{"as_of":"2026-08-07T22:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1e0a51a2b0c7c77a25d8e10d8ec4a2ce3cc996394b3bda3d44a6e137a92dc338","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:04:16.496141Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.16951/citation-record","integrity":"/paper/2507.16951/integrity","json":"/paper/2507.16951/citation-record.json","paper":"/paper/2507.16951"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:04:18.799601Z","title":"How does bert answer questions? a layer-wise analysis of transformer representations,","venue":null,"work_id":"17a46724-e8ff-43b0-a260-eae1dcc8e66a","year":2019},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:13.946250Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:fc35e0db51adaa20c400b6e1bb8b70af3b65396bddb0670cfe23d3e03b57e0c1","observation_id":"4fe5b5eb-5043-4b83-a3c5-6e069ac6392e","resolution":{"observed_at":"2026-08-06T15:04:18.923089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05029","last_updated":"2017-07-28T15:28:01Z","snapshot_observed_at":"2026-08-07T15:31:36.957938Z","submitted_at":"2016-06-16T02:20:04Z","title":"No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering \"Simple\" Questions)","version":2},"cited_work":{"arxiv_id":"1606.05029","doi":null,"metadata_source":"pith","pith_arxiv_id":"1606.05029","snapshot_observed_at":"2026-08-06T15:04:17.308289Z","title":"No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering \"Simple\" Questions)","venue":"cs.CL","work_id":"fdc32b25-d5a4-4d14-aea9-7f1f31fc39b5","year":2016},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:13.990540Z"},"links":{"cited_paper":"/paper/1606.05029","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:8dda71c7bb7dae6d1c1682ee1b0306a2ea0fb460de489d3bc018c9c53793e498","observation_id":"218392a0-71fd-4573-b069-1420b9865902","resolution":{"observed_at":"2026-08-06T15:04:17.363984Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19732","last_updated":"2024-12-20T16:19:17Z","snapshot_observed_at":"2026-08-03T16:04:58.991344Z","submitted_at":"2024-10-25T17:59:09Z","title":"Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19732","snapshot_observed_at":"2026-08-06T15:04:14.065917Z","title":"Rethinking visual dependency in long-context reasoning for large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.065917Z"},"links":{"cited_paper":"/paper/2410.19732","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:647eadb1c0e642c7890109c62d7de67afa42fa0cef024d0c26fa20833efa21df","observation_id":"f118e76e-284f-4179-b4f3-958cc2398eb5","resolution":{"observed_at":"2026-08-06T15:04:14.065917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.12840","last_updated":"2019-10-28T17:51:44Z","snapshot_observed_at":"2026-08-05T11:47:26.510410Z","submitted_at":"2019-10-28T17:51:44Z","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.12840","snapshot_observed_at":"2026-08-06T15:04:14.168505Z","title":"Evaluating the factual consistency of abstractive text summarization,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.168505Z"},"links":{"cited_paper":"/paper/1910.12840","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:4903f5d6b34b29a82c6a682be7dfbe0414ade4e3f1be340b6e7a76ce490d26fd","observation_id":"c18795c3-a97b-48cb-af59-deb021677d85","resolution":{"observed_at":"2026-08-06T15:04:14.168505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06044","last_updated":"2019-09-27T00:43:28Z","snapshot_observed_at":"2026-07-06T08:21:25.975119Z","submitted_at":"2019-09-13T05:50:50Z","title":"Say What I Want: Towards the Dark Side of Neural Dialogue Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06044","snapshot_observed_at":"2026-08-06T15:04:14.236797Z","title":"Say what i want: Towards the dark side of neural dialogue models,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.236797Z"},"links":{"cited_paper":"/paper/1909.06044","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:cf2da028537580bd8e677500b0d48b6b80d1d044b5f6c17f40c7e3c87fd02793","observation_id":"da21dd94-cc70-447c-a26d-72e934f8ef9e","resolution":{"observed_at":"2026-08-06T15:04:14.236797Z","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":"2026-08-06T15:04:18.626010Z","title":"Weak