{"as_of":"2026-08-18T22:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12eefa6b53873e9ca1c8ae3ecbe7c9f0073ff66d0c46980ee09066fa5a682a7c","coverage":[{"denominator":89,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":89,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T16:16:29.497121Z","state":"measured"},{"denominator":89,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":89,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2512.14177/citation-record","integrity":"/paper/2512.14177/integrity","json":"/paper/2512.14177/citation-record.json","paper":"/paper/2512.14177"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.05980","last_updated":"2025-03-07T23:25:19Z","snapshot_observed_at":"2026-08-16T12:52:01.751556Z","submitted_at":"2025-03-07T23:25:19Z","title":"SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.05980","snapshot_observed_at":"2026-08-03T16:16:21.627960Z","title":"Sindex: Semantic inconsistency index for hallucination detection in llms.arXiv preprint arXiv:2503.05980, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:21.627960Z"},"links":{"cited_paper":"/paper/2503.05980","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:1c2e8aaa2d2e4da247019a60c4af00f79fe506178e5b3ce8909f9a6b5774f15e","observation_id":"b0c9700c-a4ad-406e-936b-e89049b8bc40","resolution":{"observed_at":"2026-08-03T16:16:21.627960Z","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":"2026-08-03T16:16:21.712168Z","title":"Rajendra Acharya, Vladimir Makarenkov, and Saeid Nahavandi","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:21.712168Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:dbce3a47c3828f5ffa7bed16faacc640bad4d5831becdb81874d58b50e72752c","observation_id":"b7eeed88-6ce6-442c-9d88-98573f2fc07f","resolution":{"observed_at":"2026-08-03T16:16:21.712168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15176","last_updated":"2026-04-20T11:16:26Z","snapshot_observed_at":"2026-08-13T12:58:31.150566Z","submitted_at":"2024-12-19T18:51:06Z","title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15176","snapshot_observed_at":"2026-08-03T16:16:21.834585Z","title":"Rethinking uncertainty estimation in natural language generation.arXiv preprint arXiv:2412.15176, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:21.834585Z"},"links":{"cited_paper":"/paper/2412.15176","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:eb89d05d4aaebf4facf1f70fba3aa5a3946fcb391310d02a255c215d9a5ca12b","observation_id":"54534581-3340-4cac-85b4-0f8f96c6f0c1","resolution":{"observed_at":"2026-08-03T16:16:21.834585Z","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":"2026-08-03T16:16:21.948270Z","title":"The internal state of an LLM knows when it’s lying","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:21.948270Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:d4e3ec31f7236bb86e922d665868867d2bd6fd3fc0ded9e3891575d204932d56","observation_id":"5e1098a3-0757-42e2-8c2d-d2f4af67b312","resolution":{"observed_at":"2026-08-03T16:16:21.948270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-08-14T04:17:22.593941Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-03T16:16:22.018847Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.018847Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:883a2f6c5b518f95140c7c047a206ea67a9386835071cbca513d2c575f086e82","observation_id":"e353a58c-9b92-4bdf-b20e-e531ea7aea91","resolution":{"observed_at":"2026-08-03T16:16:22.018847Z","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":"2026-08-03T16:16:22.108616Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.108616Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:5d4e137cd55553ccac6b43c2bfe3bbb33b295ac6abc98df11c8f9e48dc8743c3","observation_id":"e8a2b74a-4f0a-4e5b-abaa-f0def469e2b5","resolution":{"observed_at":"2026-08-03T16:16:22.108616Z","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":"2026-08-03T16:16:22.174132Z","title":"Post-hoc probabilistic vision-language models.arXiv preprint arXiv:2412.06014, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.174132Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:f37a9bde62457349bb332385619ad062479922a8aa5d0c0a4f5ce9656a0560a4","observation_id":"360158e6-52b8-4f05-926a-e6555a3e06b9","resolution":{"observed_at":"2026-08-03T16:16:22.174132Z","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":"2026-08-03T16:16:22.268046Z","title":"Hallucination detec- tion in LLMs using spectral features of attention maps","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.268046Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:6e0a7f6e1389141c7b7875a64e1d18231f1884208b7464ea20a734e58d977628","observation_id":"3826f353-3e14-4fe6-b3f0-aac1249beaaa","resolution":{"observed_at":"2026-08-03T16:16:22.268046Z","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":"2026-08-03T16:16:22.367375Z","title":"Weight uncertainty in neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.367375Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:d5b7f822cea47f9e711050313e1d1fc01bdfc9602a14132a0c6e59aa41e8f32c","observation_id":"72d189c4-10b0-44e7-a32f-948226217121","resolution":{"observed_at":"2026-08-03T16:16:22.367375Z","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":"2026-08-03T16:16:22.470226Z","title":"Popqa: A ques- tion answering benchmark for evaluating the factual consis- tency of language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.470226Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:91e4b5c2e978d7b7eb8732fe62d94781cde43ce44977fe0bb96061a091edf2ca","observation_id":"a10a3650-57d0-4a0b-9061-92c48c7d848e","resolution":{"observed_at":"2026-08-03T16:16:22.470226Z","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":"2026-08-03T16:16:22.544122Z","title":"INSIDE: LLMs’ internal states retain the power of hallucination detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.544122Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:e7ae7e546ea2dd79f795af5f772ddb9059eb36f0c37a8a766819a0f113aad65b","observation_id":"ec0a24f4-68de-4526-9cd4-ed24e4b29c7a","resolution":{"observed_at":"2026-08-03T16:16:22.544122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.16820","last_updated":"2025-02-25T05:03:51Z","snapshot_observed_at":"2026-08-17T00:11:53.136536Z","submitted_at":"2025-02-24T04:05:08Z","title":"Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.16820","snapshot_observed_at":"2026-08-03T16:16:22.653456Z","title":"Uncertainty quantification of large language models through multi-dimensional responses","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.653456Z"},"links":{"cited_paper":"/paper/2502.16820","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8e27c03330f375eca593d1e0bb49dc99af85aeeac230eea8df592d8e522f4930","observation_id":"9841133e-9d66-4186-b6f0-dca6ea37f65c","resolution":{"observed_at":"2026-08-03T16:16:22.653456Z","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":"2026-08-03T16:16:22.763353Z","title":"LM vs LM: Detecting factual errors via cross examination","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.763353Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:74f80f10aae55320b81dc22195d4f1f126406f839218a7a0f4d242a00913d187","observation_id":"496cfc6b-5752-4b0e-aa44-627033009b16","resolution":{"observed_at":"2026-08-03T16:16:22.763353Z","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":"2026-08-03T16:16:22.873003Z","title":"I don't know: Explicit modeling of uncertainty with an [idk] token","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.873003Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:0e6543ae9152451a2db26f1d82ff78dd69bf046c027310c72818123b1f01b992","observation_id":"34d8a1a7-63af-4e0d-8b4a-13830c536574","resolution":{"observed_at":"2026-08-03T16:16:22.873003Z","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":"2026-08-03T16:16:22.954205Z","title":"Laplace redux-effortless bayesian deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:22.954205Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:2ce6febb9c7ac75eb99f91467cd647f33e99e2536453269ea5714a7f486c2f80","observation_id":"18478781-4ca3-4296-a5e7-d133536add54","resolution":{"observed_at":"2026-08-03T16:16:22.954205Z","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":"2026-08-03T16:16:23.099747Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.099747Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:61bddad9c4090c7c9fd3409d4827f7079e23fab65b9390732599e272f70f7d78","observation_id":"32281d1d-f100-4f2a-bde9-d446e0f10afd","resolution":{"observed_at":"2026-08-03T16:16:23.099747Z","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":"2026-08-03T16:16:23.218633Z","title":"Eigentrack: Spectral activation feature track- ing for hallucination and out-of-distribution detection in llms and vlms.arXiv preprint arXiv:2509.15735, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.218633Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:94ca0fddee96675264ae3f658d870e1c551d9f5027fbbdf4234674935b007a38","observation_id":"2fe13635-ccf4-4228-af33-0a5a825a5ac9","resolution":{"observed_at":"2026-08-03T16:16:23.218633Z","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":"2026-08-03T16:16:23.294181Z","title":"Detecting hallucinations in large language models using semantic entropy.Nature, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.294181Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ddd70b72f1f03fd5b038526ab0e203f976ded8687609c4d265795128a9c344a1","observation_id":"4201b8c2-b9ae-4542-8831-c2fbde28d222","resolution":{"observed_at":"2026-08-03T16:16:23.294181Z","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":"2026-08-03T16:16:23.370786Z","title":"Tradi: Tracking deep neu- ral network weight distributions","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.370786Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8db09d1f6cba6b55064b1b73f224de351b424a49f168c142523a3a3381343ec4","observation_id":"c6f07be8-92ce-4bc6-95b5-65af9401b1b1","resolution":{"observed_at":"2026-08-03T16:16:23.370786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.18358","last_updated":"2026-04-21T06:00:16Z","snapshot_observed_at":"2026-07-06T22:33:43.999976Z","submitted_at":"2025-10-21T07:26:38Z","title":"Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.18358","snapshot_observed_at":"2026-08-03T16:16:23.484943Z","title":"Ensembling pruned attention heads for uncertainty-aware efficient transformers","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.484943Z"},"links":{"cited_paper":"/paper/2510.18358","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:014261e4ec0bbbcfb3cfeb2e020a33194dbe21c197b9f356ef7e0be1ce6a54f2","observation_id":"af415ce9-f837-410c-8a7d-403b514cadc6","resolution":{"observed_at":"2026-08-03T16:16:23.484943Z","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":"2026-08-03T16:16:23.590183Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.590183Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:9ff061ff0c65a4fc004c154d2634985d2d2c213eaa18ba1a52e7649dfd96a9b8","observation_id":"58e4be37-9001-4c48-b36c-f5e82c989c4a","resolution":{"observed_at":"2026-08-03T16:16:23.590183Z","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":"2026-08-03T16:16:23.671361Z","title":"SPUQ: Perturbation-based uncertainty quantification