{"as_of":"2026-08-23T20:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ccad3e531d79157c20abe71a2435ce8ec1233d2520a232d319881226eefa8e00","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T12:18:30.232009Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2606.06197/citation-record","integrity":"/paper/2606.06197/integrity","json":"/paper/2606.06197/citation-record.json","paper":"/paper/2606.06197"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:18:26.855479Z","title":"Nativqa: Multilingual culturally-aligned natural query for llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:26.855479Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:d27def7d5c5f816e0ef266464d57dd192123ce261bae0df28ea52fe8262f2582","observation_id":"7ed64b42-5f16-4a92-b58a-6672c2d6ef21","resolution":{"observed_at":"2026-08-02T12:18:26.855479Z","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":"2026-08-02T12:18:26.911197Z","title":"You make me feel like a natural question: Training QA systems on transformed trivia questions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:26.911197Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:0064eb0265af9f07a3aa91c4343c5e64bc98e0f4b37a6c602788be8df95dfd6a","observation_id":"6fc5e967-901e-4e89-adfa-fe7f14de5490","resolution":{"observed_at":"2026-08-02T12:18:26.911197Z","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":"2026-08-02T12:18:27.022862Z","title":"Exploring expected answer types for effective question answering systems for low resource language,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.022862Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:b2f50dd2119e3623ca6af20ebda35982cd030e2a96f4fa9ecdaeab7891cbfa7e","observation_id":"f8b50d98-9071-4b41-8e0a-e542b7b9ad05","resolution":{"observed_at":"2026-08-02T12:18:27.022862Z","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":"2026-08-02T12:18:27.135017Z","title":"LocalRQA: From generating data to lo- cally training, testing, and deploying retrieval-augmented QA systems,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.135017Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:c5731209551a26cd41bfee342351174c246831b0134ef935126750fa67604fa1","observation_id":"6b32aae1-2174-42ab-9ff7-696055416093","resolution":{"observed_at":"2026-08-02T12:18:27.135017Z","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":"2026-08-02T12:18:27.236655Z","title":"How accurate are LLMs at multi- question answering on conversational transcripts?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.236655Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:f53d162d57a041468d5ff0e77954b6165dcba21e5fbaa2f0f7a88cfb2893c4e3","observation_id":"9817807f-e34b-4845-a875-89b25bd92649","resolution":{"observed_at":"2026-08-02T12:18:27.236655Z","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":"2026-08-02T12:18:27.386423Z","title":"Desiderata for the context use of question answering systems,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.386423Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:134dc6072779fddd64690b81da0757596cb2d9b84a1e32b4e1f13bae59159021","observation_id":"18cf1567-f91c-4fb2-aa81-e5bbf32dce6a","resolution":{"observed_at":"2026-08-02T12:18:27.386423Z","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":"2026-08-02T12:18:27.500754Z","title":"Context-aware an- swer extraction in question answering,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.500754Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:9a8f82fcefb0c961ede606e3870c161c8b5b583cf7f49c1440504c0d3ce32810","observation_id":"a7c3c272-a27d-4257-a726-a16ed666995c","resolution":{"observed_at":"2026-08-02T12:18:27.500754Z","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":"2026-08-02T12:18:27.567011Z","title":"Never lost in the middle: Mastering long-context question answering with position-agnostic decompositional training,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.567011Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:690120b33c850147aad48a420e53bdf7733c6ee4b0cd7e7817ad94f107ecb720","observation_id":"a43a97c5-f3c5-4abc-8e43-955d7100c505","resolution":{"observed_at":"2026-08-02T12:18:27.567011Z","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":"2026-08-02T12:18:27.663434Z","title":"Augmenting compliance- guaranteed customer service chatbots: Context-aware knowledge expan- sion with large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.663434Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:9b634ac55e7eb1082e31f6d5ec790fbbf2ec8a5ec79dae3e99cd523b0a140a25","observation_id":"b11f7533-a7a1-4aef-a93f-44b7c7497a14","resolution":{"observed_at":"2026-08-02T12:18:27.663434Z","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":"2026-08-02T12:18:27.806852Z","title":"How proficient are large language models in formal languages? an in- depth insight for knowledge base question answering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.806852Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:ab5d4643e353cd328be8fb96e27eeea6cfab484036713d6bbe248a2183120b1f","observation_id":"b78a29b0-e7a3-4816-9b9b-ceb7ed9804a4","resolution":{"observed_at":"2026-08-02T12:18:27.806852Z","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":"2026-08-02T12:18:27.918981Z","title":"Webglm: