{"as_of":"2026-08-23T06:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2a0c8825466fb3405f8786037689ee0250ff45fe09b2e3f0448f67de5a29a668","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:48:07.554421Z","state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"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/2506.16037/citation-record","integrity":"/paper/2506.16037/integrity","json":"/paper/2506.16037/citation-record.json","paper":"/paper/2506.16037"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.820422Z","title":"Cab-kws: Con- trastive augmentation: An unsupervised learning approach for keyword spotting in speech technology,","venue":null,"work_id":"c023ca7c-01e5-4bf2-8722-05c0addada8b","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.569112Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:a368c2a36390e514522646685b10613d9c531ee4059b849a63d5c42db60f9a07","observation_id":"e0430962-32e6-42ba-a03f-2c3c3b3c95ee","resolution":{"observed_at":"2026-08-06T23:48:07.825987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.800664Z","title":"Attention-driven interaction network for e-commerce recom- mendations,","venue":null,"work_id":"a79ff8f0-aa28-485e-993c-49a2d33dfd01","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.726242Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:92bcc59468074b4da17860ceb77e78a0d2a19c26ca63b587701a8f935ff7bf55","observation_id":"1b8bc425-8253-44b1-b0cb-5874935efc74","resolution":{"observed_at":"2026-08-06T23:48:07.806307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15800","last_updated":"2025-09-03T07:11:43Z","snapshot_observed_at":"2026-08-16T13:16:56.997474Z","submitted_at":"2025-04-22T11:30:13Z","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.15800","snapshot_observed_at":"2026-08-06T23:48:06.816069Z","title":"Finder: Financial dataset for question answer- ing and evaluating retrieval-augmented generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.816069Z"},"links":{"cited_paper":"/paper/2504.15800","citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:53a2ba8aa7ad3ae9ccf199880b3f0816f8f917757023e5fae7608423f763958e","observation_id":"e451ad7e-2013-4184-80b5-b883dbdf1cc0","resolution":{"observed_at":"2026-08-06T23:48:06.816069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.15191","last_updated":"2025-03-19T13:21:49Z","snapshot_observed_at":"2026-08-20T01:49:22.684103Z","submitted_at":"2025-03-19T13:21:49Z","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.15191","snapshot_observed_at":"2026-08-06T23:48:06.852776Z","title":"Optimizing retrieval strate- gies for financial question answering documents in retrieval-augmented generation systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.852776Z"},"links":{"cited_paper":"/paper/2503.15191","citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:1d16f9f656dc6da9fb156dc0a12f7347f59c2cda3fa208ad646e0b40d98e7347","observation_id":"afd3ab8c-3f1d-4f72-b0b5-de66c0a56720","resolution":{"observed_at":"2026-08-06T23:48:06.852776Z","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":"2026-08-06T23:48:07.779861Z","title":"Coarse-to-fine multi-view 3d reconstruction with slam opti- mization and transformer-based matching,","venue":null,"work_id":"3e944ee8-1e5c-4991-9532-67d4847c4e87","year":2024},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.920817Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:fd0ce0f79e72d81d4ec156cda2db863d200e368148c7c2bbb7a0f00cb56e6015","observation_id":"aef49496-a5f5-4f3e-85ce-eae748ab21f8","resolution":{"observed_at":"2026-08-06T23:48:07.785505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.761429Z","title":"Breast cancer risk prediction: A machine learning study using network analysis,","venue":null,"work_id":"8b27fddd-5d35-4e6e-9734-7dff2f9271bb","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:06.986271Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:5db7e19b3eeefba1e5dae822756fd5cea9287659960815d8cae2e444b2847a3c","observation_id":"a78ee2d3-eb80-4451-9d20-0dd7e4184a58","resolution":{"observed_at":"2026-08-06T23:48:07.767090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.740043Z","title":"Gemini-graphqa: Integrating language models and graph encoders for executable graph