for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.671361Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ea3f3b8442cf439dfd0905dc86a5fde88bbd70df1ec65af0eef9fb6727e2920d","observation_id":"778e70e9-2606-4e84-a2e5-fde3120c12c4","resolution":{"observed_at":"2026-08-03T16:16:23.671361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22685","last_updated":"2024-10-30T04:41:46Z","snapshot_observed_at":"2026-08-16T13:04:42.179256Z","submitted_at":"2024-10-30T04:41:46Z","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.22685","snapshot_observed_at":"2026-08-03T16:16:23.746023Z","title":"Im- proving uncertainty quantification in large language models via semantic embeddings.arXiv preprint arXiv:2410.22685,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.746023Z"},"links":{"cited_paper":"/paper/2410.22685","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:0644b0118b42ec47ffb3bc5d426fa4733a45a9bac2cc742406ed89b43e51eec6","observation_id":"7f24faa4-1c2d-4d4c-a4d1-fdc7cb4758ce","resolution":{"observed_at":"2026-08-03T16:16:23.746023Z","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":"2026-08-03T16:16:23.856533Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.856533Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:a60ff7da9d5ac37a59dc5e731175bf452c9fd5310e28b72b8e4e5ac0bcc66bad","observation_id":"bdd0c645-3f98-4f67-9d22-93605edf3501","resolution":{"observed_at":"2026-08-03T16:16:23.856533Z","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":"2026-08-03T16:16:23.934381Z","title":"Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:23.934381Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:60830b1abc096c8a330124eea9ea4b658a1e0a82dfaa8f6dbeac556a78702f1c","observation_id":"3bbf4a04-9d7e-4180-8ae4-ed6793ba3494","resolution":{"observed_at":"2026-08-03T16:16:23.934381Z","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":"2026-08-03T16:16:24.016921Z","title":"Vizwiz grand challenge: Answering visual questions from blind people","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.016921Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b76a269542d5e3ea8b459096fddf0d5ac50d542097148c728c4e9f2a32760777","observation_id":"66033dec-0519-49f9-810b-9f0daa93bda6","resolution":{"observed_at":"2026-08-03T16:16:24.016921Z","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":"2026-08-03T16:16:24.130598Z","title":"{DEBERTA}: {DECODING}-{enhanced} {bert} {with} {disentangled} {attention}","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.130598Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8de2bc316afc4c43d00e9c2b2c14bd4d49cb70c6333ad750d964cf53892d0427","observation_id":"709eea2d-18ab-4a36-a35b-82ca92cf8608","resolution":{"observed_at":"2026-08-03T16:16:24.130598Z","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":"2026-08-03T16:16:24.266299Z","title":"A baseline for detect- ing misclassified and out-of-distribution examples in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.266299Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:682e5e9b498553f2a4b984ab21960a58f9d794722a1a6cefb300023285e28809","observation_id":"0973be2d-dedc-4844-837b-5cadc709035e","resolution":{"observed_at":"2026-08-03T16:16:24.266299Z","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":"2026-08-03T16:16:24.360703Z","title":"Prob- abilistic backpropagation for scalable learning of bayesian neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.360703Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:e8eb96d0cf3d812eefab82363b382122e1aa4572d0d4954d282dfb1724289622","observation_id":"08f10653-3a82-4b7c-b617-4f9b60ca1876","resolution":{"observed_at":"2026-08-03T16:16:24.360703Z","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":"2026-08-03T16:16:24.511191Z","title":"Imagenette: A smaller subset of 10 eas- ily classified classes from imagenet.https://github","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.511191Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:d33026fd72e7e526de6032a6bafb107cec4b4117ec202d03219086b0adc5c48f","observation_id":"0b2f794b-3c55-4c52-8b8b-181050720ad4","resolution":{"observed_at":"2026-08-03T16:16:24.511191Z","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":"2026-08-03T16:16:24.603545Z","title":"A survey on hallucination in large language models: Principles, tax- onomy, challenges, and open questions.TIS, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.603545Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:3b5c4acc15e025742874335340113c9f766e5ef000025ef5eb0078af68357944","observation_id":"ff395072-fb5d-4cbb-9169-f99c5cfda1ba","resolution":{"observed_at":"2026-08-03T16:16:24.603545Z","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":"2026-08-03T16:16:24.684928Z","title":"The illusion of progress: Re-evaluating hallucination detec- tion in LLMs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.684928Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:cf3d8144e1fae6194b6ba3c6f829bf52b3ebdaed174181deca41f1532104dede","observation_id":"a362761c-b29d-454b-8933-ebf5bcd80a71","resolution":{"observed_at":"2026-08-03T16:16:24.684928Z","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":"2026-08-03T16:16:24.725918Z","title":"Survey of hallucination in natural language generation.CS, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.725918Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:d6e6c63b1490fe53b44684599543c7e29caa882862afb9c6b24b61c7b682dcbf","observation_id":"b112cfd7-1fad-4824-9b68-1cfa7a06d868","resolution":{"observed_at":"2026-08-03T16:16:24.725918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14477","last_updated":"2025-04-22T19:00:41Z","snapshot_observed_at":"2026-08-18T17:01:12.130898Z","submitted_at":"2025-03-18T17:51:04Z","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14477","snapshot_observed_at":"2026-08-03T16:16:24.791454Z","title":"Calibrating