{"as_of":"2026-08-03T22:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e985ac278821f274f21db7561223b34992dd04b42f2bd6e9cd4a112f69e2ad68","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":22,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T02:55:23.411003Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T08:49:41.640745Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2503.10615","last_updated":"2025-03-18T08:52:34Z","snapshot_observed_at":"2026-07-06T20:52:09.743730Z","submitted_at":"2025-03-13T17:56:05Z","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-16T00:19:20.462455Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2503.10615"},"observation_digest":"sha256:a0f16b33f2386a14c1ed3d265e4dc19d33b169ef8e56392d37119e93e74b8bc5","observation_id":"d3d2f3e0-0ea2-4655-82f3-ded6840c9ba8","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2505.06698","last_updated":"2026-05-01T06:37:35Z","snapshot_observed_at":"2026-07-06T21:21:57.650402Z","submitted_at":"2025-05-10T16:52:40Z","title":"SCAN: Structured Capability Assessment and Navigation for LLMs","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-22T16:11:36.613334Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2505.06698"},"observation_digest":"sha256:c1077f4847977d28481d5622a3efc3caa2d1404e1d31e9f55260e09bdaf13756","observation_id":"34766d48-582d-4b35-a054-ef7c618cf600","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2505.07062","last_updated":"2025-05-11T17:28:30Z","snapshot_observed_at":"2026-08-02T16:13:31.498470Z","submitted_at":"2025-05-11T17:28:30Z","title":"Seed1.5-VL Technical Report","version":1},"reference_index":114,"source":"pdf_text","source_observed_at":"2026-05-11T05:26:04.960844Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2505.07062"},"observation_digest":"sha256:21f1f089b632a77b6c4f05ac1de19befbd3e791f818a32b53930f582338d8a1d","observation_id":"e3f32080-9df0-49f2-8ed2-11638ecb1d4e","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2507.01006","last_updated":"2026-01-01T13:07:25Z","snapshot_observed_at":"2026-08-03T18:50:30.558321Z","submitted_at":"2025-07-01T17:55:04Z","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","version":6},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-11T04:48:26.355351Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2507.01006"},"observation_digest":"sha256:746c44650b254ef99382820b0e457ca1e91baa3a649a4325bc5511d246e490ae","observation_id":"72ce693f-81b5-4041-8af2-6027aa1b2613","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2507.06261","last_updated":"2025-12-19T14:25:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-07T17:36:04Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","version":6},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-05-19T05:48:02.828938Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2507.06261"},"observation_digest":"sha256:46f4f146da57c7814458f1b372619bca55d7f8b5e16c062284e4c422e3b31d55","observation_id":"1e5d77b1-ae26-4692-935b-c591748238e0","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2602.02276","last_updated":"2026-02-02T16:17:38Z","snapshot_observed_at":"2026-07-06T22:44:09.804048Z","submitted_at":"2026-02-02T16:17:38Z","title":"Kimi K2.5: Visual Agentic Intelligence","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-10T16:09:05.225767Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2602.02276"},"observation_digest":"sha256:c7ea0d1892a7a4311019a33f4fabeedb3fa7a347f392fc86baa44bf7d24e2679","observation_id":"f6b1e8b0-932f-4649-a42a-c00b089b2f09","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2603.20633","last_updated":"2026-04-17T08:57:17Z","snapshot_observed_at":"2026-07-06T22:49:57.103822Z","submitted_at":"2026-03-21T04:03:45Z","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-15T07:44:02.827006Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2603.20633"},"observation_digest":"sha256:7c374a4346043bbd06a308635c3dde85ccfcf3b79ec28d73c553857bdf417703","observation_id":"fbd72c36-3362-4fad-a307-7bb6779e68a9","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2604.03128","last_updated":"2026-04-08T08:22:36Z","snapshot_observed_at":"2026-08-03T04:49:13.270533Z","submitted_at":"2026-04-03T15:50:07Z","title":"Self-Distilled