to strong generalization for large language models with multi-capabilities,","venue":null,"work_id":"e58e094a-8c73-4bc9-be8a-de5c22153f8a","year":2025},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.303639Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:49b39f888ae5fb39fc95be72e480b3faf6e963b53001885d1e94ca859e3708cf","observation_id":"d1067c27-58e1-45c3-ae82-4e6950686eb1","resolution":{"observed_at":"2026-08-06T15:04:18.703532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16897","last_updated":"2024-05-25T11:48:50Z","snapshot_observed_at":"2026-08-07T15:31:38.524463Z","submitted_at":"2024-05-25T11:48:50Z","title":"InstructPatentGPT: Training patent language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":"2406.16897","doi":"10.48550/arxiv.2406.16897","metadata_source":"pith","pith_arxiv_id":"2406.16897","snapshot_observed_at":"2026-08-06T18:16:30.548575Z","title":"InstructPatentGPT: Training patent language models to follow instructions with human feedback","venue":"cs.CL","work_id":"4a98e248-8c11-4764-85df-b4825d04d75e","year":2024},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.384190Z"},"links":{"cited_paper":"/paper/2406.16897","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:2207e3b40e24c4f14bb49ef4667abcecddef56f02fea7b6881c77560213459b3","observation_id":"12ac24b9-22e2-45c1-8482-4888fcbc8259","resolution":{"observed_at":"2026-08-06T15:04:16.765780Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15451","last_updated":"2023-11-26T22:47:54Z","snapshot_observed_at":"2026-07-06T16:52:49.773956Z","submitted_at":"2023-11-26T22:47:54Z","title":"Uncertainty-aware Language Modeling for Selective Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15451","snapshot_observed_at":"2026-08-06T15:04:14.470908Z","title":"Uncertainty-aware language modeling for selective question answering,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.470908Z"},"links":{"cited_paper":"/paper/2311.15451","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:26a4c7fcfa477d2eecaee87461cd29ecb29b2a183d6ef798908d63b34574ec47","observation_id":"d1630db8-117e-4d4c-b8d5-b3c9c5fd87b1","resolution":{"observed_at":"2026-08-06T15:04:14.470908Z","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":"2026-08-06T15:04:14.566411Z","title":"Claret: Pre-training a correlation-aware context-to-event transformer for event-centric gener- ation and classification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.566411Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:a140baee8a15fee496293d6d2b0a4f5394440ea21208e23ea4d8a66fdcbde7bb","observation_id":"aa476e44-3da1-49a2-866c-63a9087e7582","resolution":{"observed_at":"2026-08-06T15:04:14.566411Z","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":"2026-08-06T15:04:18.491244Z","title":"Question generation for question answering,","venue":null,"work_id":"73e4c6bf-156e-408a-ab4f-71c624a1dbe5","year":2017},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.686126Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:252b102e813527029cd105e7ab7bf8764f7d6e5270559322f6af41e82bc7fd5c","observation_id":"2c7968a7-4573-4648-aae1-d4a28dcbe066","resolution":{"observed_at":"2026-08-06T15:04:18.547930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:04:14.785830Z","title":"Attentional transfer is all you need: Technology-aware layout pattern generation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.785830Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:77c69e4059dc85269ae8fd93c69b9f59882db1391f5ae8072f24d65dfe70ec23","observation_id":"b9325baf-d242-4162-8820-9db0692c6428","resolution":{"observed_at":"2026-08-06T15:04:14.785830Z","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":"2026-08-06T15:04:14.844113Z","title":"BERT: pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.844113Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:416808f89eed50dcbe2035063b05e04062b5d7b4c732c658f5ade86a003e2269","observation_id":"71b974bd-19da-497c-b5a7-fcbc80106830","resolution":{"observed_at":"2026-08-06T15:04:14.844113Z","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":"2026-08-06T15:04:14.964860Z","title":"Eventbert: A pre- trained model for