verbal uncertainty as a linear feature to reduce hallucinations.arXiv preprint arXiv:2503.14477, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.791454Z"},"links":{"cited_paper":"/paper/2503.14477","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:e00f62720329151423bddd1af3da892cb7272ac5b862264a7e7210586fbe9837","observation_id":"893f21b0-b576-46a0-9219-dd3775a00322","resolution":{"observed_at":"2026-08-03T16:16:24.791454Z","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":"2026-08-03T16:16:24.877745Z","title":"Cleanse: Uncertainty estima- tion approach using clustering-based semantic consistency in LLMs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.877745Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b79cd21fb6cbdb75b5e5b48bc1348ff9f77afcda5a951488986c48c69682d9e8","observation_id":"8a8e8ea9-edb5-4f9c-93d2-7067cc6f88d4","resolution":{"observed_at":"2026-08-03T16:16:24.877745Z","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":"2026-08-03T16:16:24.972611Z","title":"Weld, and Luke Zettle- moyer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:24.972611Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:2406714f8d99cfa8d6bb310b9cc31bc775da91ce72b5e078442f2c8c9a211303","observation_id":"49e8be7f-7c10-462a-8c6a-93e93d236c27","resolution":{"observed_at":"2026-08-03T16:16:24.972611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05221","last_updated":"2022-11-21T16:38:35Z","snapshot_observed_at":"2026-08-14T05:42:29.067319Z","submitted_at":"2022-07-11T22:59:39Z","title":"Language Models (Mostly) Know What They Know","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05221","snapshot_observed_at":"2026-08-03T16:16:25.063991Z","title":"Language models (mostly) know what they know.arXiv preprint arXiv:2207.05221, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.063991Z"},"links":{"cited_paper":"/paper/2207.05221","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:5fff200c7a25df5b5c8961682c911911a6b7006b192085903793521f215a1253","observation_id":"b533b47d-7096-4cf7-85a9-c5820250a364","resolution":{"observed_at":"2026-08-03T16:16:25.063991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15927","last_updated":"2024-06-22T19:46:06Z","snapshot_observed_at":"2026-07-30T04:59:24.269176Z","submitted_at":"2024-06-22T19:46:06Z","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15927","snapshot_observed_at":"2026-08-03T16:16:25.158930Z","title":"Semantic entropy probes: Robust and cheap hallucination detection in llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.158930Z"},"links":{"cited_paper":"/paper/2406.15927","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:67138832be0df6f4957b1e7122fb582b8080d66e2ebd64e573f9a7fa1fd47996","observation_id":"d5c87d45-0a8b-4241-858b-dc75fff2538e","resolution":{"observed_at":"2026-08-03T16:16:25.158930Z","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":"2026-08-03T16:16:25.254217Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.254217Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:4335b00e6154b83d32a4cf98306117d06b6841effd51cbf70c819416797dc0c6","observation_id":"2fff7be3-2778-48ff-98f7-cc4231af66a3","resolution":{"observed_at":"2026-08-03T16:16:25.254217Z","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":"2026-08-03T16:16:25.376625Z","title":"Semantic uncertainty: Linguistic invariances for uncertainty estima- tion in natural language generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.376625Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:59c9bc2b8b1b5b5f30d7ec09df3d2ca0a27cea1a03d320de79f056090ed386b0","observation_id":"94e5ff29-3d83-4604-a4b7-090ce2ca452c","resolution":{"observed_at":"2026-08-03T16:16:25.376625Z","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":"2026-08-03T16:16:25.441914Z","title":"Semantic uncertainty: Linguistic invariances for uncertainty estima- tion in natural language generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.441914Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:d583420cf225830f9a676424f1ff2a95bfa1c5ccb49a91f95e91bb6c31531a2d","observation_id":"71cae03a-d998-4c63-8122-a99d077ccc23","resolution":{"observed_at":"2026-08-03T16:16:25.441914Z","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":"2026-08-03T16:16:25.527448Z","title":"Simple and scalable predictive uncertainty esti- mation using deep ensembles","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.527448Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:e1f88f0f0f061e51d99401d32b294fa6bd2fef4eac36b4df7bcbd9208240ecf0","observation_id":"a365ed00-bd3f-4b71-8a42-65bd45e1e022","resolution":{"observed_at":"2026-08-03T16:16:25.527448Z","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":"2026-08-03T16:16:25.628972Z","title":"Uncertainty quantification for multimodal large language models with coherence-adjusted semantic volume, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.628972Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:1de6095b7d89b04ee52eb808df8c94dcb7c65c2069a9bc6f539c1cf3c2031a76","observation_id":"d10e84d0-2e0c-4047-9489-02ce87219560","resolution":{"observed_at":"2026-08-03T16:16:25.628972Z","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":"2026-08-03T16:16:25.721726Z","title":"A dataset of clinically generated visual questions and answers about radiology images.Scientific data, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.721726Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:2b58217d886cc82ec40fdcaa07d819a50481f480dac319032e3112edf8a2ce52","observation_id":"028908eb-6941-4e8f-8842-fc3aec64fe60","resolution":{"observed_at":"2026-08-03T16:16:25.721726Z","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":"2026-08-03T16:16:25.811727Z","title":"What