RLVR","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-13T19:43:46.623267Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.03128"},"observation_digest":"sha256:a07de065247ec8d0dff500cf1e83b358db0ffa31457abd9a4df61b20c3f29c5c","observation_id":"7eed3b2b-8d9c-4ee8-9ac6-a42438f9b796","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2604.10219","last_updated":"2026-05-28T16:20:33Z","snapshot_observed_at":"2026-08-01T16:49:58.717615Z","submitted_at":"2026-04-11T13:59:05Z","title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-10T16:03:15.222571Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.10219"},"observation_digest":"sha256:2a9dd59f64e1d70151bcf9a5a6d6a32138831c2069cd5c6cf53cd787ded8b041","observation_id":"e2b0a151-a2cf-4c5c-9912-ebf4ada0572b","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-12T22:48:45.647588Z","title":"Zerobench: An impossible visual benchmark for contemporary large multimodal models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.10219","last_updated":"2026-05-28T16:20:33Z","snapshot_observed_at":"2026-08-01T16:49:58.717615Z","submitted_at":"2026-04-11T13:59:05Z","title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-07-12T22:48:45.647588Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.10219"},"observation_digest":"sha256:5bccef8b084e3f16bb346f607c36232e4494f29611f30c56ad6fdae1cddc4651","observation_id":"550446f8-6f7c-4807-91e4-2dbc659f2889","resolution":{"observed_at":"2026-07-12T22:48:45.647588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2604.15804","last_updated":"2026-04-21T03:35:14Z","snapshot_observed_at":"2026-08-01T22:56:50.755050Z","submitted_at":"2026-04-17T08:05:46Z","title":"Qwen3.5-Omni Technical Report","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T08:11:22.402552Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.15804"},"observation_digest":"sha256:8afbb289ad00f79ebaeb097c08f41aeffa09374c0c6fc477e971f550b5f90157","observation_id":"fb8cab9e-44fe-49df-b047-586e83a01698","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2604.20733","last_updated":"2026-04-22T16:20:41Z","snapshot_observed_at":"2026-07-06T23:07:25.185196Z","submitted_at":"2026-04-22T16:20:41Z","title":"Near-Future Policy Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T00:51:36.580600Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.20733"},"observation_digest":"sha256:bc26a61eeb8c6db1a32f9bf7bbc179e8329bd2b23b0d79d92be1c4724fb3822c","observation_id":"3d0e8800-e10b-491f-b257-ef0e97432a72","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2604.27083","last_updated":"2026-04-29T18:24:11Z","snapshot_observed_at":"2026-07-06T23:12:38.453388Z","submitted_at":"2026-04-29T18:24:11Z","title":"Co-Evolving Policy Distillation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-07T08:23:41.819485Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2604.27083"},"observation_digest":"sha256:13d38ef97c3db1f3a5958a3406fac5dfe98546de1ced71332556eaa53db41681","observation_id":"59bade78-b347-4887-87ec-819ddbbc3e3d","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2605.30265","last_updated":"2026-05-28T17:27:55Z","snapshot_observed_at":"2026-08-01T22:14:47.638279Z","submitted_at":"2026-05-28T17:27:55Z","title":"LoMo: Local Modality Substitution for Deeper Vision-Language Fusion","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T08:20:05.081980Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2605.30265"},"observation_digest":"sha256:9a32b5f8107c33c63d5384dff6fa3aebd7753a4a0a7d73f6c16d0be9607ba79b","observation_id":"4bbfcb8f-eadb-4b75-a59b-a251d94b360b","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2606.03087","last_updated":"2026-06-02T03:17:34Z","snapshot_observed_at":"2026-07-06T23:43:22.513369Z","submitted_at":"2026-06-02T03:17:34Z","title":"Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR","version":1},"reference_index":128,"source":"arxiv_source","source_observed_at":"2026-06-28T11:50:00.954670Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2606.03087"},"observation_digest":"sha256:81a22e77a33393656b07dc3faeae82d898fd08f76e8732f38abf946f9938131f","observation_id":"263ef561-e9fc-44e6-819e-76f2f5c527ef","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2606.06538","last_updated":"2026-06-04T01:11:21Z","snapshot_observed_at":"2026-08-02T18:50:27.808385Z","submitted_at":"2026-06-04T01:11:21Z","title":"WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark","version":1},"reference_index":144,"source":"arxiv_source","source_observed_at":"2026-06-28T03:04:31.607329Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2606.06538"},"observation_digest":"sha256:50afd32a8aeb8fef98