{"as_of":"2026-08-15T21:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ad667230093e871390b75b68652ec7d118c3e70bdbcdb7fe65d98535de62feb4","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T00:24:47.278909Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2608.01311/citation-record","integrity":"/paper/2608.01311/integrity","json":"/paper/2608.01311/citation-record.json","paper":"/paper/2608.01311"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T00:24:41.071078Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.071078Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:063675df8e9c6667d2546dd5a6835e55da2fa305b2e32b61e4fdaacfeeb1e2e2","observation_id":"acf7fa1e-c8e4-400f-b88f-8279c6205a37","resolution":{"observed_at":"2026-08-06T00:24:41.071078Z","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":"2026-08-06T00:24:55.726590Z","title":"Leveraging passage retrieval with generative models for open domain question answering","venue":null,"work_id":"17b71fb4-fbb0-49ee-aa48-8496eb8d75ce","year":2021},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.101890Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:3e779e2b1c6a12534385fde415393ef102a341482ca6daae2e99533c5dc29b28","observation_id":"a21e70d9-933f-424e-b515-c7382f275b80","resolution":{"observed_at":"2026-08-06T00:24:55.839994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16130","last_updated":"2025-02-19T10:49:41Z","snapshot_observed_at":"2026-07-06T18:05:11.700127Z","submitted_at":"2024-04-24T18:38:11Z","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16130","snapshot_observed_at":"2026-08-06T00:24:41.264186Z","title":"From local to global: A graph rag approach to query-focused summarization.arXiv preprint arXiv:2404.16130, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.264186Z"},"links":{"cited_paper":"/paper/2404.16130","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:3db4a1b64e4132fbfebf5236506f0e3acb9b973ba1048528af2dd31338d16091","observation_id":"87ac33ba-124e-4e02-8871-15d8bcde5cc6","resolution":{"observed_at":"2026-08-06T00:24:41.264186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03381","last_updated":"2024-07-23T11:54:10Z","snapshot_observed_at":"2026-08-13T00:37:48.214988Z","submitted_at":"2024-04-04T11:27:54Z","title":"Learning to Plan and Generate Text with Citations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03381","snapshot_observed_at":"2026-08-06T00:24:41.299085Z","title":"Learning to plan and generate text with citations.arXiv preprint arXiv:2404.03381, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.299085Z"},"links":{"cited_paper":"/paper/2404.03381","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:1b8f2efea4d514a9761469a331c8331d1597682fb402fc0e5386527a6acb96f0","observation_id":"d7359a9d-2658-4df6-b872-2f582cbabe7c","resolution":{"observed_at":"2026-08-06T00:24:41.299085Z","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":"2026-08-06T00:24:55.467470Z","title":"Kanell, Peter Xu, Omar Khattab, and Monica S","venue":null,"work_id":"f942771d-5762-4da4-b2e4-1e7d4c0053a1","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.438604Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:9ad9598b04f1165079750d10e39aabd5873acb2b0f062db927797599e04cb893","observation_id":"6772fa55-f515-439a-81d6-439e60130188","resolution":{"observed_at":"2026-08-06T00:24:55.594703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12652","last_updated":"2023-05-24T05:08:07Z","snapshot_observed_at":"2026-08-02T02:08:12.414817Z","submitted_at":"2023-01-30T04:18:09Z","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12652","snapshot_observed_at":"2026-08-06T00:24:41.567857Z","title":"Replug: Retrieval-augmented black-box