matters when building vision-language models? InNeurIPS, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.811727Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:94dcdc1634151ba1bcb01cde146c0a7ec1ffbc4c2ddfef287eba54fcb513a383","observation_id":"2f62abd4-107f-4c9a-8a0c-d5a0abbcc252","resolution":{"observed_at":"2026-08-03T16:16:25.811727Z","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":"2026-08-03T16:16:25.903527Z","title":"Packed-ensembles for efficient uncertainty estima- tion.arXiv preprint arXiv:2210.09184, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.903527Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:f4d67615643649098d700a330e9c02033bc97407935f4dd51eb94922f1048962","observation_id":"46a5c1ee-de64-401a-b0f7-82156e0698e5","resolution":{"observed_at":"2026-08-03T16:16:25.903527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08287","last_updated":"2023-10-12T12:45:13Z","snapshot_observed_at":"2026-08-16T14:52:43.246899Z","submitted_at":"2023-10-12T12:45:13Z","title":"A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08287","snapshot_observed_at":"2026-08-03T16:16:25.979639Z","title":"A symmetry-aware exploration of bayesian neural network posteriors.arXiv preprint arXiv:2310.08287, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:25.979639Z"},"links":{"cited_paper":"/paper/2310.08287","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:00325ab85363c17e52dcfbf483ef6dd10c8ff9d6ca40a308f13f22080190e958","observation_id":"dcc5ceb8-191b-404b-b3b1-49c3a10802f8","resolution":{"observed_at":"2026-08-03T16:16:25.979639Z","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":"2026-08-03T16:16:26.111409Z","title":"Efficient latent semantic clustering for scaling test-time computation of llms, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.111409Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:f91db71818d2a564e4eb8ad26e2df2fbd4d6b4fd863695e74211b48add294001","observation_id":"dce41224-c056-406f-8aa3-15998ab2ceeb","resolution":{"observed_at":"2026-08-03T16:16:26.111409Z","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":"2026-08-03T16:16:26.198286Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.198286Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:75843d6bf1ffb1966f92444ab1012f6941ff585453785776a79f554fb4fe0867","observation_id":"7b1f80fe-c4de-4a15-86d5-a633cdf78047","resolution":{"observed_at":"2026-08-03T16:16:26.198286Z","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":"2026-08-03T16:16:26.297311Z","title":"Inference-time intervention: Elic- iting truthful answers from a language model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.297311Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b5c8842445849da606148abec480c497298b3ef1eff7865146f9925ebbe54d26","observation_id":"e33e783d-9020-4c85-9ac2-0a350de44272","resolution":{"observed_at":"2026-08-03T16:16:26.297311Z","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":"2026-08-03T16:16:26.355177Z","title":"Adversarial vqa: A new benchmark for evaluating the robustness of vqa models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.355177Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:17d94cbe36609795ee753ef7bb675981c6d497d3b8c1185c2d002f7f13027f0b","observation_id":"321f23f8-ea24-4898-9fd5-770fe2629d51","resolution":{"observed_at":"2026-08-03T16:16:26.355177Z","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":"2026-08-03T16:16:26.466825Z","title":"Seman- tic volume: Quantifying and detecting both external and in- ternal uncertainty in llms.arXiv preprint arXiv:2502.21239,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.466825Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:9bbe5ad0f96c1b20b55f6f9263e0e348f2488afc0c84852a8765ffad45110d05","observation_id":"e5a463f9-663b-4e53-804f-85fbe9d05c42","resolution":{"observed_at":"2026-08-03T16:16:26.466825Z","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":"2026-08-03T16:16:26.589802Z","title":"Teaching models to express their uncertainty in words.TMLR, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.589802Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:bc08289d7de11fbefa0f7d3fd153772f79f39b264531b7b885d2cf7df4e9979b","observation_id":"9632db36-4977-47f5-bb89-87b0cf58e120","resolution":{"observed_at":"2026-08-03T16:16:26.589802Z","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":"2026-08-03T16:16:26.653848Z","title":"Generat- ing with confidence: Uncertainty quantification for black- box large language models.TMLR, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.653848Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:87981753b22604074cc65429237313b3a58ab984c54612e446e505988d17b3f4","observation_id":"31e376ff-b879-4141-b48d-74a7331659b9","resolution":{"observed_at":"2026-08-03T16:16:26.653848Z","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":"2026-08-03T16:16:26.712358Z","title":"Improved baselines with visual instruction tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.712358Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b0b946b81feca93eda461a0d727087a054261768841490285203574c38d31277","observation_id":"cd88ef64-63b1-46ba-b151-0334e0ba6af1","resolution":{"observed_at":"2026-08-03T16:16:26.712358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00253","last_updated":"2024-05-06T01:10:01Z","snapshot_observed_at":"2026-08-17T09:37:14.144521Z","submitted_at":"2024-02-01T00:33:21Z","title":"A Survey on Hallucination in Large Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00253","snapshot_observed_at":"2026-08-03T16:16:26.799581Z","title":"A