{"as_of":"2026-08-22T01:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da85a791189adc163fe0372956416ed4c346f9302320cee7178e9a642d9174cb","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:18:22.977826Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.18311/citation-record","integrity":"/paper/2507.18311/integrity","json":"/paper/2507.18311/citation-record.json","paper":"/paper/2507.18311"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:18:21.566445Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.566445Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:4f2b418591b97e3822a8d3fc3f8e46f9c63f888a71baa95103169afb7245e22e","observation_id":"1b7a53e9-ee06-4bb7-8ca5-c4a91cf55b41","resolution":{"observed_at":"2026-08-15T18:18:21.566445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.11432","last_updated":"2021-11-22T18:59:55Z","snapshot_observed_at":"2026-07-06T12:11:02.119174Z","submitted_at":"2021-11-22T18:59:55Z","title":"Florence: A New Foundation Model for Computer Vision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.11432","snapshot_observed_at":"2026-08-15T18:18:21.676118Z","title":"Florence: A new foundation model for computer vision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.676118Z"},"links":{"cited_paper":"/paper/2111.11432","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:8ec3cfa5a7d5d873785494687a0339710ba05f05dd5b452576c10a01509ea5c1","observation_id":"0a273a13-3da5-4327-9ac7-555932e58ae2","resolution":{"observed_at":"2026-08-15T18:18:21.676118Z","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":"2026-08-15T18:18:24.740690Z","title":"Grounded language-image pre-training,","venue":null,"work_id":"90514293-d278-4b8b-b18b-b7252622e06d","year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.781805Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:0e0eaa323298235b54ad27299610731602be2502046f24faaf3b95ef7230b672","observation_id":"95f53601-84a5-4dae-a50a-68b5638b68fa","resolution":{"observed_at":"2026-08-15T18:18:24.748835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:24.705236Z","title":"Regionclip: Region-based language-image pretraining,","venue":null,"work_id":"15e963d8-1fc5-4dc2-ae96-31bd2e2eaacf","year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.790043Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:fb28cf7ee88ddde6b18b18d8f085522447969c33caf721feb05a773f7452a003","observation_id":"9b0c6902-b4e7-4d24-92da-06e1dcecd7fe","resolution":{"observed_at":"2026-08-15T18:18:24.715325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:24.543828Z","title":"Generalized decoding for pixel, image, and language,","venue":null,"work_id":"cc420492-1612-4c12-b843-530c9023be4b","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.797700Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:aeb04fc666fefe9bc57e5107cd572df48ec310a5c693b097a88f5ecd68032ef0","observation_id":"a79780fd-d54b-496e-9ae9-79357d68a275","resolution":{"observed_at":"2026-08-15T18:18:24.607101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03546","last_updated":"2022-04-03T03:33:43Z","snapshot_observed_at":"2026-08-01T06:14:31.660540Z","submitted_at":"2022-01-10T18:59:10Z","title":"Language-driven Semantic Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03546","snapshot_observed_at":"2026-08-15T18:18:21.803678Z","title":"Language-driven semantic segmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.803678Z"},"links":{"cited_paper":"/paper/2201.03546","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:9c4fc8f4d2f7372e2411da086c4f0edb912fc304a4f5163fd16456544067abeb","observation_id":"14a56748-080c-4cb3-b5d8-503c0dd48e8f","resolution":{"observed_at":"2026-08-15T18:18:21.803678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-08-21T16:02:41.546193Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-15T18:18:21.810989Z","title":"Qwen2. 