{"as_of":"2026-08-08T11:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b3d20f11fb5aa97e29b3a0d6371e8e9e20010200487d76b1c2d1f99ee4dd2a95","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:23:03.775891Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.24649/citation-record","integrity":"/paper/2505.24649/integrity","json":"/paper/2505.24649/citation-record.json","paper":"/paper/2505.24649"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:08.349577Z","title":"Gpt-4 technical report","venue":null,"work_id":"f1a03c44-097d-4128-9807-59a22a30ab93","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.316425Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:55f1175c73765fc5a10c888621b5226cf595a7e5ab8554110dc43a3cc60b178d","observation_id":"78d66c6f-34a3-4dc1-9881-3168660ddc07","resolution":{"observed_at":"2026-08-07T12:23:08.436436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:08.251162Z","title":"Hierarchi- cal neural story generation","venue":null,"work_id":"e1b957e5-21cc-4191-ac70-cef385817ce4","year":2018},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.382995Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:ce6fce2fb6c375d580c46b9259130c6c2958a7c8d9448de8a7b5d9318db87a1d","observation_id":"f9102589-327c-47d9-a850-b3931664de99","resolution":{"observed_at":"2026-08-07T12:23:08.285236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:08.192462Z","title":"The claude 3 model family: Opus, sonnet, haiku","venue":null,"work_id":"cd787a97-d554-443d-9603-7b4e5b0e1063","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.472955Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:cf8e38c0d6691e65aea51a9666ccef6e6ee7bdab34c6ce6f394e164621f94eb0","observation_id":"8efe8bc5-caa8-4e43-b279-4ff80189248d","resolution":{"observed_at":"2026-08-07T12:23:08.223427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:08.112751Z","title":"Qwen2.5-vl technical report","venue":null,"work_id":"290e62ce-4c55-4154-ae34-b54c592eb498","year":2025},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.567383Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:ea8eceb21dfc2efef8348003f861fe0dfbf37823913fb2b222e6ab3e08d46cea","observation_id":"90fde9d3-4245-4b6b-ba59-b77703582235","resolution":{"observed_at":"2026-08-07T12:23:08.141622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:22:58.669407Z","title":"Lan- guage models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.669407Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:d85042a63780b9c6ff678f63bba6cc040a8c6741814f9f236db44a6f8bae68ea","observation_id":"0e0d600b-1ccb-40ba-ae4d-e83942a0ba6f","resolution":{"observed_at":"2026-08-07T12:22:58.669407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:08.010492Z","title":"Gonzalez, Ion Stoica, and Eric P","venue":null,"work_id":"1fbde2c5-ae2c-423b-92e9-8804b277f310","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.764415Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:b5a3455b3d3c7c9e79e333de77ff63c7e7f999e2421e448693dfc4176eabde3c","observation_id":"41d5ad46-4490-4532-8dd4-7e8308315db7","resolution":{"observed_at":"2026-08-07T12:23:08.066044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.952647Z","title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","venue":null,"work_id":"22a8fc30-b127-4327-b0ca-e781b8f34db1","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.848174Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:700de2fa36d99fba5a964cf942add0db1e0cfe32ece556bee5bb7a9a2db89e27","observation_id":"4b313293-ff57-4ddc-912d-6ba520d634c1","resolution":{"observed_at":"2026-08-07T12:23:07.977554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.845803Z","title":"Density estimation using real NVP","venue":null,"work_id":"d0e85395-3198-4d50-bcc6-543a0f2a483a","year":2017},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:58.957828Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:188343c94996d2e93ef1a638d4a725f064b84aef4c60e6189008500583b88a27","observation_id":"71a3fa60-0f05-444f-a6e8-e3ece5fab6bf","resolution":{"observed_at":"2026-08-07T12:23:07.941117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.727872Z","title":"Vec2face: Unveil hu- man faces from their blackbox features in face recognition","venue":null,"work_id":"6c0171e7-b9ea-494a-ab60-b1cd0ab57fed","year":2020},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.103100Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:0195aecdb7f192b63ac20ccb6ea30413ae35a7dea8e7161a470c95e1d3f4ee0b","observation_id":"cf1efb7f-1117-4998-8d12-dbd837049fe6","resolution":{"observed_at":"2026-08-07T12:23:07.782649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.624720Z","title":"Beam search strate- gies for neural machine translation","venue":null,"work_id":"af098a78-7857-4d36-b24a-5eaf7611db9a","year":2017},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.223318Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:0568d4b905adbdb8dce9d790d69e46709edd6c5ad559d00cde4bd869e9b53c60","observation_id":"ed2eea5c-fcaa-403e-87be-2fd74b3e0882","resolution":{"observed_at":"2026-08-07T12:23:07.683052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.497657Z","title":"Made: