","title":"Evaluation of ChatGPT Model for Vulnerabil- ity Detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.055205Z"},"links":{"cited_paper":"/paper/2304.07232","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:c36da169f33869f39d0227283c9f76f88ad94832332408e67d2a3e1618cb75ee","observation_id":"dbc61c80-be9b-4462-a8f2-f3e0fdd7bdff","resolution":{"observed_at":"2026-08-07T04:19:09.055205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04756","last_updated":"2025-05-20T02:09:07Z","snapshot_observed_at":"2026-08-16T13:00:30.803995Z","submitted_at":"2024-12-06T03:45:49Z","title":"ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models","version":2},"cited_work":{"arxiv_id":"2412.04756","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.04756","snapshot_observed_at":"2026-08-07T04:19:11.798594Z","title":"ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models","venue":"cs.CR","work_id":"7d5ed5fe-aefd-49d3-b8e7-680f690cbc8a","year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.205815Z"},"links":{"cited_paper":"/paper/2412.04756","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:afd7a8da957e4fd33cbbc0e31bd3beb0367b8b8eefeb095a343a6dedded50082","observation_id":"47a047df-903d-45ac-9a67-669c915781a9","resolution":{"observed_at":"2026-08-07T04:19:11.910825Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:16.527448Z","title":"PentestGPT: Evaluating and Harnessing Large Language Models for Automated Pen- etration Testing","venue":null,"work_id":"0468684d-91cb-4828-b9ab-e7cf25f1a374","year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.315584Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:bdaa318011433f9b15c585e90dab807057110ab48428568fe9e696e1277915e4","observation_id":"c464d64d-2833-439e-a4b8-5877d8644a76","resolution":{"observed_at":"2026-08-07T04:19:16.638521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:09.397480Z","title":"A Sliding Layer Merging Method for Effi- cient Depth-Wise Pruning in LLMs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.397480Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:7550a2f6f7a89de7d4f250edc19d98ff80c0990d324037b92d63d8e94408361d","observation_id":"175b029d-4952-4885-8a71-3c57a781ca31","resolution":{"observed_at":"2026-08-07T04:19:09.397480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11147","last_updated":"2025-06-17T15:07:17Z","snapshot_observed_at":"2026-08-16T13:42:27.339640Z","submitted_at":"2024-06-17T02:25:45Z","title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11147","snapshot_observed_at":"2026-08-07T04:19:09.495629Z","title":"Vul-RAG: Enhancing LLM- based Vulnerability Detection via Knowledge-level RAG","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.495629Z"},"links":{"cited_paper":"/paper/2406.11147","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:f5c8df71eb43e03f527acd62f1210110b52048e09ad75a0f8fb719a98e1fb70f","observation_id":"b4bb763a-a0a8-4c26-b822-015755f801cb","resolution":{"observed_at":"2026-08-07T04:19:09.495629Z","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":"2026-08-07T04:19:16.285482Z","title":"Introducing Gemma 3: The Most Ca- pable Model You Can Run on a Single GPU or TPU","venue":null,"work_id":"cc3d819a-713c-49b2-91d7-c591438b1ec1","year":2025},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.583875Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:6441c909a4c4cc98e5aa3847cc7a68b2f200ba26a7d065cbc0173c2bbcd10bab","observation_id":"eb038151-ef34-4102-845c-64006b06d0a2","resolution":{"observed_at":"2026-08-07T04:19:16.416978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:16.015173Z","title":"From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy","venue":null,"work_id":"310374c2-6e06-482d-a0a0-f755c99c7701","year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.653511Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:27492f400a2dfe7142ac265ffae9293bb9ca3f1ba8909321dc7c01dd49ea8962","observation_id":"c329cf78-7070-4ca4-bea6-13c4ccae29c9","resolution":{"observed_at":"2026-08-07T04:19:16.155391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:15.728856Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","venue":null,"work_id":"56d1b2de-5154-4e38-b0f6-d99236be7068","year":2021},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.741719Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:754cb140f41e5bc6cb512a91483c125b8d06dae0e1849df10cf36500648f040d","observation_id":"b374c62c-7837-4db5-a386-86b1d6dd5446","resolution":{"observed_at":"2026-08-07T04:19:15.880215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05232","last_updated":"2024-11-19T12:42:45Z","snapshot_observed_at":"2026-07-06T16:45:07.733095Z","submitted_at":"2023-11-09T09:25:37Z","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05232","snapshot_observed_at":"2026-08-07T04:19:09.845343Z","title":"A Survey on Hallucination in Large Language Models: Princi- ples, Taxonomy, Challenges, and Open Questions.arXiv preprint