reasoning,","venue":null,"work_id":"9fea6f49-375b-402b-a97a-876cd0bc9699","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.061163Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:b20d43c4e73a9055490589ebefe71e803dc5615179e7b6f569d35a5cdbdb68cc","observation_id":"cac47411-0d3a-4b2f-8773-5e75068b39fd","resolution":{"observed_at":"2026-08-06T23:48:07.746988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09980","last_updated":"2024-05-16T10:53:31Z","snapshot_observed_at":"2026-08-21T08:43:52.597160Z","submitted_at":"2024-05-16T10:53:31Z","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09980","snapshot_observed_at":"2026-08-06T23:48:07.211413Z","title":"Fintextqa: A dataset for long-form financial question answering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.211413Z"},"links":{"cited_paper":"/paper/2405.09980","citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:315bd1c8b596c351093e8160fde918378bcdc055e10c2860226ecc22e7614b2b","observation_id":"bd5a954e-3032-40e3-8bfc-41d24c39d6fc","resolution":{"observed_at":"2026-08-06T23:48:07.211413Z","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":"2026-08-06T23:48:07.341095Z","title":"Hy- bridrag: Integrating knowledge graphs and vector retrieval augmented generation for efficient information extraction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.341095Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:680fb0c13e26e4742648187b3a982a7fd9720174aea9d71e721dd734ce76e968","observation_id":"02d0a714-3ca7-4caf-b3f6-535a1363c6d0","resolution":{"observed_at":"2026-08-06T23:48:07.341095Z","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":"2026-08-06T23:48:07.707199Z","title":"Evaluating retrieval- augmented generation models for financial report question and answer- ing","venue":null,"work_id":"5ab0c38d-bfba-4c07-b281-01c227500803","year":2024},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.473301Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:81f29b43db645b9a0fcf1627b52fa2db655cf5570112f6ac27e7450b56f93cc8","observation_id":"8dade4c7-e5bf-4a11-ab57-610f3c5d39fc","resolution":{"observed_at":"2026-08-06T23:48:07.712250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.689045Z","title":"Towards intelligent cloud scheduling: Dynasched-net with rein- forcement learning and predictive modeling,","venue":null,"work_id":"53bf4c4f-2232-4551-9b17-8a92d33689be","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.540897Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:fb4b708ca17e97168b14c9fca7d37af62f4b004cae26786bba661ee0a9ac0508","observation_id":"649383fa-4459-43b1-8981-fa1f146d6e01","resolution":{"observed_at":"2026-08-06T23:48:07.694668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.15532134","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Tax share analysis and prediction of kernel extreme learning machine optimized by vector weighted average algorithm,","venue":"RePEc: Research Papers in Economics","work_id":"bb43d0cc-4c7f-4396-bdbc-07aaa051b194","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.548086Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:a9e560085deb2a1b2f5563ba503cb7eea1956b9c7b8b1028c390f6891b9a18ac","observation_id":"42e957a9-4994-431b-aa37-88fa6f175f59","resolution":{"observed_at":"2026-08-06T23:48:07.599359Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:48:07.670743Z","title":"Privacypreservenet: A multilevel privacy-preserving framework for multimodal llms via gradient clipping and attention noise,","venue":null,"work_id":"bc548bf3-add3-460b-9533-398b61be135a","year":2025},"citing_paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:48:07.554421Z"},"links":{"citing_paper":"/paper/2506.16037"},"observation_digest":"sha256:e86c234cc5801250e7b401b6c2fa3a282ee5109e940b775856615a0e4ff0e2ed","observation_id":"7f093e72-017d-4d34-bf25-13612f5cda97","resolution":{"observed_at":"2026-08-06T23:48:07.675770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.16037","last_updated":"2025-06-19T05:22:18Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:17:49.257160Z","submitted_at":"2025-06-19T05:22:18Z","title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":8},"total_outbound_references":13},"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 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2506.16037."}