Masked autoencoder for distribution es- timation","venue":null,"work_id":"c7ce58d2-5445-4435-b650-c74562848aa3","year":2015},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.437392Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:5b419031ea09770d041dca13ed90980e556b7d10e68b8b71b1822fd2e84cd2e0","observation_id":"e739e130-334b-44d9-8c6a-9cc46d5b566c","resolution":{"observed_at":"2026-08-07T12:23:07.550057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T12:22:59.586587Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.586587Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:1fd1eb0b984587f124a091177467febccec7d07004fab385bf3c7ef827559a16","observation_id":"a7558e35-7802-4d0e-9d23-f338f22c75c5","resolution":{"observed_at":"2026-08-07T12:22:59.586587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1211.3711","last_updated":"2012-11-14T19:25:21Z","snapshot_observed_at":"2026-07-06T02:59:58.238741Z","submitted_at":"2012-11-14T19:25:21Z","title":"Sequence Transduction with Recurrent Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1211.3711","snapshot_observed_at":"2026-08-07T12:22:59.678995Z","title":"Sequence transduction with recurrent neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.678995Z"},"links":{"cited_paper":"/paper/1211.3711","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:553dd8efa839d60aa25281e32545afb7cb351b3535f2c9c1ed4c1e6607247c7e","observation_id":"20ca98c5-18d3-4b6f-ab5e-ece3dc82530b","resolution":{"observed_at":"2026-08-07T12:22:59.678995Z","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":"2026-08-07T12:22:59.732991Z","title":"Detecting and preventing hallucinations in large vision language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.732991Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:13b34a84ee1133df5957a209c1123c7c08bf6b2c6a45220c45bcd5efe53f7cf0","observation_id":"7fda46ec-ae11-4415-b6ab-05e0178fbffa","resolution":{"observed_at":"2026-08-07T12:22:59.732991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T12:22:59.821422Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.821422Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:be0472097a0346fe136635cf791539a64e9fdf0b85195b5c51cee055a20ca46c","observation_id":"5d50fb40-478d-431f-a122-e892edd7a1e5","resolution":{"observed_at":"2026-08-07T12:22:59.821422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.397479Z","title":"The curious case of neural text degeneration","venue":null,"work_id":"ec211aea-94b6-4ae4-8a33-9df8145b31b1","year":null},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.887893Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:6e5aa7ca2fb4e97e5f1ccffa2501b045ed20b62b8713dafd54424f171beb7379","observation_id":"e74f500a-dcd4-446e-b561-aa3798805ef4","resolution":{"observed_at":"2026-08-07T12:23:07.428384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.319072Z","title":"Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation","venue":null,"work_id":"bacd3056-2482-4336-a539-1ce0ef39b493","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:22:59.923497Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:169b137801b00341e5dcb0729aa8ce5a8d582c4ce5312a1321a1c2f28ae02e63","observation_id":"3f95acc4-1124-474d-86d1-71d35109f737","resolution":{"observed_at":"2026-08-07T12:23:07.354543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.169707Z","title":"Self-introspective de- coding: Alleviating hallucinations for large vision-language models","venue":null,"work_id":"ff272489-f583-4a7d-9fca-63dca1ea22dc","year":2025},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.006394Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:bd2b762ba722bec5d619a55353029dcd4674e65848972d5c59c06c9a33a8d372","observation_id":"ceb4bff2-b354-4d92-aa25-0a7caf0f667e","resolution":{"observed_at":"2026-08-07T12:23:07.227457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:07.076638Z","title":"Interpreting and editing vision-language representations to mitigate hallucinations","venue":null,"work_id":"eff475bd-bec7-4ebd-b45d-6559764c7d82","year":2025},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.127184Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:749068e0c2bb008bd2a9db0994b37eed41c7e5060b977813dc885bcace791c9d","observation_id":"ff8d98bb-993b-4dfa-937e-b03109cbb03f","resolution":{"observed_at":"2026-08-07T12:23:07.105246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.996182Z","title":"Glow: Generative flow with invertible 1x1 convolutions","venue":null,"work_id":"c4f32084-3153-45f0-981e-7bc77379a486","year":2018},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.184139Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:cbb9da0b5df32a2f07dda91a2cee07fb52d39dd5edce519aef6ea5165b8daef0","observation_id":"d3219d1f-9266-401d-b741-d5e36be95a1e","resolution":{"observed_at":"2026-08-07T12:23:07.040597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.812350Z","title":"Improved