arXiv:2311.05232, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.845343Z"},"links":{"cited_paper":"/paper/2311.05232","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:4087e007cd5b8434dbec94aabf04012f24c7c7fe06144b6bf6b71e5324a65599","observation_id":"c32f4d49-b9b9-4596-8f69-65fc55324fb1","resolution":{"observed_at":"2026-08-07T04:19:09.845343Z","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":"2026-08-07T04:19:15.436292Z","title":"DeepSeek-R1-Distill-Llama-8B","venue":null,"work_id":"017728fb-e336-4da3-9ac4-665a52982652","year":2025},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:09.949350Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:b45f68472ad0f5eb2a6d4fb9223b602a9a6808595e1fb3c31da7842e2ce4f5aa","observation_id":"88cf17e3-b3a6-4840-b848-643a999185dd","resolution":{"observed_at":"2026-08-07T04:19:15.589915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14403","last_updated":"2024-03-28T06:45:11Z","snapshot_observed_at":"2026-08-16T14:07:41.100742Z","submitted_at":"2024-03-21T13:52:30Z","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14403","snapshot_observed_at":"2026-08-07T04:19:10.037010Z","title":"Adaptive-RAG: Learn- ing to Adapt Retrieval-Augmented Large Language Models through Question Complexity","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.037010Z"},"links":{"cited_paper":"/paper/2403.14403","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:a7297cd3b1d5d8158fc9fc7901b4a97579216fcc3fd2a0ec1d30d5e8d423671a","observation_id":"8e8f508e-ad6b-4e8b-bb59-8f2553931c61","resolution":{"observed_at":"2026-08-07T04:19:10.037010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16169","last_updated":"2024-10-23T07:32:15Z","snapshot_observed_at":"2026-08-16T14:42:40.879076Z","submitted_at":"2023-11-16T13:17:20Z","title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16169","snapshot_observed_at":"2026-08-07T04:19:10.099050Z","title":"Understand- ing the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.099050Z"},"links":{"cited_paper":"/paper/2311.16169","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:eb703bccf3542ec1464a8cad7941098483dfa5cd5c035ceedbdd0da1a44c6815","observation_id":"d85352a8-7bf2-4f5b-bec6-c701cb2fb5be","resolution":{"observed_at":"2026-08-07T04:19:10.099050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13081","last_updated":"2024-04-17T01:15:54Z","snapshot_observed_at":"2026-08-16T14:00:18.043136Z","submitted_at":"2024-04-17T01:15:54Z","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13081","snapshot_observed_at":"2026-08-07T04:19:10.177621Z","title":"SuRe: Summarizing Retrievals using An- swer Candidates for Open-domain QA of LLMs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.177621Z"},"links":{"cited_paper":"/paper/2404.13081","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:160b229920a1ca2a65b91670ee58701688b31775c4fdb768b6b4e05c89164f34","observation_id":"360285c3-ccb4-444f-a4dd-27ad0c4403ea","resolution":{"observed_at":"2026-08-07T04:19:10.177621Z","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":"2026-08-07T04:19:15.225326Z","title":"LLM- Pruner: On the Structural Pruning of Large Language Models","venue":null,"work_id":"d4aa7d46-de1d-49b0-8051-27961c21d396","year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.281766Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:180d75a31da48e255d6e93e7b28df582963981d31353c2f4f322f2584b656ad9","observation_id":"a16f72d8-0c51-466c-9e3e-cbfdcd3f1b96","resolution":{"observed_at":"2026-08-07T04:19:15.319963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:14.865879Z","title":"Llama 3.2: Revolutionizing edge ai and vi- sion with open, customizable models","venue":null,"work_id":"530dedca-09cb-45dd-ac9e-1dcac52ad020","year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.349510Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:c80285639be91c8b4689e30a9ac4081e9e8bcb3b6ccd7ae7352a2b0279e722ba","observation_id":"9035c8ac-ddf2-46a2-9cdd-36968beb8ca6","resolution":{"observed_at":"2026-08-07T04:19:15.009956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:14.534773Z","title":"Mistral Small 3","venue":null,"work_id":"0f6ddf6a-3280-40f2-9b22-9bcbf5b5976f","year":2025},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.443777Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:5ea0d4be0404884aef97707430d114351c978d736927d467ab78076e79e8428f","observation_id":"5692323b-bbc4-4caa-b3a1-02d5f6dc0f04","resolution":{"observed_at":"2026-08-07T04:19:14.683230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10036","last_updated":"2025-02-09T20:56:46Z","snapshot_observed_at":"2026-08-16T14:26:26.213872Z","submitted_at":"2024-01-18T15:00:01Z","title":"LOCALINTEL: Generating Organizational Threat Intelligence from Global and Local Cyber Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10036","snapshot_observed_at":"2026-08-07T04:19:10.531760Z","title":"LOCALINTEL: Generating Organizational Threat Intelligence from Global and Local Cyber