event correlation reasoning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:14.964860Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:ca1b0fc16ceed911e3bf108aad70871152ce39c5e45da111044a4f660906f7dc","observation_id":"c0514d13-8fb8-448f-8bb5-994dffd3c6aa","resolution":{"observed_at":"2026-08-06T15:04:14.964860Z","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":"2026-08-06T15:04:15.060344Z","title":"Modeling event-pair relations in external knowledge graphs for script reasoning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.060344Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:b8f6dcea69bc3d533d67bcba61c0548091d338468e6f01932c48baf53f17669c","observation_id":"0c73497b-a8a7-4388-a530-a3da0091ef7d","resolution":{"observed_at":"2026-08-06T15:04:15.060344Z","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":"2026-08-06T15:04:18.306374Z","title":"Language models with image descriptors are strong few- shot video-language learners,","venue":null,"work_id":"8b9c6d7e-805c-4c40-8c94-4ebc0dbf3819","year":2022},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.148575Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:eb7371d78da88b53c8790ddca20db60ded4f2824471faef82067c0611e7bc8fa","observation_id":"f127bde3-d45c-4d88-805d-8ae8d5d6dc26","resolution":{"observed_at":"2026-08-06T15:04:18.384960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:04:18.155523Z","title":"U-shaped and inverted-u scaling behind emergent abilities of large language models,","venue":null,"work_id":"55b23b89-1aab-4498-94ec-6fa66e0b86e2","year":2025},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.251379Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:dd62b6b9b09c53e3fbdf1a5fe27a6391e726bb19d7ce9624eab49add8b17a157","observation_id":"cc75d803-936d-48a5-8733-a195d176de35","resolution":{"observed_at":"2026-08-06T15:04:18.223850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:04:17.975764Z","title":"Palm: Scaling language modeling with pathways,","venue":null,"work_id":"9d136dc5-2871-4fea-93ef-08c6314e1b9f","year":null},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.340827Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:97d4f07ed176a70ba919fca98078c9ba93c6f1f7e0c4e94581d08d7613239d6a","observation_id":"a4ea7d28-45df-42ed-bdc8-15a5620a6821","resolution":{"observed_at":"2026-08-06T15:04:18.058110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-06T15:04:15.509937Z","title":"Llama 2: Open foundation and fine-tuned chat models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.509937Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:ce3a67183205b05f94db3ae824a78449c96c984ff21678066ad91d8cbb84ffc4","observation_id":"d967bc84-481d-4437-8040-bf113c169971","resolution":{"observed_at":"2026-08-06T15:04:15.509937Z","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":"2026-08-06T15:04:15.609630Z","title":"Visual in-context learning for large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.609630Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:e7da19df2b7081d695258fcfa42cb220499a6713723317a21e19eb9cb3f5fbcd","observation_id":"8d03d3b0-9842-4b9e-bf96-3919a8b6599c","resolution":{"observed_at":"2026-08-06T15:04:15.609630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24787","last_updated":"2025-05-30T16:48:14Z","snapshot_observed_at":"2026-08-07T15:30:21.145991Z","submitted_at":"2025-05-30T16:48:14Z","title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.24787","snapshot_observed_at":"2026-08-06T15:04:15.709414Z","title":"Draw all your imagine: A holistic benchmark and agent framework for complex instruction-based image generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.709414Z"},"links":{"cited_paper":"/paper/2505.24787","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:6c6c003e93cb033efbdf005280842643b0ac23b2bea3385f715ae11e86c9dbe5","observation_id":"5ba1275a-4bbe-4f0b-9b05-f91ff74e114f","resolution":{"observed_at":"2026-08-06T15:04:15.709414Z","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":"2026-08-06T15:04:17.618125Z","title":"Retrieval-augmented generation for knowledge-intensive NLP