Towards an efficient and reliable web-enhanced question-answering system,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:27.918981Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:792530c19190add9d5a6b0e5a4170ce25effce493ea034c1a98baa88a77525e4","observation_id":"c13ee3a2-588d-4196-aed6-af04c14b4896","resolution":{"observed_at":"2026-08-02T12:18:27.918981Z","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":"2026-08-02T12:18:28.067705Z","title":"Evaluating open- domain question answering in the era of large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.067705Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:28a80a47272b3b5d2c45dc1e6715848c7d98eebd0fa1aa5989a9e9516b483f50","observation_id":"36907bf6-f516-415b-bff0-967c444121a0","resolution":{"observed_at":"2026-08-02T12:18:28.067705Z","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":"2026-08-02T12:18:28.237881Z","title":"Few-shot prompt- ing for extractive quranic qa with instruction-tuned llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.237881Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:b46063d3567af030c1ad86d755ab70e2b0b78e3a42a5aa96bf9b7a90bd90068b","observation_id":"4c9f08d7-6ede-4c30-9171-00e361cc7ad5","resolution":{"observed_at":"2026-08-02T12:18:28.237881Z","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":"2026-08-02T12:18:28.391088Z","title":"Two- stage quranic qa via ensemble retrieval and instruction-tuned answer extraction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.391088Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:dcb420ce6097837dabf531b38fea042ae470b29860ae8c815df9bd02c421d7bf","observation_id":"f614c1e0-edfa-4a44-a86a-2f20b92cf78d","resolution":{"observed_at":"2026-08-02T12:18:28.391088Z","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":"2026-08-02T12:18:28.523470Z","title":"Cross-language approach for quranic qa,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.523470Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:f9140ad8a24de6b1ea072a23dc9d1301dffc06ff4c7cab014187210d911cca4c","observation_id":"8d9437ba-a00a-4109-8047-81432ef10b03","resolution":{"observed_at":"2026-08-02T12:18:28.523470Z","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":"2026-08-02T12:18:28.665817Z","title":"Hybrid graphs for table-and-text based question answering using llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.665817Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:03bffa1b5925353dcf1994b680c00859c63a644d407a238cae1c039f95ed8b5d","observation_id":"b05c76b7-1b51-48d4-b846-edbdce1bff7a","resolution":{"observed_at":"2026-08-02T12:18:28.665817Z","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":"2026-08-02T12:18:28.765543Z","title":"Large language models meet knowledge graphs for question answering: Synthesis and opportunities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.765543Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:539f92dbaffc8afc4295b89c8920d3f71a571b27c375f1fb9878ce58339fee7e","observation_id":"25dc59eb-ba8c-47cf-8a29-cee9c89ca9f0","resolution":{"observed_at":"2026-08-02T12:18:28.765543Z","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":"2026-08-02T12:18:28.902818Z","title":"Aestar at semeval-2025 task 8: Agentic llms for question answering over tabular data,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:28.902818Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:bd9a89788657c4b2468fed7d20489bb5b0c1b3d65610e1787c8b5966cb9938d9","observation_id":"6cbfe000-91d2-4900-8b08-234909f2046b","resolution":{"observed_at":"2026-08-02T12:18:28.902818Z","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":"2026-08-02T12:18:29.049486Z","title":"Opti- mized quran passage retrieval using an expanded qa dataset and fine- tuned language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.049486Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:59b9ab3f38f14fb29781569dd7a09bd1b8674cde1b1bacb67e827c1b2687eea5","observation_id":"429a859e-1ebf-4240-987b-183fdb96186f","resolution":{"observed_at":"2026-08-02T12:18:29.049486Z","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":"2026-08-02T12:18:29.182073Z","title":"Trustuqa: A trustful framework for unified structured data question answering,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.182073Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:a3287e85b8b019e4bfd5c3ff0321d562202d45d8e3c651f746833e53aab8e1c8","observation_id":"187b871b-cb8e-47cd-9a4c-66419562d624","resolution":{"observed_at":"2026-08-02T12:18:29.182073Z","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":"2026-08-02T12:18:29.286130Z","title":"Riro: Reshaping inputs, refining outputs unlocking the potential of large language models in data-scarce contexts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.286130Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:42245dff12443b2dbaece25ccdd32944d8ba3b3e004f332f1fe614e9d83db1bc","observation_id":"f1b79502-68eb-407a-90d9-f09854f244b9","resolution":{"observed_at":"2026-08-02T12:18:29.286130Z","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":"2026-08-02T12:18:29.375548Z","title":"Rationale-guided