Knowl- edge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.531760Z"},"links":{"cited_paper":"/paper/2401.10036","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:10c51c893766665d2149f9b0966080caab510cedcc11b1dbaf13639170b5ce09","observation_id":"bf44201d-a2b2-453b-81c4-83c2dd60ae5d","resolution":{"observed_at":"2026-08-07T04:19:10.531760Z","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":"2026-08-07T04:19:14.228257Z","title":"CVE - Common Vulnerabilities and Expo- sures","venue":null,"work_id":"3f9abc7f-22ed-4f15-8af3-bb2f24d7b4f8","year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.625495Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:d2032397fc1801be11ac24bcd59349f6db815af17bc0d7b60698ab4c416c8e3b","observation_id":"6a728d09-ede6-442d-905d-be4fe5940a81","resolution":{"observed_at":"2026-08-07T04:19:14.372881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:13.848680Z","title":"National Vulnerability Database (NVD)","venue":null,"work_id":"6a6d4760-a0b1-4e47-951c-0c19998972d0","year":2024},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.701814Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:5794f4cf34a2072a10fa9490322fabef35df7a80387b5782bed817301e5e4e44","observation_id":"41b53623-c34f-4374-873d-bc59c7b94be0","resolution":{"observed_at":"2026-08-07T04:19:14.070591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:13.476584Z","title":"Empirical Validation of Automated Vulnerability Curation and Characterization","venue":null,"work_id":"d87cdd6c-59cc-414f-b14e-60efd8874cb7","year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.792775Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:f8bdaf542c282a5b84ce18e3e4e93fc9149e4b8ce675152af788a7f63c39852a","observation_id":"d77ef160-c97a-4d38-8ff6-77b45800b9bd","resolution":{"observed_at":"2026-08-07T04:19:13.692872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:13.058487Z","title":"AGIR: Automating Cyber Threat Intelligence Reporting with Natural Language Gener- ation","venue":null,"work_id":"af65e334-d916-479e-bff3-6091b02b6a38","year":2023},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:10.913406Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:3869f295c1c143263ed4ceea25be0f3456b8b73fc960b4f227db690498e368e1","observation_id":"9e83884f-962a-4081-87c0-cb4987ea9294","resolution":{"observed_at":"2026-08-07T04:19:13.225834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04988","last_updated":"2023-10-23T03:37:34Z","snapshot_observed_at":"2026-08-16T14:54:09.946279Z","submitted_at":"2023-10-08T03:31:29Z","title":"The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04988","snapshot_observed_at":"2026-08-07T04:19:11.006093Z","title":"The Troubling Emergence of Hallucination in Large Language Models–An Extensive Definition, Quantification, and Prescriptive Remedia- tions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:11.006093Z"},"links":{"cited_paper":"/paper/2310.04988","citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:dd6f6dd14ed1106a3c067c85a367988af045c1fd8a2237ffc039afa516940ad4","observation_id":"e8f980ab-0f0c-4aab-aedb-114ebc784011","resolution":{"observed_at":"2026-08-07T04:19:11.006093Z","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":"2026-08-07T04:19:12.763428Z","title":"What is a CVE? https://www.redhat","venue":null,"work_id":"fbfee08c-ef8f-4c14-841a-c54505a58197","year":null},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:11.123507Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:861ebbd0a1a63cfd51c70fddb2d1f2be8f133e2e715465b96069bd4df375f5b8","observation_id":"399edb2e-e258-4a16-90f8-fe608bdaf866","resolution":{"observed_at":"2026-08-07T04:19:12.915559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:12.462000Z","title":"Attention Is All You Need","venue":null,"work_id":"ad35a64e-2277-45ab-a558-70259d8e7fa5","year":2017},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:11.282544Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:06301f8a09c9f743a2a028efb0a966413c8041316b82c381c2a5efa2ddfa3c78","observation_id":"ce05af3b-5b0c-4e72-92f7-d9440f4b8b52","resolution":{"observed_at":"2026-08-07T04:19:12.615822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:19:12.124598Z","title":"Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review","venue":null,"work_id":"bcd62416-7408-4e67-84cf-98b721011b1e","year":2025},"citing_paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:19:11.444452Z"},"links":{"citing_paper":"/paper/2506.12100"},"observation_digest":"sha256:bdda607e5c3a08b136e73040520f8fad37533f1cf281e87278312a0618f7c3c2","observation_id":"fa617041-db12-48c2-bc37-b3a04c8b0aea","resolution":{"observed_at":"2026-08-07T04:19:12.311818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.12100","last_updated":"2025-09-03T17:18:40Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-11T11:38:49.983940Z","submitted_at":"2025-06-12T21:20:10Z","title":"LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":27},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2506.12100."}