tasks,","venue":null,"work_id":"1fb67fb4-1e32-48f6-84cd-35cee2cf7e9b","year":2020},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.855654Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:3538f2cc260b49145d7148ad3a526c06fa7b91025b56b43a0cfaddbf95aadb05","observation_id":"23607d79-2794-4266-9747-15b0b07ec2e9","resolution":{"observed_at":"2026-08-06T15:04:17.708290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12701","last_updated":"2024-10-15T14:21:54Z","snapshot_observed_at":"2026-08-04T07:48:34.455699Z","submitted_at":"2024-05-21T11:50:16Z","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","version":3},"cited_work":{"arxiv_id":"2405.12701","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.12701","snapshot_observed_at":"2026-08-06T15:04:17.044229Z","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","venue":"cs.CL","work_id":"a4fda72f-039d-4b26-9c12-0fee91803e5f","year":2024},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:16.102624Z"},"links":{"cited_paper":"/paper/2405.12701","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:cda00ba41a7040576a7ddd1bda87752b1e9c463343add4d19ba34314436b16d9","observation_id":"dd64c302-b50c-49dd-bb0f-bc9759567efb","resolution":{"observed_at":"2026-08-06T15:04:17.107479Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:04:16.236883Z","title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:16.236883Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:72e012ef36c5f8e989dead75460241aab25b58c18e82d256c79090b615af99d1","observation_id":"87821a92-7565-4bc2-bd8b-fc5bee9b0c56","resolution":{"observed_at":"2026-08-06T15:04:16.236883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.07958","last_updated":"2022-05-08T02:43:02Z","snapshot_observed_at":"2026-08-03T16:26:48.747700Z","submitted_at":"2021-09-08T17:15:27Z","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.07958","snapshot_observed_at":"2026-08-06T15:04:16.384046Z","title":"Truthfulqa: Measuring how models mimic human falsehoods,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:16.384046Z"},"links":{"cited_paper":"/paper/2109.07958","citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:737f86b411ce60aa5384c6b32bd9e4893494cf55ce92f8e5914bbbd6abe2cd38","observation_id":"e6c90c6a-48a5-4faa-af03-a1ebbb38680d","resolution":{"observed_at":"2026-08-06T15:04:16.384046Z","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":"2026-08-06T15:04:16.496141Z","title":"Hint-enhanced in-context learning wakes large language models up for knowledge-intensive tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:16.496141Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:b92ac78b836f584ccc28cd2747343dc53b9b2efe61710bf8bbac51e629c45d35","observation_id":"01dd0901-c709-4aa1-bda5-9e17dd7df278","resolution":{"observed_at":"2026-08-06T15:04:16.496141Z","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":"2026-08-06T15:04:17.475781Z","title":"Available: https://proceedings.neurips.cc/paper/2020/ hash/6b493230205f780e1bc26945df7481e5-Abstract.html","venue":null,"work_id":"90155ee7-b079-405e-b155-549f0d1eb6d3","year":2020},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.974553Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:602777099fe82e803043caf57d99431b9f86fb45917de37992e4714f76003cad","observation_id":"604274ff-0252-4456-b471-2d48aaeb6816","resolution":{"observed_at":"2026-08-06T15:04:17.528797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:04:17.787907Z","title":"Available: https://jmlr.org/papers/v24/22-1144.html","venue":null,"work_id":"7f9644cb-ed6f-429c-a866-e405af96eee1","year":null},"citing_paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T15:04:15.438533Z"},"links":{"citing_paper":"/paper/2507.16951"},"observation_digest":"sha256:0a072349d716145573ed5f9855093f43a0e78f5d9d7c42e01f251ce2c2b0e8b2","observation_id":"7ce6e6c7-b03f-4257-a498-aae412ce8b0f","resolution":{"observed_at":"2026-08-06T15:04:17.849906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.16951","last_updated":"2025-07-22T18:44:18Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T15:30:59.778374Z","submitted_at":"2025-07-22T18:44:18Z","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":3,"verified_fuzzy":9},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2507.16951."}