language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.567857Z"},"links":{"cited_paper":"/paper/2301.12652","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:dbd5f78666b22420494081ecaf5e38c8f934336c8ad09d005656e9173cf2af4a","observation_id":"549bfc47-4e87-41f6-bca6-b9895b5ebba1","resolution":{"observed_at":"2026-08-06T00:24:41.567857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.10308","last_updated":"2024-04-16T06:34:08Z","snapshot_observed_at":"2026-08-14T05:32:53.778879Z","submitted_at":"2024-04-16T06:34:08Z","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","version":1},"cited_work":{"arxiv_id":"2404.10308","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.10308","snapshot_observed_at":"2026-08-06T00:24:49.155086Z","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","venue":"cs.LG","work_id":"1d0fc0f1-047e-40c9-bed1-fe70851cbe5e","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.672867Z"},"links":{"cited_paper":"/paper/2404.10308","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:8f9f5822a59a8c0c1897ae34a2b283628180947d75a508e3345b039a3eb60e22","observation_id":"dc284e69-4de1-44f4-ab57-4db3c1945448","resolution":{"observed_at":"2026-08-06T00:24:49.230186Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:55.249540Z","title":"Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models","venue":null,"work_id":"eed202d7-8212-4139-9629-4050908840d4","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.741602Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:2de289b021121b4cbc0e2f2493df1fd8c8f7c54a12d1bf8323a0e539a12977fd","observation_id":"80fc8168-3c8c-4cbe-b67b-7cefedf556eb","resolution":{"observed_at":"2026-08-06T00:24:55.350509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:41.871685Z","title":"Mirage: Scaling test-time inference with parallel graph-retrieval-augmented reasoning chains.arXiv preprint arXiv:2508.18260, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:41.871685Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:9b08f5b301d6a841e9e116856bebaad3661d433601220930c29659469367afd0","observation_id":"c565aa9e-adca-487c-b8b2-4f9cf7aafae8","resolution":{"observed_at":"2026-08-06T00:24:41.871685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11511","last_updated":"2023-10-17T18:18:32Z","snapshot_observed_at":"2026-08-12T20:38:07.563701Z","submitted_at":"2023-10-17T18:18:32Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11511","snapshot_observed_at":"2026-08-06T00:24:42.062854Z","title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection.arXiv preprint arXiv:2310.11511, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.062854Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:3253e9f4d080407a564346be39dd1e6d176e2c451b0d57f630aa4c79e66d001d","observation_id":"4db9dcbb-5a6f-4744-9a01-fd4a17f71f1c","resolution":{"observed_at":"2026-08-06T00:24:42.062854Z","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":"2026-08-06T00:24:54.932251Z","title":"Factscore: Fine-grained atomic evaluation of factual precision in long form text generation","venue":null,"work_id":"fbfaa277-6530-4a85-989e-da231ae76aec","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.179206Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:02e3254233b91d758e60f5c3f18c8a096a97c49a1507cede4543ef2cb4a76e4d","observation_id":"7f0b42dc-2453-4a39-bebd-5f2a5cb8d4a6","resolution":{"observed_at":"2026-08-06T00:24:55.070115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:54.692248Z","title":"Alignscore: Evaluating factual consistency with a unified alignment function","venue":null,"work_id":"44c07a73-8ad7-42d5-a46c-36d0bc2accd4","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.369931Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:2c6724dc3b3339f14d835b2187d5c1ebec5ca724fed2bdf3b89d145c18188f56","observation_id":"408b7ade-6784-44a5-8906-a4a0a312a886","resolution":{"observed_at":"2026-08-06T00:24:54.802054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09525","last_updated":"2021-11-18T05:02:31Z","snapshot_observed_at":"2026-08-15T02:51:56.797215Z","submitted_at":"2021-11-18T05:02:31Z","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.09525","snapshot_observed_at":"2026-08-06T00:24:42.457819Z","title":"Bennett, and Marti A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.457819Z"},"links":{"cited_paper":"/paper/2111.09525","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:f54e2463a532d2202c9bae1d5428bfe50346e1d30a19695ef94ffb682308fa1e","observation_id":"73761409-4cb5-45d5-839d-718e3909c6f6","resolution":{"observed_at":"2026-08-06T00:24:42.457819Z","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":"2026-08-06T00:24:54.502138Z","title":"Wayback machine.https://archive.org/web/, 