5-vl technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.810989Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:4db428c951ca2186d0c8acf8b2e8f5cbae2925b07070ffe48309b843a46c8438","observation_id":"c6611f54-0e5d-4733-997e-a176473d1bb6","resolution":{"observed_at":"2026-08-15T18:18:21.810989Z","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":"2026-08-15T18:18:21.821249Z","title":"Taming transformers for high- resolution image synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.821249Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:9f59e713a1eb37e751469b248e9f56b315eccd026311b14af3884356815875eb","observation_id":"bda556c5-e5a4-4d41-9738-47a0c7303e89","resolution":{"observed_at":"2026-08-15T18:18:21.821249Z","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":"2026-08-15T18:18:21.888245Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:21.888245Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:196fe1d1598249ec0de65c6b2a31a07ae4b48f918bfc5528589f265648fc8099","observation_id":"e48aba71-56c9-467b-bed9-b63dd2512219","resolution":{"observed_at":"2026-08-15T18:18:21.888245Z","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":"2026-08-15T18:18:22.011003Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.011003Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:717a2c8c817d77382c399a9124219078a92d8bf3bcc5d35d528875bc64dddf77","observation_id":"3f69028a-45fe-4e10-bb29-65c6860091fa","resolution":{"observed_at":"2026-08-15T18:18:22.011003Z","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":"2026-08-15T18:18:22.101128Z","title":"Improving language understanding by generative pre-training,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.101128Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:18b22c2b8ef0e5a20b161da0e4838ac328d5f2a11fda40cfd6c11e239fa41138","observation_id":"dd41f4d7-ed7c-4c70-90eb-49376a5443a8","resolution":{"observed_at":"2026-08-15T18:18:22.101128Z","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":"2026-08-15T18:18:22.110573Z","title":"Language mod- els are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.110573Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:6ac8845edd1c7271df1e1be6205910d11f5750b72800231b2af1fcf23605800a","observation_id":"f5519ddc-d98e-468f-b61f-08a692b0c4e8","resolution":{"observed_at":"2026-08-15T18:18:22.110573Z","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":"2026-08-15T18:18:22.188247Z","title":"Palm: Scal- ing language modeling with pathways,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.188247Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:63186123be416f25de6a1ec988d616f798e7966e3792cf958e20b77018d0c7f4","observation_id":"13aa76bf-a208-4907-a1b9-6de632b9aa81","resolution":{"observed_at":"2026-08-15T18:18:22.188247Z","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":"2026-08-15T18:18:22.263075Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.263075Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:d1154e5a76907a7c2db04495cec272e8e49f6ea113aaa484a02637b04ecee042","observation_id":"246fc5a2-1785-4aa5-bb64-151f70404f48","resolution":{"observed_at":"2026-08-15T18:18:22.263075Z","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":"2026-08-15T18:18:24.287465Z","title":"Role of chat gpt in public health,","venue":null,"work_id":"fc737032-94b5-452c-a64e-390162b0867d","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.268481Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:5b22403669355cdddc1ee64db33aea099456fdfb67cd08e805d7610752cb3351","observation_id":"5a09ef39-ea11-427c-ab75-7e01eab04c1e","resolution":{"observed_at":"2026-08-15T18:18:24.355815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:22.273092Z","title":"Scaling up visual and vision-language representation learning with noisy text supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.273092Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:5270389265cd2e05c33f3cb877529b024d4c9fa2c66e62694e5557b11e7a1bc9","observation_id":"6b74f596-2779-428d-bde7-6246807a18e9","resolution":{"observed_at":"2026-08-15T18:18:22.273092Z","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":"2026-08-15T18:18:22.279741Z","title":"Visual instruction tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.279741Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:d554a1daa9d57f4ee46eb8b7e8eefbea7f435c7885f9b08a8e42317b8ae4282f","observation_id":"0b3b4db8-8132-4af8-ba1c-ba84e5d74687","resolution":{"observed_at":"2026-08-15T18:18:22.279741Z","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":"2026-08-15T18:18:24.206352Z","title":"Instructblip: Towards general-purpose vision- language models with instruction tuning,","venue":null,"work_id":"98c8a111-1522-42af-9d29-fb09693e05cb","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.443265Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:9cb52efc8bc2205376f36dc8bfd12bc4cb6f9fe108b524ff5bc7e3047cace14c","observation_id":"137f4753-54f9-439a-a2d7-39fbc1e6e486","resolution":{"observed_at":"2026-08-15T18:18:24.214296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:24.182573Z","title":"The