{"as_of":"2026-08-13T12:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b5c357b5feb22b79b926c0e2feb5798d81127d114bf271afd7a9bec3f2c27f1","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:38:05.193302Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2507.07695/citation-record","integrity":"/paper/2507.07695/integrity","json":"/paper/2507.07695/citation-record.json","paper":"/paper/2507.07695"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:38:05.124158Z","title":"Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.124158Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:e6baac4917e0523a0e7d80e256b04dc08fb6a84b57415debcac5712616d5a403","observation_id":"ec918219-1463-4e83-a3cd-30114bab03ae","resolution":{"observed_at":"2026-08-06T18:38:05.124158Z","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":"2026-08-06T18:38:05.127292Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.127292Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:f0facde1c38836a3a82c8cbbac2bc0c7692ab34ed885fafece7058b2201e7f73","observation_id":"14a2c4fd-9428-4e73-8be5-b7c2a3ca6146","resolution":{"observed_at":"2026-08-06T18:38:05.127292Z","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":"2026-08-06T18:38:05.130166Z","title":"Qlora: Efficient finetuning of quantized llms, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.130166Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:c632d892ef8082d401ea57947ada7d833d84e0b80fe0b2d8ce281c8a532ae827","observation_id":"1cc97401-c5bd-4ef3-a462-9dd5266a8ed0","resolution":{"observed_at":"2026-08-06T18:38:05.130166Z","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":"2026-08-06T18:38:05.401207Z","title":"An empirical study of llama3 quantization: From llms to mllms, 2024","venue":null,"work_id":"6dd5cd49-6995-472a-b656-e310b1c19e88","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.132685Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:bc642af92456bbb43bcc7f70da590173ea9d17991acfbf59834cb436719b5904","observation_id":"cec40276-046c-44bc-873e-a9df421e2363","resolution":{"observed_at":"2026-08-06T18:38:05.405067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.135342Z","title":"Retrieval-augmented generation for large language models: A survey, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.135342Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:6d3a9c77fdbdae68e0a31cd84f20e31dbd282132a144954744d1f0683784454e","observation_id":"1a10fac8-0591-4596-bd24-4641f2468a9f","resolution":{"observed_at":"2026-08-06T18:38:05.135342Z","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":"2026-08-06T18:38:05.137874Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.137874Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:c06eb9643d24d88413b057b007838c7a48917713af74822f1c796fc0be80378e","observation_id":"902b3561-b2bd-4e40-806e-dbe9c93ddf1b","resolution":{"observed_at":"2026-08-06T18:38:05.137874Z","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":"2026-08-06T18:38:05.140926Z","title":"Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.140926Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:d34b8b48507fcbf25a3857d106f70f7d0dea1a82d9bd0146333b43e695d11d38","observation_id":"5a526fb9-6aee-4064-bf6b-3154a02b368b","resolution":{"observed_at":"2026-08-06T18:38:05.140926Z","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":"2026-08-06T18:38:05.377981Z","title":"Fabbri, Caiming Xiong, and Chien-Sheng Wu","venue":null,"work_id":"8a9e7845-3d34-4df5-b2e8-2376ff46654d","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.142984Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:3d475a09fc86afe09e70c359781564a3fb0690c45b1c85da1530e4ac36309eca","observation_id":"42601dac-8c49-4360-ba41-4d469c002240","resolution":{"observed_at":"2026-08-06T18:38:05.382272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.369512Z","title":"Searching for best practices in retrieval-augmented generation, 2024","venue":null,"work_id":"66ce97a2-5c48-49e9-a4c8-38be4c33e73c","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.145562Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:455182b1f5ab76a35220a94b0079ae540bc90226c09991dd62a206d6d5e75e5b","observation_id":"80f4ab0d-80ec-4abb-8cff-824efb498146","resolution":{"observed_at":"2026-08-06T18:38:05.372371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.361142Z","title":"Relevance filtering for embedding-based retrieval","venue":null,"work_id":"d7df98c8-d9c2-4e5f-ba7e-fce8bcf1ade5","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.147793Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:b2ba04529c79d8fe086ae2a9f4bd8b1fc8156242601fcd570b108eb791e0bab5","observation_id":"2fb94f93-2247-4c4b-828c-a84b4d200d0e","resolution":{"observed_at":"2026-08-06T18:38:05.363950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.353277Z","title":"Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, and Antoine Zimmermann","venue":null,"work_id":"6476a85f-2a22-4723-b3ef-bc129db747f1","year":2021},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.149999Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:86fa92837fc5dff09271c3d70927e4d1b830514c1f3dd542cc99e74ba75d5acb","observation_id":"827a6196-60a9-45b1-954a-1467a41658e7","resolution":{"observed_at":"2026-08-06T18:38:05.356068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.344888Z","title":"Blended