2024","venue":null,"work_id":"b9878f3a-e6a6-4453-989f-073fdd58dfb2","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.614834Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:a329ed82bfe85b2a2a4e30d5f7ad64b9e103437c26cc34561828f63c8ddb8474","observation_id":"80c48667-fede-430e-a11c-acf8e55e85ad","resolution":{"observed_at":"2026-08-06T00:24:54.582040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10883","last_updated":"2022-07-22T17:37:58Z","snapshot_observed_at":"2026-08-15T13:09:17.506019Z","submitted_at":"2022-06-22T07:26:55Z","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10883","snapshot_observed_at":"2026-08-06T00:24:42.723650Z","title":"Multi-lexsum: Real-world summaries of civil rights lawsuits at multiple granularities.arXiv preprint arXiv:2206.10883, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.723650Z"},"links":{"cited_paper":"/paper/2206.10883","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:f75ee616383fc63ebd1a9f088fe86ed9f800d626936a934a510f5fcb492be7c1","observation_id":"1a5c1f30-4d34-4948-ad52-b017fb493b88","resolution":{"observed_at":"2026-08-06T00:24:42.723650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-06T00:24:42.815445Z","title":"Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.815445Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:007c69eeb37baabd4c3a3469b1f662ce6677f4dcd4c72ec7449dc7cc01346119","observation_id":"0beca5af-fdc1-4329-bddc-4cc46d56a768","resolution":{"observed_at":"2026-08-06T00:24:42.815445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-06T00:24:42.917170Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:42.917170Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:105226878a89082598f6f8d8f89edca7a235830b9c140759e4c5efc67698e557","observation_id":"c506a304-2915-482d-848e-ccb683c615f9","resolution":{"observed_at":"2026-08-06T00:24:42.917170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-06T00:24:43.059118Z","title":"Qwen2.5 technical report.arXiv preprint arXiv:2412.15115, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.059118Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:2bf48158c0218ad0191865d9f8fc5c10eb8bf11b52ff97d3dbeea270ef88f099","observation_id":"fe208088-2df4-400f-b40f-0be6d397a059","resolution":{"observed_at":"2026-08-06T00:24:43.059118Z","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":"2026-08-06T00:24:54.226691Z","title":"Xing, Ion Stoica, and Joseph E","venue":null,"work_id":"39286f63-7aec-4a45-829c-3eb13226f439","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.160150Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:4e2c55f8eb649693c4b69fc5a9ebeb677129313fa1459842492866043993547c","observation_id":"90940bd7-5fe3-4c9a-87dd-7d672c64ad76","resolution":{"observed_at":"2026-08-06T00:24:54.335040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:54.040995Z","title":"The probabilistic relevance framework: Bm25 and beyond.Foundations and Trends in Information Retrieval, 2009","venue":null,"work_id":"35ff8ff0-5536-40c6-be8f-0170a3b2ef88","year":2009},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.266973Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:1496002fc6d9dff234e45ba89096881b21f129fb2ae67e4c6287c448546dd69f","observation_id":"60930da3-cdeb-426e-a8fa-90a3a1b5c86f","resolution":{"observed_at":"2026-08-06T00:24:54.120639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.03012","last_updated":"2024-11-05T11:25:12Z","snapshot_observed_at":"2026-08-13T20:20:48.706263Z","submitted_at":"2024-11-05T11:25:12Z","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","version":1},"cited_work":{"arxiv_id":"2411.03012","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.03012","snapshot_observed_at":"2026-08-06T00:24:48.339817Z","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","venue":"cs.CL","work_id":"08a03dc2-b3d5-4c1b-85b6-b1a965285dfe","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.428868Z"},"links":{"cited_paper":"/paper/2411.03012","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:4d8f422bd1538cebb56467743663d790d6497250c3e48d6bd82a30175a0526ba","observation_id":"f0e26f3b-9095-46e8-b2bd-ba346a03eb60","resolution":{"observed_at":"2026-08-06T00:24:48.434703Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03187","last_updated":"2024-03-05T18:22:33Z","snapshot_observed_at":"2026-08-13T04:02:48.790747Z","submitted_at":"2024-03-05T18:22:33Z","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03187","snapshot_observed_at":"2026-08-06T00:24:43.540189Z","title":"Reliable, adaptable, and