survey on hallucination in large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.799581Z"},"links":{"cited_paper":"/paper/2402.00253","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:9784281ea62d93003f4ec69a263cd1c62b7dfcc0f827624e1d0e5cf8f3d1e02b","observation_id":"a4dcbfc0-3deb-4b35-a28f-7cc2ba78b289","resolution":{"observed_at":"2026-08-03T16:16:26.799581Z","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":"2026-08-03T16:16:26.896036Z","title":"Probable networks and plausible predictions-a review of practical bayesian methods for su- pervised neural networks.Network: computation in neural systems, 1995","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.896036Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:15007fe7ee67444982b6d255c29523b8f37844d1ebc2b1fd05eb74a133cdbffd","observation_id":"0695e636-66cf-4151-b85e-eeef8b10aaec","resolution":{"observed_at":"2026-08-03T16:16:26.896036Z","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":"2026-08-03T16:16:26.954293Z","title":"CalTech, 1992","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:26.954293Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:67076bf8865ad1a875910c69058d5a48e160576cebb25d7d0b8afb0a46c91648","observation_id":"40b9759f-93f6-42e2-b134-11600927c376","resolution":{"observed_at":"2026-08-03T16:16:26.954293Z","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":"2026-08-03T16:16:27.041521Z","title":"A simple baseline for bayesian uncertainty in deep learning.NeurIPS, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.041521Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:fc2c2b0b89cb2d96fac18ca0a8258172be23670e2cf5c707a35b3240638bfc88","observation_id":"91fb43e0-74fa-40e9-ac44-0eecff6a719d","resolution":{"observed_at":"2026-08-03T16:16:27.041521Z","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":"2026-08-03T16:16:27.129117Z","title":"Uncertainty estimation in autoregressive structured prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.129117Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:0792f1ec2f34a1225381f246d07b669a3a45775e4847d1610258567d36be827b","observation_id":"4382f77e-ae6e-4b91-8c4f-cababc934955","resolution":{"observed_at":"2026-08-03T16:16:27.129117Z","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":"2026-08-03T16:16:27.196512Z","title":"Self- CheckGPT: Zero-resource black-box hallucination detection for generative large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.196512Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:23c68c85d05f669afe6e309f1c31c3880e75fb11b9c84a5022cf58b7a2d20ad1","observation_id":"9ffcc773-dfa3-4108-9c84-d36931c65cfd","resolution":{"observed_at":"2026-08-03T16:16:27.196512Z","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":"2026-08-03T16:16:27.284839Z","title":"Ok-vqa: A visual question answering benchmark requiring external knowledge","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.284839Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:16b280e6cb6d5dd4228a48eded8b7575261d689d3bda72195fdf9f64aee2e663","observation_id":"4de0ca17-7e48-4d37-8df2-c25280477c31","resolution":{"observed_at":"2026-08-03T16:16:27.284839Z","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":"2026-08-03T16:16:27.409384Z","title":"MIT press, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.409384Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ac65579edeb0006997e6f62d767841a82d5ab410f8dc22df704164d6f8bd9bb9","observation_id":"eabc67e2-1dda-43e4-8fa3-7c63e880f529","resolution":{"observed_at":"2026-08-03T16:16:27.409384Z","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":"2026-08-03T16:16:27.571589Z","title":"Correcting length bias in neural machine translation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.571589Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:de8ed66d4d9ebe8db0290aa6da50176d570b38187ade56347351e34cebbc990d","observation_id":"fc0f1240-f4f0-438b-9291-5bd9ba2498df","resolution":{"observed_at":"2026-08-03T16:16:27.571589Z","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":"2026-08-03T16:16:27.702032Z","title":"Springer Science & Business Media, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.702032Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ba476560b9a06fed848119a79056fb4b835a017e745cc8598da872d17abd5a70","observation_id":"0d888058-b429-4096-8c84-6c3676562a34","resolution":{"observed_at":"2026-08-03T16:16:27.702032Z","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":"2026-08-03T16:16:27.823732Z","title":"Be- yond semantic entropy: Boosting LLM uncertainty quantifi- cation with pairwise semantic similarity","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.823732Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:61431e949d92f0081c3026969dfa95023011fd35da04c5513c949c44a3c188df","observation_id":"992f638b-922b-41ea-9c64-0e0ee937a1b0","resolution":{"observed_at":"2026-08-03T16:16:27.823732Z","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":"2026-08-03T16:16:27.950615Z","title":"Kernel language entropy: Fine-grained uncer- tainty quantification for llms from semantic similarities","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:27.950615Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:040ba49ab84cbf21eabd44db1e2e34b1d2652aabd38409aa1f9be7f1937bac9f","observation_id":"03959f3f-2bf3-42d0-a2cf-dc7a67fae6e0","resolution":{"observed_at":"2026-08-03T16:16:27.950615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.13131","last_updated":"2025-06-16T06:37:18Z","snapshot_observed_at":"2026-08-11T23:48:15.512738Z","submitted_at":"2025-06-16T06:37:18Z","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.13131","snapshot_observed_at":"2026-08-03T16:16:28.071045Z","title":"Alphaevolve: A coding agent for scientific and algorithmic discovery.arXiv preprint arXiv:2506.13131,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.071045Z"},"links":{"cited_paper":"/paper/2506.13131","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:28b2b9a12af1391e49a6a32c839f717967bbebaf357b0f58027f64bd4454b629","observation_id":"b0bf1ece-995b-4979-a518-174ea8a1bb72","resolution":{"observed_at":"2026-08-03T16:16:28.071045Z","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":"2026-08-03T16:16:28.148467Z","title":"LLMs know more than they show: On the intrinsic representation of LLM hallucinations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.148467Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:52956db8e67c7eb4b28aa71d0b5593eeec1f61dd0c455e99d4ada66b3e0add7c","observation_id":"30ae742d-a613-4cf1-baec-ed5ccf662896","resolution":{"observed_at":"2026-08-03T16:16:28.148467Z","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":"2026-08-03T16:16:28.185630Z","title":"Semantic density: Uncer- tainty quantification for large language models through con- fidence measurement in semantic space","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.185630Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:fa5da2b66f4fec7e877873c7c688075e40a3d803aed487d2f4661157719b7988","observation_id":"b51f9ad9-3528-44cd-9740-20b265342546","resolution":{"observed_at":"2026-08-03T16:16:28.185630Z","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":"2026-08-03T16:16:28.263911Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.263911Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:9cc775950ee33475eaf849556e99a19d16d06100da99d83de9100e83d231f978","observation_id":"bdd12321-995b-4516-b848-d3ccc21007da","resolution":{"observed_at":"2026-08-03T16:16:28.263911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-03T16:16:28.321101Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks.arXiv preprint arXiv:1908.10084, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.321101Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8c50739659b7be1cb6117659902f2896dc2af7511b078762c5756041bbd6ddab","observation_id":"7e4051b0-0ce9-4896-baa9-c0bf61a6ce34","resolution":{"observed_at":"2026-08-03T16:16:28.321101Z","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":"2026-08-03T16:16:28.377108Z","title":"Out- of-distribution detection and selective generation for condi- tional language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.377108Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:391776714bb8ac1f4fe8e48ae6d4f80ef05390ed0e0e9ff5349eaa30d3a5e7fc","observation_id":"0ba794d8-1d7c-488f-81df-397d15ade06b","resolution":{"observed_at":"2026-08-03T16:16:28.377108Z","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":"2026-08-03T16:16:28.459485Z","title":"A scal- able laplace approximation for neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.459485Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:00361a642d62084946de7a8522afd5c3e57ba25ef597e3055b56c0c1706bf77d","observation_id":"2260ddcf-1c0c-419a-8a02-4dc9baeac514","resolution":{"observed_at":"2026-08-03T16:16:28.459485Z","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":"2026-08-03T16:16:28.543535Z","title":"MIT press, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.543535Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:5975d0c1123b7f7b63e422a324dadfd340b62d6a37206abbb00d9223db0e124e","observation_id":"447541a6-007c-479e-9d01-e56c791cc039","resolution":{"observed_at":"2026-08-03T16:16:28.543535Z","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":"2026-08-03T16:16:28.660474Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.660474Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b26e453b5e04b4e95e84144fe6bd8afb708f123d01e99bf40f2e6bad46540569","observation_id":"826793cd-52f3-40f5-bc27-e36029b7823e","resolution":{"observed_at":"2026-08-03T16:16:28.660474Z","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":"2026-08-03T16:16:28.778702Z","title":"Layer by layer: Uncovering hidden representations in lan- guage models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.778702Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:21d4179e60b9bf7e72f4093115b4dbd978dff70befc10e1838fa80a91bf61218","observation_id":"3087c9ff-47ee-4c9b-9d25-3088d998fe25","resolution":{"observed_at":"2026-08-03T16:16:28.778702Z","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":"2026-08-03T16:16:28.890011Z","title":"Llm-check: Investigating detection of hallucinations in large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.890011Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8b375e984b0d83a38a2bc2cfc7b225c5fef0fb3f78dc44edf3378c6025ee8c88","observation_id":"d7f626fc-e4cf-4264-89ff-9e1a5c29a575","resolution":{"observed_at":"2026-08-03T16:16:28.890011Z","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":"2026-08-03T16:16:28.921878Z","title":"Gemini 1.5: Unlocking multimodal under- standing across millions of tokens of context, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:28.921878Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ddf9bee69ea2d66fb3bf001f9d2ee841dd2123c34b88eb7c1e03239f09f3b79d","observation_id":"f6200473-a878-4e94-98fe-58b882e82127","resolution":{"observed_at":"2026-08-03T16:16:28.921878Z","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":"2026-08-03T16:16:29.000472Z","title":"The llama 3 herd of