art of artificial intelligence: Themes and case studies of knowledge engineering,","venue":null,"work_id":"a7f697d0-06f1-41cf-ba1d-57ae67707229","year":1977},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.451861Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:4f6905f1bf41ead457f8f3d93c09d5934da88b8dd334bb5035092956b3157789","observation_id":"0caab068-45d5-4033-bea0-25fdbaf689a2","resolution":{"observed_at":"2026-08-15T18:18:24.188510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:24.152360Z","title":"Large language models for scientific discovery in molecular property prediction,","venue":null,"work_id":"766c2540-a99d-42b9-b7a8-4c950457fb13","year":2025},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.463489Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:3f1bdb4f77c1a5d094768ae3751287aadfbbe795ed3803f2113b9fdf7e05eda6","observation_id":"4788aa79-1087-49ea-8ad2-5b2cabdbbfe0","resolution":{"observed_at":"2026-08-15T18:18:24.163107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:23.959793Z","title":"Unsupervised word embeddings capture latent knowledge from materials science literature,","venue":null,"work_id":"d5c69ae5-bc55-467e-9f80-ef89688d2a7d","year":2019},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.567702Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:c931f9fb7a1e61266f737f5a547a7e10c98fea13864430a77b8165eb958e8385","observation_id":"42ab902f-4ecf-46cc-b18e-919769ae09d1","resolution":{"observed_at":"2026-08-15T18:18:24.064530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:22.691111Z","title":"Highly accurate protein structure prediction with alphafold,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.691111Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:9f8963042299386cc7725086d4fcce69609debbd37020c8c4dde5d74fdf08797","observation_id":"33be2691-f9e8-4dc1-9aca-423a9c35ea40","resolution":{"observed_at":"2026-08-15T18:18:22.691111Z","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":"2026-08-15T18:18:22.698307Z","title":"Improving clip training with language rewrites,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.698307Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:1ff5796c5c15177395adcd74ad51bb36bcb8e61f606ad58e871d047f18f7a713","observation_id":"4ad6e46b-0f0a-4f94-97e1-f89ca7eeef61","resolution":{"observed_at":"2026-08-15T18:18:22.698307Z","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":"2026-08-15T18:18:23.847227Z","title":"Datacomp: In search of the next generation of multimodal datasets,","venue":null,"work_id":"5db6cf83-797c-4a3d-8a35-b35c0a7b2bd4","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.707858Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:110e33026265eeb5c3a0ce7415ba8dfaa702253cece36202470c8f1f7960bd73","observation_id":"ad7a91b9-c93e-46ca-a428-254cb2d68e6c","resolution":{"observed_at":"2026-08-15T18:18:23.894751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:23.667206Z","title":"From scarcity to efficiency: Improving clip training via visual-enriched captions,","venue":null,"work_id":"42d3e5dc-e881-4f38-a577-1ce876d3d5a3","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.745980Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:c3f6366be66161f94b3a1498c4cc7d9a4c55d9cce15c37db9be3dfc1ed14c602","observation_id":"9c32cad9-26a6-4faa-84fd-928d4f677761","resolution":{"observed_at":"2026-08-15T18:18:23.707326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:23.541244Z","title":"Improv- ing multimodal datasets with image captioning,","venue":null,"work_id":"15c66a97-2ef3-4078-adce-c00dd9feb096","year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.783709Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:8f2eb2131ec1795e79c9f442467ae094e18ebbf255cabde6a4b46d6c8d995e59","observation_id":"12bbb6a0-4206-4baf-a944-e4312bcf8894","resolution":{"observed_at":"2026-08-15T18:18:23.597154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T18:18:22.802016Z","title":"Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.802016Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:20ce1e56090566ab4f2dcb0d68232328940617d066df5858eef958da9395c95d","observation_id":"9e39ce4d-bccf-4ca9-a8c8-cf7d455a03c8","resolution":{"observed_at":"2026-08-15T18:18:22.802016Z","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":"2026-08-15T18:18:22.812432Z","title":"Laion- 5b: An open large-scale dataset for training next generation image-text