attributable language models with retrieval.arXiv preprint arXiv:2403.03187, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.540189Z"},"links":{"cited_paper":"/paper/2403.03187","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:6edfd7a6491536e9387e716174f8c92b72ecebcd44bbd9b4b241b39f69094386","observation_id":"9399b5f3-dfcc-4967-9068-8defbb6faa01","resolution":{"observed_at":"2026-08-06T00:24:43.540189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-06T00:24:43.679174Z","title":"Peters, and Arman Cohan","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.679174Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:be8fd5ab698de70d05d8a4cb52ef8c5186e1957a3365c52692a79f660a2ec2d3","observation_id":"abb0babd-da61-4da0-a22d-fa2bf1530f66","resolution":{"observed_at":"2026-08-06T00:24:43.679174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.01625","last_updated":"2023-10-30T19:44:47Z","snapshot_observed_at":"2026-08-13T11:50:37.389751Z","submitted_at":"2023-05-02T17:35:08Z","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.01625","snapshot_observed_at":"2026-08-06T00:24:43.820633Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.820633Z"},"links":{"cited_paper":"/paper/2305.01625","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:66af2a9966e4e7716b0127c38ccbb18cbf10dbde943e8f288495a9bcde301d06","observation_id":"57e32bde-4fb9-4ff8-ab20-ceaa24f58f89","resolution":{"observed_at":"2026-08-06T00:24:43.820633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10247","last_updated":"2023-01-20T06:13:46Z","snapshot_observed_at":"2026-08-13T13:39:39.954896Z","submitted_at":"2022-11-18T14:07:29Z","title":"GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state","version":2},"cited_work":{"arxiv_id":"2211.10247","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.10247","snapshot_observed_at":"2026-08-06T00:24:47.932135Z","title":"GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state","venue":"cs.CL","work_id":"fbe8133a-1090-4440-9314-c5ac07f3e3ca","year":2022},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:43.965549Z"},"links":{"cited_paper":"/paper/2211.10247","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:1f035ee75e92ca0fc92c3491e13cb2997aed44d2385cf4e60b11aa116bf1147a","observation_id":"c8b3f963-bed9-4ab4-a1af-70a4063b1106","resolution":{"observed_at":"2026-08-06T00:24:47.989266Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:53.896159Z","title":"Attributed question answering: Evaluation and modeling for attributed large language models","venue":null,"work_id":"8bd5451b-5fae-4b8b-9c9d-e21b7e73db7b","year":2022},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.034951Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:5819915786daca64d2cd1db8c18b817c7c5cd4f23ea0d5164452100c14ad6ca3","observation_id":"e4472114-c5f6-40f8-85f8-50fcbccd9f12","resolution":{"observed_at":"2026-08-06T00:24:53.943596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:53.617569Z","title":"Booookscore: A systematic exploration of book-length summarization in the era of llms","venue":null,"work_id":"6938dc62-77b6-49ec-b3db-4469058c0a49","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.157628Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:c714313d4a55d40dae30abbf4d5626ef1e84f2b0ac70ed829027e5df7fad5a4f","observation_id":"fd111d2c-c7a5-4fda-86c5-39e1b432f36c","resolution":{"observed_at":"2026-08-06T00:24:53.723852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15595","last_updated":"2023-06-28T04:26:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-27T16:26:26Z","title":"Extending Context Window of Large Language Models via Positional Interpolation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.15595","snapshot_observed_at":"2026-08-06T00:24:44.314513Z","title":"Extending context window of large language models via positional interpolation.arXiv preprint