variational in- ference with inverse autoregressive flow.Advances in neural information processing systems, 2016","venue":null,"work_id":"25c086b9-83f9-4978-98b9-81befc3bda3d","year":2016},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.244340Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:e5d3f08b2778e64f7df4e940b781e85915f67c401def38595c13c2942d745b06","observation_id":"75fe310d-1285-4fd0-a910-5e931442626f","resolution":{"observed_at":"2026-08-07T12:23:06.906727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.702764Z","title":"Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding","venue":null,"work_id":"43941e6e-d135-4fcd-949a-cf148a6769cb","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.340851Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:fead98232f1e99345bec765d14bde13968dc7f5603266949e6a5f3cbc8c495d7","observation_id":"0d9a5397-3477-4672-9617-a4cbc3143228","resolution":{"observed_at":"2026-08-07T12:23:06.741493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.565745Z","title":"Multimodal foundation models: From specialists to general-purpose as- sistants","venue":null,"work_id":"1a7a8097-3e4a-4a40-ab0b-2ed184dbacb4","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.457461Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:79a99d466a838e2826e0115fde3203ed4a5e06898dfa4062b4c076d7f8f76e8e","observation_id":"eeb88ca9-1a04-451b-bfb7-a48c07caa4b2","resolution":{"observed_at":"2026-08-07T12:23:06.620553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:00.560613Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.560613Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:8d3d2863c6072fd3632178982522b5669945e0de1c4e16aaee90e1e412da6014","observation_id":"7aae60a9-cf3f-49f9-8d91-d88196b25bc4","resolution":{"observed_at":"2026-08-07T12:23:00.560613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.477544Z","title":"Contrastive decoding: Open-ended text genera- tion as optimization","venue":null,"work_id":"f18e8f9f-0808-4f32-bd13-0001d2363e81","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.681586Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:74a6257a11fe6c1356351386605df5b72a89de34c7052fba381e682fd748032e","observation_id":"91f12dcc-7575-404e-bb17-d058288abec2","resolution":{"observed_at":"2026-08-07T12:23:06.509005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.363412Z","title":"Evaluating object hallucination in large vision-language models","venue":null,"work_id":"86897880-5d42-4001-a0d2-f10d6774ce88","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.786686Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:861cacc1b9d874fe896edf9f8770fc916731b9655a9af94694eed8d16c603e06","observation_id":"5e4eb3f9-fdd2-408d-8231-d074d0c615c3","resolution":{"observed_at":"2026-08-07T12:23:06.409312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:00.900355Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.900355Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:f4ae1481c36e03e9e1e4fcf89c1736a33082be69f9ce5cc89c6ee54558de4573","observation_id":"7d990cfc-d6f4-41e5-b40a-41f48ed14ad7","resolution":{"observed_at":"2026-08-07T12:23:00.900355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.206900Z","title":"Visual instruction tuning","venue":null,"work_id":"f19e8bcd-ea93-43bb-848c-f9995c79c4e5","year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:00.985764Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:8f55f73f961f6bc400a9740f8247636a4875995d26512d1ba2aedb109fe96ace","observation_id":"9390405f-e6ee-4c41-8102-4f3c7ef13b08","resolution":{"observed_at":"2026-08-07T12:23:06.228561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:06.077789Z","title":"Improved baselines with visual instruction tuning","venue":null,"work_id":"6bcca9c5-ec17-4f59-b1e3-f761a296a7fc","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.045949Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:49afa7737b2f88183782ddce25119b436b1b2dd74d5ada6e3a854269b178a986","observation_id":"b0aa2a0e-cdd2-422d-b4ad-33c410718e7c","resolution":{"observed_at":"2026-08-07T12:23:06.122502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00253","last_updated":"2024-05-06T01:10:01Z","snapshot_observed_at":"2026-07-06T17:23:26.913214Z","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":"2026-08-07T12:23:01.151731Z","title":"A survey on hallucination in large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.151731Z"},"links":{"cited_paper":"/paper/2402.00253","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:4c58026e70f7e16f66a5395a150df59e4fffc3a723f393b1de2c75da42ba7896","observation_id":"7f43b886-a156-45e1-bcda-798f0af090cb","resolution":{"observed_at":"2026-08-07T12:23:01.151731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.923757Z","title":"Paying more at- tention to image: A training-free method for alleviating hal- lucination