models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.812432Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:034cf1f53ba655999a1cef01348e9a60963b88493489f7ecd21f513629d6664a","observation_id":"5d1a63a6-2e68-42a1-af6a-21185ecef5a1","resolution":{"observed_at":"2026-08-15T18:18:22.812432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11931","last_updated":"2024-06-17T13:51:35Z","snapshot_observed_at":"2026-08-14T04:42:19.578053Z","submitted_at":"2024-06-17T13:51:35Z","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11931","snapshot_observed_at":"2026-08-15T18:18:22.820665Z","title":"Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.820665Z"},"links":{"cited_paper":"/paper/2406.11931","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:ce80d34000859c9408ec78e41c4d74ccd2c35492926b6ae1250eb2c23491a46b","observation_id":"3e6bbfb4-c8d0-4fd9-bc3e-2d01cff555f5","resolution":{"observed_at":"2026-08-15T18:18:22.820665Z","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":"2026-08-15T18:18:22.827517Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.827517Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:23bd651a937e586c8971bc86c0eaaeabd096f2dd7cf2c760d606e426595edd65","observation_id":"21c45bc8-f1c9-4a5f-bb7c-8f53f2718f19","resolution":{"observed_at":"2026-08-15T18:18:22.827517Z","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":"2026-08-15T18:18:22.835651Z","title":"Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.835651Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:c6eb225a74fb5d0bbfec197fd13bbbd39765db755eb461ecf507a70223e8a137","observation_id":"8e924263-64ba-400c-9332-909cd2dd9d82","resolution":{"observed_at":"2026-08-15T18:18:22.835651Z","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":"2026-08-15T18:18:22.918407Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.918407Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:cf1c44c2871d0589e670374c5846b44858e2a41a0f6ef78ad89e9303604fab23","observation_id":"934a687b-28e1-4b5a-961e-e7d6520966cc","resolution":{"observed_at":"2026-08-15T18:18:22.918407Z","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":"2026-08-15T18:18:23.326086Z","title":"[Online]","venue":null,"work_id":"b89fde83-94ac-49d6-8f2e-4fe4013c8ea1","year":2024},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.926065Z"},"links":{"citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:6f47281641d55732f7339fe5d3846c5dd2e9e22c6c5bd45ef9d1d3290e93fcb9","observation_id":"6894e678-b195-4d0e-93bc-2d265002a1c7","resolution":{"observed_at":"2026-08-15T18:18:23.388167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18032","last_updated":"2024-09-26T16:38:48Z","snapshot_observed_at":"2026-08-19T14:40:17.256368Z","submitted_at":"2024-09-26T16:38:48Z","title":"FlowBench: A Large Scale Benchmark for Flow Simulation over Complex Geometries","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18032","snapshot_observed_at":"2026-08-15T18:18:22.934531Z","title":"Flowbench: A large scale benchmark for flow simulation over complex geometries,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.934531Z"},"links":{"cited_paper":"/paper/2409.18032","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:7bff5c0871ef5e420672ac94dbdb6a67ee516cb2ef837134ee498e1a29f9f9cd","observation_id":"18cb63fa-bd58-41a9-9cc8-ed2b1677ee81","resolution":{"observed_at":"2026-08-15T18:18:22.934531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05963","last_updated":"2024-02-23T16:39:40Z","snapshot_observed_at":"2026-08-19T11:17:43.771047Z","submitted_at":"2023-09-13T06:30:08Z","title":"CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05963","snapshot_observed_at":"2026-08-15T18:18:22.977826Z","title":"Cfdbench: A large-scale bench- mark for machine learning methods in fluid dynamics,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:18:22.977826Z"},"links":{"cited_paper":"/paper/2310.05963","citing_paper":"/paper/2507.18311"},"observation_digest":"sha256:3437a703263efb8d42a01557bd1ae25d88d577878e4be7c0207398566ee6d0cf","observation_id":"79bb54be-9909-43ac-b3de-af478645efdb","resolution":{"observed_at":"2026-08-15T18:18:22.977826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.18311","last_updated":"2026-07-24T08:07:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-21T17:02:09.936557Z","submitted_at":"2025-07-24T11:28:53Z","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":35},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2507.18311."}