models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.000472Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8656abc079cb0ac5c62db7c9327e69f30723f50d9a1f84b80677352c72e02da0","observation_id":"1fc7176a-5d23-409d-92ed-f55af11ab4b1","resolution":{"observed_at":"2026-08-03T16:16:29.000472Z","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":"2026-08-03T16:16:29.057172Z","title":"Gpt-4 technical report, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.057172Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:c9f85a7261174088b8001d0933ef8964d0a51b47f30eda4142fca296da38e2cb","observation_id":"2dc8aef9-f3f7-4613-a524-a03edd9dd65a","resolution":{"observed_at":"2026-08-03T16:16:29.057172Z","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":"2026-08-03T16:16:29.114528Z","title":"gpt-oss-120b and gpt-oss-20b model card,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.114528Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:e2e1156877908efedcb131fc7f967e9085f94dcf0d65f1ff4254963f40bb288e","observation_id":"cd092140-f360-4002-83cf-d1ce772606f3","resolution":{"observed_at":"2026-08-03T16:16:29.114528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.18234","last_updated":"2025-10-21T02:41:44Z","snapshot_observed_at":"2026-08-17T02:37:33.939393Z","submitted_at":"2025-10-21T02:41:44Z","title":"DeepSeek-OCR: Contexts Optical Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.18234","snapshot_observed_at":"2026-08-03T16:16:29.169533Z","title":"Deepseek- ocr: Contexts optical compression.arXiv preprint arXiv:2510.18234, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.169533Z"},"links":{"cited_paper":"/paper/2510.18234","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:6bfc04121aa0f9b733fe2df3877433a26afb98a687bfbd48c3abdf9893cf5f9f","observation_id":"e475cadb-9789-4dea-befd-89aa333b84c5","resolution":{"observed_at":"2026-08-03T16:16:29.169533Z","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":"2026-08-03T16:16:29.228439Z","title":"Batchensemble: an alternative approach to efficient ensemble and lifelong learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.228439Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:29cee00a2edee5b1208eef3bc8d2ad213694b211008f8b84f685363a7ef79a24","observation_id":"266b14a9-d601-48cb-8d8e-172d50bca622","resolution":{"observed_at":"2026-08-03T16:16:29.228439Z","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":"2026-08-03T16:16:29.278432Z","title":"Gaussian processes for machine learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.278432Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:444fa05b42ae5b37585776c7c7067ef6af0acadb6bafe0fcb6df52105c31b175","observation_id":"36cf4c3e-e28f-4906-a2e1-bde6fff37870","resolution":{"observed_at":"2026-08-03T16:16:29.278432Z","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":"2026-08-03T16:16:29.331733Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.331733Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:7dcf6fb876770350a3a9ce8929f3ed19f8cb418fed90f2ddc019906e98a45849","observation_id":"0ae43fc6-b5c2-47fc-8660-7071f8d2c299","resolution":{"observed_at":"2026-08-03T16:16:29.331733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.11737","last_updated":"2026-04-11T18:08:02Z","snapshot_observed_at":"2026-08-17T03:22:33.652659Z","submitted_at":"2025-05-16T22:47:32Z","title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.11737","snapshot_observed_at":"2026-08-03T16:16:29.383723Z","title":"Token-level uncertainty estima- tion for large language model reasoning.arXiv preprint arXiv:2505.11737, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.383723Z"},"links":{"cited_paper":"/paper/2505.11737","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:ff459b2f32e87fc6ebe80dd194a1234b51080068c8c68204bdf7fe4d121a5410","observation_id":"f7ef378b-40fd-4f59-a19e-25d06754ba4c","resolution":{"observed_at":"2026-08-03T16:16:29.383723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.03705","last_updated":"2021-05-08T14:07:58Z","snapshot_observed_at":"2026-08-16T18:26:09.925983Z","submitted_at":"2021-05-08T14:07:58Z","title":"Understanding Neural Networks with Logarithm Determinant Entropy Estimator","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.03705","snapshot_observed_at":"2026-08-03T16:16:29.437805Z","title":"Understanding neural net- works with logarithm determinant entropy estimator.arXiv preprint arXiv:2105.03705, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.437805Z"},"links":{"cited_paper":"/paper/2105.03705","citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:8e3f69c202d10cd44763e0a03a9cfbc4f0d7a11b4f6f454eb370a51874c5e9ca","observation_id":"fd845a0b-2a58-4f19-91dc-d4c24bb261a9","resolution":{"observed_at":"2026-08-03T16:16:29.437805Z","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":"2026-08-03T16:16:29.497121Z","title":"Understanding neural net- works with logarithm determinant entropy estimator.Neuro- computing, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-03T16:16:29.497121Z"},"links":{"citing_paper":"/paper/2512.14177"},"observation_digest":"sha256:b040ed5df93e1fc8b445ef102615b8eb385f8597ab5336703dbae739577fb692","observation_id":"8c7e85e9-dcfe-4c81-8964-16adf6bab588","resolution":{"observed_at":"2026-08-03T16:16:29.497121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.14177","last_updated":"2026-06-03T14:26:01Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T13:14:13.252378Z","submitted_at":"2025-12-16T08:15:24Z","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes"},"reference_resolution":{"displayed":89,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":89,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":89},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 89 of 89 outbound references and 0 inbound Pith citation observations for arXiv:2512.14177."}