in lvlms","venue":null,"work_id":"da195374-1843-4a1b-8bbf-edbdef2aa216","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.313256Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:fb22b2209de201ab3e896479cc2e9ffc465de639dc96eaf69b996560cd3636fe","observation_id":"b3feb31c-de11-4147-9077-08bb2c524f48","resolution":{"observed_at":"2026-08-07T12:23:06.021160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.813427Z","title":"interpreting gpt: the logit lens","venue":null,"work_id":"89b68034-b4cb-4515-926c-aed95680dc37","year":2020},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.428215Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:7b956aea355c759921236598ac0446220c2781419daa9d18001721f8367b7777","observation_id":"98abfa77-9a44-483e-8db1-68ea1c463719","resolution":{"observed_at":"2026-08-07T12:23:05.843533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.711217Z","title":"Masked autoregressive flow for density estimation.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"a9b89461-853e-40f3-b9fe-3c7bb1d4676f","year":2017},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.562362Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:9b41dcb5dc3722808f5ec3c4282fd67ac3b7bc85f52f453745aac087ddb97c5f","observation_id":"583a9280-d379-4952-a521-8e1033a625d1","resolution":{"observed_at":"2026-08-07T12:23:05.771178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:01.639143Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.639143Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:9a5e510a243ed0f32b6869daebe86a080a2710457900115c6feff0f222d6d11f","observation_id":"4d3cb581-8617-43cb-9c89-211cc985df25","resolution":{"observed_at":"2026-08-07T12:23:01.639143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.537288Z","title":"Variational inference with normalizing flows","venue":null,"work_id":"b095228c-bf21-455a-a8f5-556883d87b67","year":2015},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.741810Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:91033c0fbe9835601f55c834cce88d000d61f4735af324ec7a3cef5aa4c2c3af","observation_id":"3cb19aad-e194-48f8-8a89-fc9ba3b4b84f","resolution":{"observed_at":"2026-08-07T12:23:05.622383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.491380Z","title":"Object hallucination in image cap- tioning","venue":null,"work_id":"4bd7f052-6269-405f-84de-555aafc2e6e0","year":2018},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.747950Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:b079b4bab5b471176882527fefe00b87d8f61701b13213b75767c624a93cdcf2","observation_id":"760f8706-3ef9-497c-9946-611aef31f117","resolution":{"observed_at":"2026-08-07T12:23:05.519576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.380487Z","title":"A comprehensive sur- vey of hallucination in large language, image, video and au- dio foundation models","venue":null,"work_id":"972a2bd3-ebcf-4ec2-a268-ed2dc428773f","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:01.910107Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:3ce9e27b3470d351311510f0f320820091203fb733a677672b38789b10aa1d5e","observation_id":"6db5ae45-afdf-4e59-8d9a-929d40afc151","resolution":{"observed_at":"2026-08-07T12:23:05.422094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.274677Z","title":"Trusting your evidence: Hallucinate less with context-aware decoding","venue":null,"work_id":"84845727-9ef5-4fe4-8fb2-8076d63c66a3","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.078300Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:17140bb791da17051b937aff5ea784f73f2ed00d39956fe9330579ee8651f8d5","observation_id":"87d0534d-cb0d-4f75-895f-a958114eaddc","resolution":{"observed_at":"2026-08-07T12:23:05.327331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.00361","last_updated":"2025-03-01T06:00:34Z","snapshot_observed_at":"2026-08-07T17:37:45.865748Z","submitted_at":"2025-03-01T06:00:34Z","title":"Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.00361","snapshot_observed_at":"2026-08-07T12:23:02.171286Z","title":"Octopus: Alleviating hal- lucination via dynamic contrastive decoding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.171286Z"},"links":{"cited_paper":"/paper/2503.00361","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:4e187c681154207af0d8fc63a7d5dbbb6cf839b9db28a303ef07d3d516ecb30e","observation_id":"aa46b50b-1f31-4bbf-898e-64ae73531de2","resolution":{"observed_at":"2026-08-07T12:23:02.171286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.205230Z","title":"Sequence to sequence learning with neural networks","venue":null,"work_id":"d1f1ae8f-e7fb-4f6c-96b4-781448bbb0e8","year":2014},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.327379Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:881e290644d0014ae5e3de52511e26625584bb651a585af95177ba5f2a842f8a","observation_id":"bee8a936-e9d9-40b4-9a21-a66fef24ae64","resolution":{"observed_at":"2026-08-07T12:23:05.246092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-07-06T17:41:42.995949Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-08-07T12:23:02.565551Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of