arXiv:2306.15595, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.314513Z"},"links":{"cited_paper":"/paper/2306.15595","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:164db14a47140a78cc370586210142dd377482f1f4a3a10cdba61550db66910a","observation_id":"1fb17bb4-5e54-46bd-941a-15773d26da87","resolution":{"observed_at":"2026-08-06T00:24:44.314513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12307","last_updated":"2024-03-08T15:26:38Z","snapshot_observed_at":"2026-08-13T10:08:08.030837Z","submitted_at":"2023-09-21T17:59:11Z","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12307","snapshot_observed_at":"2026-08-06T00:24:44.407443Z","title":"Longlora: Efficient fine-tuning of long-context large language models.arXiv preprint arXiv:2309.12307, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.407443Z"},"links":{"cited_paper":"/paper/2309.12307","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:3c478952f66d27b5c2718b692a2d8146416446ee562c4652c271b893d0bc46a7","observation_id":"8893493d-b293-419b-821c-1f099d6c755e","resolution":{"observed_at":"2026-08-06T00:24:44.407443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10509","last_updated":"2019-04-23T19:29:47Z","snapshot_observed_at":"2026-08-09T19:46:04.857927Z","submitted_at":"2019-04-23T19:29:47Z","title":"Generating Long Sequences with Sparse Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.10509","snapshot_observed_at":"2026-08-06T00:24:44.535188Z","title":"Generating long sequences with sparse transformers","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.535188Z"},"links":{"cited_paper":"/paper/1904.10509","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:04e456edaa7e421c7f64add7ef1b8db61d8931b4b070ee36aec28c9fed758ee8","observation_id":"c65c9d88-c735-4362-b2ec-a74d67b734ff","resolution":{"observed_at":"2026-08-06T00:24:44.535188Z","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":"2026-08-06T00:24:53.255073Z","title":"A discourse-aware attention model for abstractive summarization of long documents","venue":null,"work_id":"d19c5ba7-ad28-4cbf-960d-45e84c5e3913","year":2018},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.634382Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:a29a16397c2df8db9ea90f6733f43a09a01c72b713b330fa161ff81a4a4d1409","observation_id":"d31371a8-fa54-4a91-8392-a90db4305495","resolution":{"observed_at":"2026-08-06T00:24:53.486865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-11T21:19:33.078277Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-06T00:24:44.823401Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers.arXiv preprint arXiv:2210.17323, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.823401Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:fa2466e18b43fd183493d028707fe84a07b93de7700b91b09af1a2adabeb2669","observation_id":"a35bd917-19b4-490f-8dd8-bc422acfaa47","resolution":{"observed_at":"2026-08-06T00:24:44.823401Z","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":"2026-08-06T00:24:52.984739Z","title":"Enabling large language models to generate text with citations","venue":null,"work_id":"1023d545-977d-4122-a790-5e5e0dbd0fc9","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:44.959468Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:187a0572873fa31d23c1ce5d2758b0b2912e1990ea92b8266747633cf2922e33","observation_id":"99514397-1228-45a7-8087-25b4f90930c4","resolution":{"observed_at":"2026-08-06T00:24:53.058484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:52.688134Z","title":"Memsum: Extractive summarization of long documents using multi-step episodic markov decision processes","venue":null,"work_id":"02239beb-8fa4-44c9-8bb0-87c8afb092a0","year":2022},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.184753Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:26d8beb6438a59682b0070b6e60537b9b0666cfcbed8e06d35cf9cd36a85925e","observation_id":"efc4ac4c-a0a3-4063-b6d5-d3236dc5b105","resolution":{"observed_at":"2026-08-06T00:24:52.805583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.03654","last_updated":"2021-10-06T21:02:00Z","snapshot_observed_at":"2026-07-06T09:26:29.068023Z","submitted_at":"2020-06-05T19:54:34Z","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.03654","snapshot_observed_at":"2026-08-06T00:24:45.263115Z","title":"Deberta: Decoding-enhanced bert with disentan- gled attention.arXiv preprint arXiv:2006.03654, 