rag: Improving rag (retriever-augmented generation) accuracy with semantic search and hybrid query-based retrievers","venue":null,"work_id":"09a703d7-a01f-4d57-ae70-b77f4c9be597","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.152295Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:649d7f6c07e3baf2e817c40b88dbcd4b081d3bcbb2162b7d0e8f627b7f5b64db","observation_id":"d9632dd9-0154-4c91-b435-026e6a13cc80","resolution":{"observed_at":"2026-08-06T18:38:05.348505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.337688Z","title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","venue":null,"work_id":"83e0e2f4-7104-43b2-bf5d-b67f0c7cdb23","year":2019},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.154581Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:560e711a4612d41d4becd550dccbb0eac4351aa4ad8ccdc5728483b5703d6b62","observation_id":"21f7d19c-11c0-4cd2-9a09-a0f435b2a392","resolution":{"observed_at":"2026-08-06T18:38:05.340207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.330198Z","title":"Murdick, Devvret Rishi, Jerry Sheehan, Zhihong Shen, Brandon Stilson, Alex D","venue":null,"work_id":"48bb9d9e-5334-44b1-87bd-993b3d9f2ea6","year":2020},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.156874Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:d5cdceaf4002fcd66a49ffd4bbb50c291709877b2a9dd52077626e79f81985ac","observation_id":"038e9381-aab0-4a55-9558-73971b4773d5","resolution":{"observed_at":"2026-08-06T18:38:05.332793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.159162Z","title":"Squad: 100,000+ questions for machine comprehension of text, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.159162Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:2dd5ccf239521d8b147357c3649e597a9dbc5af84cd86d9fc9d2d11c2c235669","observation_id":"bf55056d-5201-43f5-8be7-c7e88967e9a0","resolution":{"observed_at":"2026-08-06T18:38:05.159162Z","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":"2026-08-06T18:38:05.161342Z","title":"Cohen, Ruslan Salakhutdinov, and Christo- pher D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.161342Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:628ff90c2b7e39814699d8d7a46042dbeb9bc79b662c6ff483aa1c854602b8fd","observation_id":"07d46d4e-6b56-4fc6-9847-b5e7baa471f9","resolution":{"observed_at":"2026-08-06T18:38:05.161342Z","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":"2026-08-06T18:38:05.313620Z","title":null,"venue":null,"work_id":"b6d34fe6-43c3-49b6-a0ef-184f16ab204d","year":2019},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.163472Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:e08266c2886d97688bab6ccd8d136c45a61ebefcfa3e400e06035ccc1ff62a6b","observation_id":"f09c2830-2c6d-43a4-aa47-28f44b4acbd8","resolution":{"observed_at":"2026-08-06T18:38:05.315895Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04055","last_updated":"2024-01-08T17:53:06Z","snapshot_observed_at":"2026-08-13T04:47:08.931971Z","submitted_at":"2024-01-08T17:53:06Z","title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04055","snapshot_observed_at":"2026-08-06T18:38:05.165803Z","title":"Sparse meets dense: A hybrid approach to enhance scientific document retrieval.CoRR, abs/2401.04055, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.165803Z"},"links":{"cited_paper":"/paper/2401.04055","citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:2c5da3a83dd80bce3409580ac24a630ecae817d7620191597c089f923c16bcab","observation_id":"ce6c1dd5-ad5c-4225-a6d1-bfd43738da8f","resolution":{"observed_at":"2026-08-06T18:38:05.165803Z","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":"2026-08-06T18:38:05.306096Z","title":"Scirepeval: A multi-format benchmark for scientific document representations, 2023","venue":null,"work_id":"3835e49c-aeb8-4023-bfff-1c142c51b411","year":2023},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.168322Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:2bb0d9c6500a4210a0f744273a50a594935506b82dfb6e8ae4127af3036c943e","observation_id":"ce4a34b4-b1af-4bc7-8f74-6800f9006599","resolution":{"observed_at":"2026-08-06T18:38:05.308665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.298697Z","title":"Document ranking with a pretrained sequence- to-sequence model","venue":null,"work_id":"13f14628-ee61-4ac1-87ed-2bec0f3b7497","year":2020},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.170371Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:d28b21c7af473ff6a90ef0ad65a70b5b105ee99b4f584a42c9179028da5edbac","observation_id":"297074cf-c779-44e2-8908-e09a5643fee6","resolution":{"observed_at":"2026-08-06T18:38:05.301301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.290567Z","title":"Re2G: Retrieve, rerank, generate","venue":null,"work_id":"3fd46603-3e49-45ea-9091-bf42c9011752","year":2022},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.172637Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:3c49bce52e10ca51acfbcf18b5e0a2175696d4fc4f25285c749661c62c4eed8f","observation_id":"07a42fa0-c628-4951-8e98-f343f782d6ca","resolution":{"observed_at":"2026-08-06T18:38:05.293527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.282317Z","title":"Fine-tuning llama for multi-stage text retrieval","venue":null,"work_id":"e4663b33-8a97-48cc-90dc-f6d84dce5a74","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.174780Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:d5ce002ccc91af6503af6e733caeee13110ba24ec7d8d0fc544acc2cd4adc980","observation_id":"62f8e9e6-a8e0-4918-9611-79bb03a070f0","resolution":{"observed_at":"2026-08-06T18:38:05.285368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.274138Z","title":"Financial time series forecasting with multi-modality graph neural network.Pattern Recognition, 121:108218, 2022","venue":null,"work_id":"9e31df0e-7a0b-4913-b0e0-f6a2858e6eb8","year":2022},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.177130Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:7ef65dc388472dfe32379a0bea111096b78755d47e8ab745e80fef67f49a9cc3","observation_id":"15098410-0ee8-4f38-9e36-813a93a4d34c","resolution":{"observed_at":"2026-08-06T18:38:05.277397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.266381Z","title":"Retrieval-augmented generation with knowledge graphs for customer service question answering","venue":null,"work_id":"a0e1d8ee-1092-400a-8989-cdcafc9fa9b1","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.179250Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:ebed369278aaff079b7737b98634b39489ce537e46907d95ba12406db737fd40","observation_id":"23e0ef84-d067-401b-81d2-a82d88026b01","resolution":{"observed_at":"2026-08-06T18:38:05.268920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.257933Z","title":"Kg-rag: Bridging the gap between knowledge and creativity, 2024","venue":null,"work_id":"27a6a8fc-f9bf-4c97-af2c-6e77c02321db","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.181994Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:cb2dad38f0cc6a5f91bbed4efafc3cfd0500a9871f32c9301894b11e293e5996","observation_id":"50f32f9a-87c0-4922-aac8-39cb168f923f","resolution":{"observed_at":"2026-08-06T18:38:05.261128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.250190Z","title":"Hybridrag: Integrating knowledge graphs and vector retrieval augmented generation for efficient information extraction","venue":null,"work_id":"58d73228-ca8d-4f00-8af2-386fbcadcd99","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.184281Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:8aadc73f17be23c9c2e1653ef4d791d7080aa91db8bce647b9a3a27e0a146a2c","observation_id":"3d244bd6-18ce-4fdb-8120-60d4147857b9","resolution":{"observed_at":"2026-08-06T18:38:05.252796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.186524Z","title":"From local to global: A graph rag approach to query-focused summarization, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.186524Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:2fa8b30340a72105c467e7ccd18ee3d9023ff430fd438f5b0ed24553639b8fae","observation_id":"16e9cd37-b2c6-4524-9d22-100c38e7777f","resolution":{"observed_at":"2026-08-06T18:38:05.186524Z","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":"2026-08-06T18:38:05.237506Z","title":"Ragas: Automated evaluation of retrieval augmented generation, 2023","venue":null,"work_id":"57d838ad-aed2-4df2-b80b-b2362707fbe3","year":2023},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.188790Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:adb753917e12d0efdca3765a4223a456f50ab68375b50129dacb9c4aa9300216","observation_id":"7e28ef2d-82af-433a-97ee-4f09e5720d60","resolution":{"observed_at":"2026-08-06T18:38:05.240494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.228937Z","title":"LongT5: Efficient text-to-text transformer for long sequences","venue":null,"work_id":"3b527cc1-a619-417b-9be9-d122331acea9","year":2022},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.191031Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:7a45d99924a8a50ada8affae845924367b964ca65db8a4f88ed802a536d6cf8d","observation_id":"805de10e-6cae-43b8-bffd-b6d863c9dbbb","resolution":{"observed_at":"2026-08-06T18:38:05.231773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T18:38:05.219117Z","title":"Multihop-RAG: Benchmarking retrieval-augmented generation for multi-hop queries","venue":null,"work_id":"2596900c-e6c7-42e9-8cdd-e0b59a325f42","year":2024},"citing_paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:05.193302Z"},"links":{"citing_paper":"/paper/2507.07695"},"observation_digest":"sha256:1da592638eb4d4a7009f4d377bf0d6b469c23332f2ab35d3b7ee5572d8df5c1e","observation_id":"9e4c1805-1aa0-4444-803d-53c78738444c","resolution":{"observed_at":"2026-08-06T18:38:05.223346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07695","last_updated":"2025-07-31T08:57:40Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T17:28:16.724527Z","submitted_at":"2025-07-10T12:19:03Z","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":19},"total_outbound_references":30},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2507.07695."}