con- text","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.565551Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:8a27f1c16dd72b7f69e83caacb16b8f3420d4472af56344aa3687a3bb02a7e06","observation_id":"62b7de11-c002-4835-8a4e-87c3226d728c","resolution":{"observed_at":"2026-08-07T12:23:02.565551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-07T12:23:02.720417Z","title":"Gemma: Open models based on gemini research and tech- nology","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.720417Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:74369960408f5b37201ef5aed46ad9f9d8bc0d7a8cbeb9499614b063ee1e176a","observation_id":"526d2d06-d50b-4fe2-af21-b3c623be0e41","resolution":{"observed_at":"2026-08-07T12:23:02.720417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:05.040007Z","title":"Gemma 2: Improving open language models at a practical size","venue":null,"work_id":"55276841-07ff-4cf8-9b8b-da339a5f9a02","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:02.865801Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:0da63ef80bd5283a7dcc602a38c455fd0b0cefec4e082b7411e6e22444957c2c","observation_id":"0907967a-7d72-43e1-bff8-e4476519668d","resolution":{"observed_at":"2026-08-07T12:23:05.196716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T12:23:03.039230Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.039230Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:50418eee54a59da9631197264f7b07655e4f459824c7c05abd626df670673867","observation_id":"fe80822e-109e-48b9-b33f-9b6ec236d682","resolution":{"observed_at":"2026-08-07T12:23:03.039230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T12:23:03.163335Z","title":"Llama 2: Open foundation and fine-tuned chat models.arXiv preprint arXiv:2307.09288, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.163335Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:6fc0c323e4c52f386b5304493e7ab9e73bb98f4308c62a385e5e22edc67c6b67","observation_id":"3352d8fb-e6bd-4263-b652-c98c8549de77","resolution":{"observed_at":"2026-08-07T12:23:03.163335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:04.816340Z","title":"Bimal: Bijective maximum likelihood approach to domain adaptation in se- mantic scene segmentation","venue":null,"work_id":"70bd7b75-244d-439d-8aea-db9d9bb0fb15","year":2021},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.202806Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:08fb5e2d481b513fda9cff5189b3fabdbabdb4c1a40178ba814b52316daa2ec1","observation_id":"57d6839c-9ce7-4f47-9052-b8bc67a85249","resolution":{"observed_at":"2026-08-07T12:23:04.926067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:04.563726Z","title":"Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution","venue":null,"work_id":"41adbe6d-9ea5-4f50-a579-1247b959a5ac","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.330611Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:38614d7d7976400bea7170395f6dfd5cf38586eabf03cc6c5b13366224bab04a","observation_id":"488722e4-3f46-443b-a58b-f47f4117d5a0","resolution":{"observed_at":"2026-08-07T12:23:04.595895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:04.261512Z","title":"Mitigating hallucinations in large vision-language models with instruction contrastive decoding","venue":null,"work_id":"32def859-1295-4f5c-834c-d46e2d350e9c","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.556051Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:483d3468448ab092e3bce8a99a254cbca772cb78afbac7820e09d3c8274d59d6","observation_id":"1a58cd93-6951-46ca-8147-7a9a2028e2ec","resolution":{"observed_at":"2026-08-07T12:23:04.431183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T12:23:03.680872Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.680872Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:f662df1f3d245c507d8cb27e8071ddd0560ffbe382becf05c0648e8e4ede63fc","observation_id":"0fefd3df-9a68-413f-b64d-f598d80b9fc4","resolution":{"observed_at":"2026-08-07T12:23:03.680872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:04.046114Z","title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","venue":null,"work_id":"175a45b8-4615-4342-90a0-95d050bcf26f","year":2024},"citing_paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:23:03.775891Z"},"links":{"citing_paper":"/paper/2505.24649"},"observation_digest":"sha256:9d4adb0300f8fb59041fd7c7cb934433b08af80b8f354700fab4c0fdeb303872","observation_id":"271f23de-592f-49e0-871d-0bb10be53fa1","resolution":{"observed_at":"2026-08-07T12:23:04.123266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.24649","last_updated":"2025-05-30T14:38:07Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T12:14:03.386566Z","submitted_at":"2025-05-30T14:38:07Z","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":35},"total_outbound_references":50},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2505.24649."}