2021","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.263115Z"},"links":{"cited_paper":"/paper/2006.03654","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:2bbbd2b8941d56a1aee7c736456da19ddc6cd9c11b67f4e40e01335f87a473ed","observation_id":"528771f1-14c5-4250-b603-bb7c300897a2","resolution":{"observed_at":"2026-08-06T00:24:45.263115Z","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":"2026-08-06T00:24:52.431662Z","title":"Transformers are rnns: Fast autoregressive transformers with linear attention.ICML, 2020","venue":null,"work_id":"2170afee-ec5b-4092-9eb2-2b9e33c78501","year":2020},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.363796Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:598eee038296fdd27836b3c2b892e5bde830a14df0326579fbe7d753b2a50552","observation_id":"1cdc5a89-6a35-4efe-88cc-206a60fedbd0","resolution":{"observed_at":"2026-08-06T00:24:52.575285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:52.133046Z","title":"Booksum: A collection of datasets for long-form narrative summarization","venue":null,"work_id":"67c8ccba-fb22-4526-8189-cc8b6c45d8e2","year":2022},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.469399Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:460d48e2d285587b6cbd9c2d744cc4dac2e671351e518b0ee1ef2987f30de3ef","observation_id":"9a1792c7-677b-4fa6-b620-9b0d88cbe784","resolution":{"observed_at":"2026-08-06T00:24:52.257913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02060","last_updated":"2024-06-12T02:46:16Z","snapshot_observed_at":"2026-08-15T14:57:42.705501Z","submitted_at":"2024-04-02T15:59:11Z","title":"Long-context LLMs Struggle with Long In-context Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02060","snapshot_observed_at":"2026-08-06T00:24:45.625119Z","title":"Long-context llms struggle with long in-context learning.arXiv preprint arXiv:2404.02060, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.625119Z"},"links":{"cited_paper":"/paper/2404.02060","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:eba68fbd57bd06bef872acc6cc27d972d519d4bbf9d38f7e26345917faf4f30d","observation_id":"47cae494-6a96-47a4-a6c8-c94a54562870","resolution":{"observed_at":"2026-08-06T00:24:45.625119Z","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":"2026-08-06T00:24:51.924761Z","title":"Rouge: A package for automatic evaluation of summaries","venue":null,"work_id":"53d6a18c-0718-4f30-b168-9deee65a34e6","year":2004},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.734761Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:298a695cdcc92ad8ca5503a003ab3d5527828a4d3fa62a689fd8edf2bc040d62","observation_id":"9a890a9c-3bb1-42cf-8464-dcdfd628f637","resolution":{"observed_at":"2026-08-06T00:24:52.034753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:51.572059Z","title":"Text summarization with pretrained encoders","venue":null,"work_id":"7914dc2d-0447-4ec7-8540-c37eff80cd50","year":2019},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.844743Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:bee1996401b2fb5eb5c55751657e545e915da170298f4b293ceecba652f36004","observation_id":"296625d5-9ba1-4f6a-8758-19201c8d5357","resolution":{"observed_at":"2026-08-06T00:24:51.677378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:51.304379Z","title":"Zeroscrolls: A zero-shot benchmark for long text understanding","venue":null,"work_id":"7447703b-1b68-459f-bb19-48cd92f5a959","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:45.985009Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:b1790a882ff6f96eedfde60f32aee752c638f8729570f4eb824b5f80d0931dcb","observation_id":"f886263c-cc2d-4882-b347-6f0bef096da9","resolution":{"observed_at":"2026-08-06T00:24:51.403497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:51.151882Z","title":"Extractive is not faithful: An investigation of broad unfaithfulness problems in extractive summarization","venue":null,"work_id":"cd14f26b-499d-415a-a397-bbf7ad1d27ee","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:46.197713Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:0ceeff8e00c0f070a1c49d7e8e4f59a597159ca656d3e0d90ad27d19cf808a23","observation_id":"840a3813-1770-4139-8864-479e43a778b2","resolution":{"observed_at":"2026-08-06T00:24:51.215435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:50.855236Z","title":"Benchmarking