610f6530c7504c5f4581dd4805f14d3b08bbb97e6e497a","observation_id":"07df2b79-d2d4-4633-b939-2629537ab74e","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2606.07639","last_updated":"2026-06-01T09:07:15Z","snapshot_observed_at":"2026-07-06T23:47:15.041928Z","submitted_at":"2026-06-01T09:07:15Z","title":"MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-28T15:22:31.310003Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2606.07639"},"observation_digest":"sha256:7eb7b8ee7ddcaa76d43e03e8371747f992a15e8ee7f2aa5831271337a3f80e4b","observation_id":"a0a912cf-793d-4413-8cd4-8a37758a026f","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2606.10651","last_updated":"2026-06-09T09:58:08Z","snapshot_observed_at":"2026-07-06T23:49:51.672382Z","submitted_at":"2026-06-09T09:58:08Z","title":"Kwai Keye-VL-2.0 Technical Report","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-06-27T13:53:10.352603Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2606.10651"},"observation_digest":"sha256:b6d1cd6807fd5481f3fa2965219c0312d5be8894775c509779d2c9ed8f201908","observation_id":"a48ec12d-9f72-41da-94b8-f208e36eb6d8","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2606.22437","last_updated":"2026-06-25T12:10:03Z","snapshot_observed_at":"2026-08-03T04:49:13.185870Z","submitted_at":"2026-06-21T10:57:43Z","title":"MMGist: A Comprehensive Multimodal Benchmark for 2027","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-26T11:05:14.573386Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2606.22437"},"observation_digest":"sha256:339807540b17db4ff37534dd3d79d7eead26f1f027a4b2f1baf45023bbbddb47","observation_id":"2540585a-dd82-44aa-9c22-21aa383415c9","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":"2502.09696","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-08T01:19:04.778549Z","title":"Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma, Akash Gupta, Samuel Roberts, Ioana Croitoru, Simion-Vlad Bogolin, Jialu Tang, Flo- rian Langer, Vyas Raina, and 1 others","venue":null,"work_id":"33b36799-0b42-4ac7-893c-5fc4a26c671c","year":2025},"citing_paper":{"arxiv_id":"2607.00248","last_updated":"2026-06-30T22:57:43Z","snapshot_observed_at":"2026-08-03T15:00:12.134373Z","submitted_at":"2026-06-30T22:57:43Z","title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-07-02T18:57:46.841456Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2607.00248"},"observation_digest":"sha256:0247a64ee6293c7a150c572a6e820a554422a897c4458f2d85c5f439f45fe735","observation_id":"0f0806fb-8a45-4f6e-80d4-a406a98866c3","resolution":{"observed_at":"2026-07-08T01:19:04.778549Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-07-31T05:01:29.035002Z","title":"arXiv preprint arXiv:2502.09696 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24957","last_updated":"2026-07-27T18:04:54Z","snapshot_observed_at":"2026-08-01T22:57:25.487048Z","submitted_at":"2026-07-27T18:04:54Z","title":"PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-31T05:01:29.035002Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2607.24957"},"observation_digest":"sha256:810696f66cea3674894c64aad24d07aa03e2e3b56ebe629ffb594ca2a7f8af11","observation_id":"4f6d477b-d9a0-4c0e-9363-d00355a128cb","resolution":{"observed_at":"2026-07-31T05:01:29.035002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09696","snapshot_observed_at":"2026-08-01T02:55:23.411003Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25294","last_updated":"2026-07-28T05:06:43Z","snapshot_observed_at":"2026-08-02T22:32:42.294850Z","submitted_at":"2026-07-28T05:06:43Z","title":"CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-01T02:55:23.411003Z"},"links":{"cited_paper":"/paper/2502.09696","citing_paper":"/paper/2607.25294"},"observation_digest":"sha256:f47c90ed9570f0e790f3cc8436c200124bf4e5154ba03cf67d5ca95ccaf8ec2e","observation_id":"4af62350-4877-4c2b-b949-36e3c2447264","resolution":{"observed_at":"2026-08-01T02:55:23.411003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.09696/citation-record","integrity":"/paper/2502.09696/integrity","json":"/paper/2502.09696/citation-record.json","paper":"/paper/2502.09696"},"outbound":[],"paper":{"arxiv_id":"2502.09696","last_updated":"2026-07-07T14:07:33Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T11:27:21.448208Z","submitted_at":"2025-02-13T18:59:11Z","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 3 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2502.09696."}