retrieval augmented generation for medical question answering,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.375548Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:fa56b74926951fb73551b0138fc53091393a0b189122fa9f03347ebeae53de43","observation_id":"11538550-0193-44c9-94a2-7a63e6851f3a","resolution":{"observed_at":"2026-08-02T12:18:29.375548Z","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":"2026-08-02T12:18:29.462429Z","title":"Llm-daas: Llm-driven drone- as-a-service operations from text user requests,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.462429Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:1a4dd04aa9260037039b3290d5f8e61a266dbf6de7cb14f033e8dc9e37abc966","observation_id":"f418e000-b5e0-4433-b07e-00f55b91fe8f","resolution":{"observed_at":"2026-08-02T12:18:29.462429Z","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":"2026-08-02T12:18:29.566639Z","title":"Few-shot optimized framework for hallucination detection in resource-limited nlp systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.566639Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:6d9c7a0b45e538aaa9631484c3ccb1603a9ba20fda40d1de20f52448c2f832d6","observation_id":"afaadc89-2384-4f59-870a-7cbccadef7c0","resolution":{"observed_at":"2026-08-02T12:18:29.566639Z","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":"2026-08-02T12:18:29.695067Z","title":"Sbu-nlp at semeval-2025 task 8: Self-correction and collaboration in llms for tabular question answer- ing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.695067Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:c306a352b2931b24262f2428cc1c79405cdea555f3dcdc1bbc85d39986f3e1df","observation_id":"ea03b1d8-ea8a-43e6-9780-7605303aeee0","resolution":{"observed_at":"2026-08-02T12:18:29.695067Z","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":"2026-08-02T12:18:29.808343Z","title":"Coordinated llm multi-agent systems for collaborative question-answer generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.808343Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:d786819cf5e6b36119dc32bbbec5eac5d88faf6598bad3d2ce0c6369d14e4601","observation_id":"ed9c6e9b-1822-4e59-8630-a15b688b3329","resolution":{"observed_at":"2026-08-02T12:18:29.808343Z","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":"2026-08-02T12:18:29.890774Z","title":"Large language model synergy for ensemble learning in medical question answering: design and evaluation study,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.890774Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:9b92fb5625dd83018012f781499e15ce0d5cb554dc38e5ac6fb22e1d8dadbbe9","observation_id":"bd64e6cb-9505-41ed-8e36-ae83ecf36dc6","resolution":{"observed_at":"2026-08-02T12:18:29.890774Z","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":"2026-08-02T12:18:29.995627Z","title":"Llm-sem: A sentiment- based student engagement metric using llms for e-learning platforms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:29.995627Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:ef1fd65a3f48c1c29917b899d0b15f31ef8811d76ab888e668ed694ef8ace746","observation_id":"504de2df-9424-4f65-a5d4-11d4e0fa7da9","resolution":{"observed_at":"2026-08-02T12:18:29.995627Z","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":"2026-08-02T12:18:30.091817Z","title":"Llm-medqa: Enhancing medical question answering through case studies in large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:30.091817Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:e6671e10547a1c8c3dcc2e8a48199745ad674e3cac005e57dbd79f4b3a494d34","observation_id":"b21cc9a2-1627-4423-b12e-55d3d833e25f","resolution":{"observed_at":"2026-08-02T12:18:30.091817Z","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":"2026-08-02T12:18:30.154703Z","title":"Msa at semeval-2025 task 3: High quality weak labeling and llm ensemble verification for multilin- gual hallucination detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:30.154703Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:d2eff817a57f045ee49a7a0ba45598157c451efa0f83b07b3f1e7c63ceadf9a2","observation_id":"bfbdf647-8512-41bf-a2f6-ed0b820f1b61","resolution":{"observed_at":"2026-08-02T12:18:30.154703Z","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":"2026-08-02T12:18:30.232009Z","title":"Erpa: Efficient rpa model integrating ocr and llms for intelligent document processing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T12:18:30.232009Z"},"links":{"citing_paper":"/paper/2606.06197"},"observation_digest":"sha256:c55b0700803c2b29c22abedab5d8049f7eec48e62b64dbb4d30ca558ac8192ff","observation_id":"976813a8-757b-46ce-8f9a-0eb85f058f1d","resolution":{"observed_at":"2026-08-02T12:18:30.232009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.06197","last_updated":"2026-07-19T15:55:15Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-02T12:18:26.494624Z","submitted_at":"2026-06-04T14:04:11Z","title":"Improving Answer Extraction in Context-based Question Answering Systems Using LLMs"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":31},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2606.06197."}