foundation models with language- model-as-an-examiner.Advances in Neural Information Processing Systems, 2023","venue":null,"work_id":"d630ce37-7f51-4970-ad16-5ab4cf3ae0d4","year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:46.307854Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:cbc332aeba3693235b59d24c1a234a4709364622940b0e708d2ab0a748f0919a","observation_id":"94bf3325-3f9b-4b56-802d-c1811a63bba4","resolution":{"observed_at":"2026-08-06T00:24:50.954752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.11998","last_updated":"2024-03-10T19:34:57Z","snapshot_observed_at":"2026-08-13T10:08:28.290453Z","submitted_at":"2023-09-21T12:13:55Z","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.11998","snapshot_observed_at":"2026-08-06T00:24:46.403756Z","title":"Lmsys-chat-1m: A large-scale real-world llm conversation dataset.arXiv preprint arXiv:2309.11998, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:46.403756Z"},"links":{"cited_paper":"/paper/2309.11998","citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:95387d8d7c74dd7ddc30fafc290d0c4ae755f7e00e38749486a912cbf95ded3c","observation_id":"718a4ffc-6eed-4416-ada0-1ad21d066cc0","resolution":{"observed_at":"2026-08-06T00:24:46.403756Z","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":"2026-08-06T00:24:50.628116Z","title":null,"venue":null,"work_id":"daa54fbe-1941-42e8-9994-1148c2c14543","year":null},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:46.564692Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:a794a8d9daacedcd60dd23bede8a8e097a0d4733d15419f2450202ee554de5d7","observation_id":"40ae6733-2466-43e8-a293-8cc984889b77","resolution":{"observed_at":"2026-08-06T00:24:50.751564Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:50.314739Z","title":null,"venue":null,"work_id":"436fe839-6d1c-4e2a-8f8b-e4d92320fe4c","year":null},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:46.874753Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:271a0c8daae57e1af690483baf8d476247a662406887182ae607f83e262ea413","observation_id":"c05c0935-64c8-4bb7-9b0b-5235162bd012","resolution":{"observed_at":"2026-08-06T00:24:50.470660Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:50.028301Z","title":"section_title","venue":null,"work_id":"047b900a-4419-4896-b54c-1193dbfa1d72","year":2024},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:47.030718Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:66276559bb611acbcf8cb49604b1c0d9712f0fe204b14ce28e9704aeab72f6e7","observation_id":"1168bac8-e447-4966-86bd-638849fc85fb","resolution":{"observed_at":"2026-08-06T00:24:50.104823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:49.714117Z","title":"It explains how traditional education ne- glects these topics and how they can be learned through experiential learning and CASHFLOW games","venue":null,"work_id":"f8dd2ffc-5215-45e9-91f8-6928235b3364","year":null},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:47.127510Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:64a027edf3bd52fbe79825524ea2f0eb4ed7c969191c1cbca632208de6e2ab79","observation_id":"afec0b05-988d-45e4-9aac-44719b6675a9","resolution":{"observed_at":"2026-08-06T00:24:49.877329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T00:24:49.494769Z","title":"It explains how giving first fosters reciprocity and how creating income involves making money work for you, not working for money","venue":null,"work_id":"023ccb0c-a1ef-4fc2-9f14-edd346b75d19","year":null},"citing_paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:47.278909Z"},"links":{"citing_paper":"/paper/2608.01311"},"observation_digest":"sha256:905d06063b8e4f78638479e09185bde4485e6b5aafe5c1bd344b38a4df6d7c70","observation_id":"12a93edd-70e5-43dc-8cf6-43089413df79","resolution":{"observed_at":"2026-08-06T00:24:49.579082Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.01311","last_updated":"2026-08-02T15:27:00Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T18:32:50.284815Z","submitted_at":"2026-08-02T15:27:00Z","title":"RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":3,"verified_fuzzy":22},"total_outbound_references":49},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2608.01311."}